save

aaa_helpers.txt

@@ -23,9 +23,11 @@ nohup python cvae.py --name="lhunor_abl_all" > nohup/iccv/ablation/abl_all_3.out
 nohup python cvae.py --name="lhunor_abl_all_gnn" > nohup/iccv/ablation/abl_all_gnn.out 2>&1 &
 nohup python cvae.py --name="lhunor_abl_all_gnn_2" > nohup/iccv/ablation/abl_all_gnn.out 2>&1 &
 
-nohup python cvae.py --name="lhunor_abl_all_cape_f" > nohup/iccv/ablation/abl_all_cape_f.out 2>&1 &
+nohup python cvae.py --name="lhunor_abl_all_cape_f" > nohup/iccv/ablation/abl_all_cape_f_2.out 2>&1 &
 
 nohup python cvae.py --name="lhunor_abl_all_skirt" > nohup/iccv/ablation/abl_all_skirt.out 2>&1 &
+nohup python cvae.py --name="lhunor_abl_all_skirt_var" > nohup/iccv/ablation/abl_all_skirt_var.out 2>&1 &
+nohup python cvae.py --name="lhunor_abl_all_skirt_var" > nohup/iccv/ablation/abl_all_skirt_var_2.out 2>&1 &
 nohup python cvae.py --name="lhunor_abl_curv" > nohup/iccv/ablation/abl_curv.out 2>&1 &
 nohup python cvae.py --name="lhunor_abl_curv_skirt" > nohup/iccv/ablation/abl_curv_skirt.out 2>&1 &
 nohup python cvae.py --name="lhunor_abl_skin" > nohup/iccv/ablation/abl_skin.out 2>&1 &
@@ -39,7 +41,10 @@ nohup python cvae.py --name="lhunor_abl_skin_reg" > nohup/iccv/ablation/abl_skin
 nohup python cvae.py --name="lhunor_abl_skin_reg_skirt" > nohup/iccv/ablation/abl_skin_reg_skirt.out 2>&1 &
 nohup python cvae.py --name="lhunor_abl_skin_var" > nohup/iccv/ablation/abl_skin_var.out 2>&1 &
 
-nohup python cvae_curv.py --name="lhunor_cvae_curv" > nohup/iccv/ablation/cvae_curv.out 2>&1 &
+nohup python evaluate_ae.py --name abl_all > nohup/iccv/evaluate/abl_all.out 2>&1 &
+nohup python evaluate_ae.py --name abl_all_skirt > nohup/iccv/evaluate/abl_all_skirt.out 2>&1 &
+
+nohup python cvae_curv.py --name="lhunor_cvae_curv" > nohup/iccv/ablation/cvae_curv_3.out 2>&1 &
 
 nohup python upscale_test.py --name="iccv_32_2" > nohup/iccv/upscale/iccv_32_2.out 2>&1 &
 nohup python upscale_test.py --name="iccv_64_2" > nohup/iccv/upscale/iccv_64_2.out 2>&1 &
@@ -70,14 +75,26 @@ nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_curv" > nohup/iccv/pyr/i
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_curv_skirt" > nohup/iccv/pyr/iccv_pyr_32_curv_skirt.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_reg" > nohup/iccv/pyr/iccv_pyr_32_reg.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_reg_skirt" > nohup/iccv/pyr/iccv_pyr_32_reg_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_10p" > nohup/iccv/pyr/iccv_pyr_32_10p.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_25p" > nohup/iccv/pyr/iccv_pyr_32_25p.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_jumpsuit" > nohup/iccv/pyr/iccv_pyr_32_jumpsuit.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_trousers" > nohup/iccv/pyr/iccv_pyr_32_trousers.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_top" > nohup/iccv/pyr/iccv_pyr_32_top.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_tshirt" > nohup/iccv/pyr/iccv_pyr_32_tshirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skirt_skirt" > nohup/iccv/pyr/iccv_pyr_32_skirt_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skirt_dress" > nohup/iccv/pyr/iccv_pyr_32_skirt_dress.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skirt_batch" > nohup/iccv/pyr/iccv_pyr_32_skirt_batch.out 2>&1 &
 
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64" > nohup/iccv/pyr/iccv_pyr_32_64.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_skin" > nohup/iccv/pyr/iccv_pyr_32_64_skin.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_skin" > nohup/iccv/pyr/iccv_pyr_32_64_skin.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_skin_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_skin_skirt.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_curv" > nohup/iccv/pyr/iccv_pyr_32_64_curv.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_curv_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_curv_skirt.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_reg" > nohup/iccv/pyr/iccv_pyr_32_64_reg.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_reg_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_reg_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_10p" > nohup/iccv/pyr/iccv_pyr_32_64_10p.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_25p" > nohup/iccv/pyr/iccv_pyr_32_64_25p.out 2>&1 &
 
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_f" > nohup/iccv/pyr/iccv_pyr_64_cape_f.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_m" > nohup/iccv/pyr/iccv_pyr_64_cape_m.out 2>&1 &
@@ -85,16 +102,39 @@ nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_m_00032_SL" > nohup
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_f_03223_SL" > nohup/iccv/pyr/iccv_pyr_64_cape_f_03223_SL.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_f_03223_SS" > nohup/iccv/pyr/iccv_pyr_64_cape_f_03223_SS.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_128_cape_f" > nohup/iccv/pyr/iccv_pyr_64_128_cape_f.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_128_cape_m" > nohup/iccv/pyr/iccv_pyr_64_128_cape_m.out 2>&1 &
+
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_128_256_cape_f" > nohup/iccv/pyr/iccv_pyr_64_128_256_cape_f.out 2>&1 &
 
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_pre_cape_f" > nohup/iccv/pyr/iccv_pyr_64_pre_cape_f.out 2>&1 &
 
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128" > nohup/iccv/pyr/iccv_pyr_32_64_128.out 2>&1 &
 nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_skirt.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_skin" > nohup/iccv/pyr/iccv_pyr_32_64_128_skin.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_skin" > nohup/iccv/pyr/iccv_pyr_32_64_128_skin_2.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_reg" > nohup/iccv/pyr/iccv_pyr_32_64_128_reg.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_skin_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_skin_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_reg" > nohup/iccv/pyr/iccv_pyr_32_64_128_reg_2.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_curv" > nohup/iccv/pyr/iccv_pyr_32_64_128_curv.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_curv_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_curv_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_var" > nohup/iccv/pyr/iccv_pyr_32_64_128_var.out 2>&1 &
 
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256" > nohup/iccv/pyr/iccv_pyr_32_64_128_256.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_128_cape_m_00032_SL" > nohup/iccv/pyr/iccv_pyr_64_128_cape_m_00032_SL.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_128_cape_f_03223_SL" > nohup/iccv/pyr/iccv_pyr_64_128_cape_f_03223_SL.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_128_cape_f_03223_SS" > nohup/iccv/pyr/iccv_pyr_64_128_cape_f_03223_SS.out 2>&1 &
+
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_2.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_skirt_2.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_skin" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_skin.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_curv" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_curv.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_curv_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_curv_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_reg" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_reg.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_seq_2_fine" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_seq_2_fine.out 2>&1 &
+
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_skirt.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_skin" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_skin.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_curv" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_curv.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_reg" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_reg.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_64_128_256_512_fine" > nohup/iccv/pyr/iccv_pyr_32_64_128_256_512_fine.out 2>&1 &
 
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32 > nohup/iccv/evaluate/iccv_pyr_32.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_skirt > nohup/iccv/evaluate/iccv_pyr_32_skirt.out 2>&1 &
@@ -104,18 +144,43 @@ nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_reg > nohup/i
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_reg_skirt > nohup/iccv/evaluate/iccv_pyr_32_reg_skirt.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_curv > nohup/iccv/evaluate/iccv_pyr_32_curv.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_curv_skirt > nohup/iccv/evaluate/iccv_pyr_32_curv_skirt.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_10p > nohup/iccv/evaluate/iccv_pyr_32_10p.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_25p > nohup/iccv/evaluate/iccv_pyr_32_25p.out 2>&1 &
 
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64 > nohup/iccv/evaluate/iccv_pyr_32_64.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_skin > nohup/iccv/evaluate/iccv_pyr_32_64_skin.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_skin_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_skin_skirt.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_reg > nohup/iccv/evaluate/iccv_pyr_32_64_reg.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_skirt.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_curv > nohup/iccv/evaluate/iccv_pyr_32_64_curv.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_curv_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_curv_skirt.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_10p > nohup/iccv/evaluate/iccv_pyr_32_64_10p.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_25p > nohup/iccv/evaluate/iccv_pyr_32_64_25p.out 2>&1 &
 
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128 > nohup/iccv/evaluate/iccv_pyr_32_64_128.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_128_skirt.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_skin > nohup/iccv/evaluate/iccv_pyr_32_64_128_skin.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_skin_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_128_skin_skirt.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_reg > nohup/iccv/evaluate/iccv_pyr_32_64_128_reg.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_curv > nohup/iccv/evaluate/iccv_pyr_32_64_128_curv.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_curv_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_128_curv_skirt.out 2>&1 &
 
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256 > nohup/iccv/evaluate/iccv_pyr_32_64_128_256.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_seq > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_seq.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_skirt.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_skin > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_skin.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_curv > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_curv.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_reg > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_reg.out 2>&1 &
 
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_512 > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_512.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_512_skirt > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_512_skirt.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_512_reg > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_512_reg.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_512_skin > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_512_skin.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_128_256_512_curv > nohup/iccv/evaluate/iccv_pyr_32_64_128_256_512_curv.out 2>&1 &
+
+nohup python cvae.py --name="lhunor_cape_f_03223_SL" > nohup/iccv/ablation/abl_all_cape_f_03223_SL.out 2>&1 &
+nohup python cvae.py --name="lhunor_cape_f_03223_SS" > nohup/iccv/ablation/abl_all_cape_f_03223_SS.out 2>&1 &
+nohup python cvae.py --name="lhunor_cape_m_00032_SL" > nohup/iccv/ablation/abl_all_cape_m_00032_SL.out 2>&1 &
 
 
 

calculate_error.py

@@ -1,37 +1,37 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_64_skin import config
+from configs.iccv.config_abl_pyr_32_64_128_seq import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
-# import tensorflow as tf
+import tensorflow as tf
 
-# gpus = tf.config.experimental.list_physical_devices('GPU')
+gpus = tf.config.experimental.list_physical_devices('GPU')
-# if gpus:
+if gpus:
-#     try:
+    try:
-#         # Currently, memory growth needs to be the same across GPUs
+        # Currently, memory growth needs to be the same across GPUs
-#         for gpu in gpus:
+        for gpu in gpus:
-#             tf.config.experimental.set_memory_growth(gpu, True)
+            tf.config.experimental.set_memory_growth(gpu, True)
-#         logical_gpus = tf.config.experimental.list_logical_devices('GPU')
+        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
-#         print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
+        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
-#     except RuntimeError as e:
+    except RuntimeError as e:
-#         # Memory growth must be set before GPUs have been initialized
+        # Memory growth must be set before GPUs have been initialized
-#         print(e)
+        print(e)
 
 import csv
 import glob
 import time
 import argparse
 import wandb
-import tqdm
+from tqdm import tqdm
 import random
 import numpy as np
 import plotly.graph_objects as go
 import plotly.express as ex
-
+from losses import collision_loss, normal_loss
-# if config['is_skirt']:
+if config['is_skirt']:
-#     from losses import edge_loss_skirt as edge_loss
+    from losses import edge_loss_skirt as edge_loss
-# else:
+else:
-#     from losses import edge_loss
+    from losses import edge_loss
 
 
 
@@ -53,9 +53,13 @@ if __name__ == '__main__':
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())
 
+    print(config['name'])
+
     # smpl = SMPL(use_one_hot=config['use_one_hot'])
     skirt_modifier = '_skirt' if config['is_skirt'] else ''
 
+    error_type = 'euclidean' # 'euclidean' 'collision' edge normal
+
     folder = config['test_dir']
 
     checkpoint_name = config['name']
@@ -68,7 +72,7 @@ if __name__ == '__main__':
     output_folder = '/home/workspace/local-data/results/iccv/' + checkpoint_name + '-'
     # check if there is a folder that starts with this name using glob
     folders = glob.glob(output_folder + '*')
-    assert len(folders) == 1, 'There should be only one checkpoint that starts with this name'
+    assert len(folders) == 1, f'There should be only one checkpoint that starts with this name, but found {len(folders)}'
     output_folder = folders[0]
     iteration = output_folder.split('-')[-1]
 
@@ -78,6 +82,7 @@ if __name__ == '__main__':
     # ids = [id.split('.')[0] for id in ids]
     # faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
 
+    print('Reading masks...')
     masks_folder = '/home/workspace/local-data' + ('' if config['is_skirt'] else '_127') + '/test' + ('_skirt' if config['is_skirt'] else '') + '_ready' + ('_2' if config['is_skirt'] else '') + '/mesh_mask'
     ids = os.listdir(masks_folder)
     ids = [id.split('.')[0] for id in ids]
@@ -85,6 +90,11 @@ if __name__ == '__main__':
 
     frames = os.listdir(output_folder)
     frames = [frame for frame in frames if not frame.endswith('_fixed_coll.npy')]
+    # frames = frames[:100]
+
+    # print('Reading bodies...')
+    # bodies_folder = '/home/workspace/local-data' + ('' if config['is_skirt'] else '_127') + '/test' + ('_skirt' if config['is_skirt'] else '') + '_ready' + ('_2' if config['is_skirt'] else '') + '/mesh_posed_body_no_orient'
+    # bodies = {frame : np.load(bodies_folder + '/' + frame[:-1] + 'z')['mesh_posed_body_no_orient'] for frame in tqdm(frames) }
 
     if config['remove_global_orientation']:
         gt_name = 'mesh_posed_no_orient'
@@ -99,12 +109,32 @@ if __name__ == '__main__':
     else:
         per_garment_errors = { 'Tshirt': [], 'Jumpsuit': [], 'Trousers': [], 'Top': [] }
 
-    for frame in tqdm.tqdm(frames):
+    for frame in tqdm(frames):
         id = frame.split('_')[0]
         frame_nr = frame.split('.')[0].split('_')[1]
         gt = np.load(os.path.join(orig_folder, id + '_' + frame_nr + '.npz'))[gt_name][masks[id], :].astype(np.float32)
         pred = np.load(os.path.join(output_folder, id + '_' + frame_nr + '.npy'))
-        metric = np.mean(np.sqrt(np.sum((gt - pred) ** 2, axis=-1)))
+        if error_type == 'edge':
+            pred_unmasked = np.zeros((1, 14475, 3), dtype=np.float32)
+            pred_unmasked[0, masks[id], :] = pred
+            gt_unmasked = np.zeros((1, 14475, 3), dtype=np.float32)
+            gt_unmasked[0, masks[id], :] = gt
+            metric = edge_loss(gt_unmasked, pred_unmasked, masks[id][None,:].astype(np.float32)).numpy()[0]
+        elif error_type == 'euclidean':
+            metric = np.mean(np.sqrt(np.sum((gt - pred) ** 2, axis=-1)))
+        elif error_type == 'collision':
+            pred_unmasked = np.zeros((1, 14475, 3), dtype=np.float32)
+            pred_unmasked[0, masks[id], :] = pred
+            metric = collision_loss(pred_unmasked, bodies[frame][None,:,:], masks[id][None,:].astype(np.float32))[0].numpy()[0]
+        elif error_type == 'normal':
+            pred_unmasked = np.zeros((1, 14475, 3), dtype=np.float32)
+            pred_unmasked[0, masks[id], :] = pred
+            gt_unmasked = np.zeros((1, 14475, 3), dtype=np.float32)
+            gt_unmasked[0, masks[id], :] = gt
+            metric = normal_loss(gt_unmasked, pred_unmasked, masks[id][None,:].astype(np.float32)).numpy()
+        else:
+            raise ValueError('Error type not supported')
+            
         errors[id + '_' + frame_nr] = metric
         per_garment_errors[garment_type_table[id]].append(metric)
 
@@ -112,7 +142,7 @@ if __name__ == '__main__':
     for key in per_garment_errors.keys():
         print(key + ': ' + str(np.mean(per_garment_errors[key])))
 
-    with open('/home/workspace/data/results/errors/iccv/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
+    with open(f'/home/workspace/data/results/errors/iccv/{checkpoint_name}-{iteration}-{error_type}.csv', mode='w') as f:
         file_writer = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
 
         for key in sorted(errors.keys()):

compare_cape.py

@@ -23,7 +23,7 @@ import numpy as np
 import trimesh as tm
 import plotly.express as ex
 import plotly.graph_objects as go
-from custom_utils.custom_utils import _maskFaces
+from custom_utils.custom_utils import _maskFaces, save_stl
 from custom_utils.smpl import SMPL
 from plotly.subplots import make_subplots
 from scipy.spatial.transform import Rotation as R
@@ -215,8 +215,8 @@ if __name__ == '__main__':
     errors_cape_m = get_cape_errors('CAPE/results/CAPE-affineconv_nz18_pose24_clotype8_male/errors.npy', frames_m)
     errors_cape_m = dict(reversed(sorted(errors_cape_m.items(), key=lambda item: item[1])))
 
-    errors_f = get_errors('temp/error_abl_2_pyr_64_128_256_512_cape_f.txt')
+    errors_f = get_errors('temp/archive/error_abl_2_pyr_64_128_256_512_cape_f.txt')
-    errors_m = get_errors('temp/error_abl_2_pyr_64_128_256_512_cape_m.txt')
+    errors_m = get_errors('temp/archive/error_abl_2_pyr_64_128_256_512_cape_m.txt')
 
     folder_pyr_f = '/home/workspace/data/results/cape/abl_2_pyr_64_128_256_512_cape_f'
     folder_pyr_m = '/home/workspace/data/results/cape/abl_2_pyr_64_128_256_512_cape_m'
@@ -238,9 +238,10 @@ if __name__ == '__main__':
 
 
     _, faces = _maskFaces(np.zeros((3638, 3)), np.load('custom_utils/smpl_faces_orig.npy'), cape_mask)
+    faces = faces.astype(np.int32)
     colors = np.ones((3627, 3), np.int8) * 230
 
-    gender = 'male'
+    gender = 'female'
 
     if gender == 'male':
         folder_cape = folder_m
@@ -262,11 +263,18 @@ if __name__ == '__main__':
     all_errors_1 = []
     all_errors_2 = []
 
-    # for key in tqdm.tqdm(errors_cape.keys()):
+    for key in tqdm.tqdm(errors_cape.keys()):
-    count = 0
+    # count = 0
-    while True:
+    # while True:
-        key = random.choice(list(errors_cape.keys()))
+        if os.path.exists(f'temp/cape_stl/{key}_gt.stl'):
+            continue
+        # key = random.choice(list(errors_cape.keys()))
         cape = read_obj(os.path.join(folder_cape, '{:0>4d}.obj'.format(frames_to_i[key])))[clothing_verts_idx, :]  - J0[np.newaxis, :]
+        split = key.split('_')
+        file = '_'.join(split[:-1]) + '.' + split[-1] + '.npy'
+        pose_shape_path = os.path.join(pose_folder, file)
+        if not os.path.exists(pose_shape_path):
+            continue
         cape = add_global_orientation(cape, key, pose_folder, inverse=True)
         if not os.path.exists(os.path.join(folder, key + '_posed.npy')):
             continue
@@ -284,10 +292,13 @@ if __name__ == '__main__':
     # print(np.mean(all_errors_1))
     # print(np.mean(all_errors_2))
 
-        fig = plot_fixed_all(gt, cape, ours, errors_cape[key], errors[key], faces, colors)
+        # fig = plot_fixed_all(gt, cape, ours, errors_cape[key], errors[key], faces, colors)
-        fig.write_image('temp/cape/' + key + '.png')
+        # fig.write_image('temp/cape_2/' + key + '.png')
+        save_stl(f'temp/cape_stl/{key}_gt.stl', gt, faces)
+        save_stl(f'temp/cape_stl/{key}_cape.stl', cape, faces)
+        save_stl(f'temp/cape_stl/{key}_ours.stl', ours, faces)
 
-        print(count)
+        # print(count)
-        count += 1
+        # count += 1
 
     print()

compare_sampling.py

@@ -0,0 +1,65 @@
+import os
+import sys
+import numpy as np
+import trimesh as tm
+from stl import mesh
+
+# os.environ["CUDA_VISIBLE_DEVICES"] = '1'
+# import tensorflow as tf
+
+# gpus = tf.config.experimental.list_physical_devices('GPU')
+# if gpus:
+#     try:
+#         # Currently, memory growth needs to be the same across GPUs
+#         for gpu in gpus:
+#             tf.config.experimental.set_memory_growth(gpu, True)
+#         logical_gpus = tf.config.experimental.list_logical_devices('GPU')
+#         print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
+#     except RuntimeError as e:
+#         # Memory growth must be set before GPUs have been initialized
+#         print(e)
+
+# from losses import collision_loss, normal_loss
+
+
+# from losses import edge_loss_skirt as edge_loss
+# from losses import edge_loss
+
+
+if __name__ == '__main__':
+    frame = '04173_193' # '02276_232', '02978_242', '04173_193'
+    folder = 'examples/sampling_analysis'
+    # original_folder = '/home/workspace/data/dataset/local-cache/train_skirt'
+    original_folder = '/home/workspace/local-data/train'
+    # folder = 'examples/sampling'
+
+    id = frame.split('_')[0]
+    mask = np.load(os.path.join(original_folder, 'mesh_mask', f'{id}.npy'))
+    gt = np.load(os.path.join(folder, frame, f'{frame}_gt.npy'))
+    faces = np.load(os.path.join(folder, frame, f'{frame}_faces.npy'))
+    edges = tm.Trimesh(vertices=gt, faces=faces, validate=False, process=False).edges
+    edges_gt = np.linalg.norm(gt[edges[:, 0]] - gt[edges[:, 1]], axis=1)
+    area_gt = np.sum(np.linalg.norm(np.cross(gt[faces[:, 0]] - gt[faces[:, 1]], gt[faces[:, 0]] - gt[faces[:, 2]]), axis=1))
+
+    errors = []
+    vars = []
+    area_diffs = []
+    # for i in [1,2,4,10]:
+    for i in range(15):
+        sample = np.load(os.path.join(folder, frame, f'{frame}_{i}.npy'))
+        edges_sample = np.linalg.norm(sample[edges[:, 0]] - sample[edges[:, 1]], axis=1)
+        error = np.mean(np.abs(edges_sample - edges_gt))
+        var = np.var(np.abs(edges_sample - edges_gt))
+        errors.append(error)
+        vars.append(var)
+
+        area_sample = np.sum(np.linalg.norm(np.cross(sample[faces[:, 0]] - sample[faces[:, 1]], sample[faces[:, 0]] - sample[faces[:, 2]]), axis=1))
+        area_diff = np.abs(area_sample - area_gt)
+        area_diffs.append(area_diff)
+
+    print(np.array(errors).mean())
+    print(np.array(vars).mean())
+    print(np.array(area_diffs).mean())
+    print(area_gt)
+
+

configs/iccv/config_abl_all.py

@@ -35,9 +35,9 @@ config['is_skirt'] = False
 config['dataset_in_memory'] = False
 config['is_cape'] = False
 
-config['train_dir'] = '/home/workspace/local-data/train'
+config['train_dir'] = '/home/workspace/local-data_127/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
-config['test_dir'] = '/home/workspace/data/dataset/test_ready'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
 
 config['static_model'] = 'checkpoints/iccv/static_iccv_1'
 config['body_model'] = 'checkpoints/iccv/body_iccv_1'

configs/iccv/config_abl_all_cape_f.py

@@ -18,8 +18,8 @@ config['use_norm_loss'] =             True
 ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
 assert ablation_count == 1 or ablation_count == 0
 
-config['gpu'] = '6'
+config['gpu'] = '2'
-config['name'] = 'abl_all_cape_f'
+config['name'] = 'abl_all_cape_f_2'
 config['notes'] = ''
 config['tags'] = ['iccv', 'abl_all']
 
@@ -50,7 +50,7 @@ if config['is_cape']:
 
 config['latent_dim'] = 128
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccv/abl_all_cape_f'
 
 ###############    
 config['lr'] = 0.0001#                 0.0001

configs/iccv/config_abl_all_cape_f_03223_SL.py

@@ -0,0 +1,128 @@
+config = dict()
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK AVG GARMENT USED
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_curvature'] =             True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               True
+
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['gpu'] = '2'
+config['name'] = 'abl_all_cape_f_03223_SL'
+config['notes'] = ''
+config['tags'] = ['iccv', 'abl_all']
+
+config['avg_garment_path'] = 'custom_data/train_cape_f_03223_SL_2_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and config['avg_garment_path'] == '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = True
+
+config['train_dir'] = '/home/workspace/local-data_127/cape_processed/train/female'
+config['valid_dir'] = '/home/workspace/local-data_127/cape_processed/train/female'
+config['test_dir'] = '/home/workspace/local-data/cape_processed/train/female'
+config['frames_file'] = 'frames_03223_SL_train_2.txt'
+config['frames_file_valid'] = 'frames_03223_SL_test_2.txt'
+config['frames_file_test'] = 'frames_03223_SL_test_2.txt'
+
+config['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_f'
+config['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_f'
+config['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_f'
+
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+config['pretrained_model'] = ''
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['is_label'] = False
+config['cvae']['latent_dim'] = 64 * config['bottleneck_scale']
+config['cvae']['add_noise'] = False
+config['cvae']['noise_amount'] = 0.0
+
+config['cvae']['kernel_size'] = 7
+config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
+config['cvae']['encoder_dims'] = [32, 64, 128, 256, config['cvae']['latent_dim']]
+config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
+config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
+
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_all_cape_f_03223_SS.py

@@ -0,0 +1,128 @@
+config = dict()
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK AVG GARMENT USED
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_curvature'] =             True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               True
+
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['gpu'] = '4'
+config['name'] = 'abl_all_cape_f_03223_SS'
+config['notes'] = ''
+config['tags'] = ['iccv', 'abl_all']
+
+config['avg_garment_path'] = 'custom_data/train_cape_f_03223_SS_2_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and config['avg_garment_path'] == '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = True
+
+config['train_dir'] = '/home/workspace/local-data_127/cape_processed/train/female'
+config['valid_dir'] = '/home/workspace/local-data_127/cape_processed/train/female'
+config['test_dir'] = '/home/workspace/local-data/cape_processed/train/female'
+config['frames_file'] = 'frames_03223_SS_train_2.txt'
+config['frames_file_valid'] = 'frames_03223_SS_test_2.txt'
+config['frames_file_test'] = 'frames_03223_SS_test_2.txt'
+
+config['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_f'
+config['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_f'
+config['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_f'
+
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+config['pretrained_model'] = ''
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['is_label'] = False
+config['cvae']['latent_dim'] = 64 * config['bottleneck_scale']
+config['cvae']['add_noise'] = False
+config['cvae']['noise_amount'] = 0.0
+
+config['cvae']['kernel_size'] = 7
+config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
+config['cvae']['encoder_dims'] = [32, 64, 128, 256, config['cvae']['latent_dim']]
+config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
+config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
+
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_all_cape_m_00032_SL.py

@@ -0,0 +1,128 @@
+config = dict()
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK AVG GARMENT USED
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_curvature'] =             True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               True
+
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['gpu'] = '3'
+config['name'] = 'abl_all_cape_m_00032_SL'
+config['notes'] = ''
+config['tags'] = ['iccv', 'abl_all']
+
+config['avg_garment_path'] = 'custom_data/train_cape_m_00032_SL_2_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and config['avg_garment_path'] == '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = True
+
+config['train_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
+config['valid_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
+config['test_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
+config['frames_file'] = 'frames_00032_SL_train_2.txt'
+config['frames_file_valid'] = 'frames_00032_SL_test_2.txt'
+config['frames_file_test'] = 'frames_00032_SL_test_2.txt'
+
+config['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_m'
+config['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_m'
+config['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_m'
+
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+config['pretrained_model'] = ''
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['is_label'] = False
+config['cvae']['latent_dim'] = 64 * config['bottleneck_scale']
+config['cvae']['add_noise'] = False
+config['cvae']['noise_amount'] = 0.0
+
+config['cvae']['kernel_size'] = 7
+config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
+config['cvae']['encoder_dims'] = [32, 64, 128, 256, config['cvae']['latent_dim']]
+config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
+config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
+
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_all_skirt.py

@@ -37,7 +37,7 @@ config['is_cape'] = False
 
 config['train_dir'] = '/home/workspace/local-data/train_skirt'
 config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
-config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
+config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
 
 config['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
 config['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'

configs/iccv/config_abl_all_skirt_var.py

@@ -0,0 +1,125 @@
+config = dict()
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK AVG GARMENT USED
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_curvature'] =             True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               True
+
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['gpu'] = '3'
+config['name'] = 'abl_all_skirt_var_dasda'
+config['notes'] = ''
+config['tags'] = ['iccv', 'abl_all', 'skirt']
+
+config['avg_garment_path'] = 'custom_data/train_no_shape_skirt_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and config['avg_garment_path'] == '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = True
+config['dataset_in_memory'] = False
+config['is_cape'] = False
+
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data/test_skirt_ready_2'
+
+config['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+config['pretrained_model'] = 'checkpoints/iccv/abl_all_skirt'
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.1
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (14475, 3,),
+                          'mesh_posed': (14475, 3,),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (14475,),
+                              'uv_mask': (512, 256,),
+                              }
+
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (14475, 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['is_label'] = False
+config['cvae']['latent_dim'] = 64 * config['bottleneck_scale']
+config['cvae']['add_noise'] = False
+config['cvae']['noise_amount'] = 0.0
+
+config['cvae']['kernel_size'] = 7
+config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
+config['cvae']['encoder_dims'] = [32, 64, 128, 256, config['cvae']['latent_dim']]
+config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
+config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
+
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32.py

@@ -33,6 +33,7 @@ config['pyramid']['final_upscale_enhancer'] = ''
 config['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
 config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+
 config['batch_size'] = 4
 config['is_skirt'] = False
 config['is_cape'] = False
@@ -93,11 +94,10 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 512
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 7
-    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
-    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 64, 16]
     level['avg_garment_path'] = ''
     level['upscale_enhancer'] = ''
     config['pyramid']['levels'].append(level)
@@ -106,13 +106,12 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 256
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 5
-    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_depths'] = [3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
-    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 64, 16]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   elif res == 128:
@@ -120,13 +119,12 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 128
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 5
-    level['encoder_depths'] = [16, 9, 9, 9]
+    level['encoder_depths'] = [9, 9, 9]
-    level['encoder_dims'] = [64, 128, 128, 64]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
-    level['decoder_input'] = (4, 2, 128)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [16, 9, 9, 9]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 128, level['latent_dim']]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   elif res == 64:
@@ -139,7 +137,7 @@ for res in config['pyramid']['resolutions']:
     level['decoder_depths'] = level['encoder_depths']
     level['decoder_dims'] = level['encoder_dims']
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   elif res == 32:

configs/iccv/config_abl_pyr_32_10p.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_10p'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+
+config['frames_file'] = 'frames_10p.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_10p'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_10p'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_10p'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_25p.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_25p'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+
+config['frames_file'] = 'frames_25p.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_25p'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_25p'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_25p'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_10p.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'iccv_pyr_32_64_10p'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_10p'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+
+config['frames_file'] = 'frames_10p.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_10p'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_10p'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_10p'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256.py

@@ -1,7 +1,7 @@
 config = dict()
 
-config['gpu'] = '3'
+config['gpu'] = '1'
-config['name'] = 'iccv_pyr_32_64_128_256'
+config['name'] = 'iccv_pyr_32_64_128_256_2'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv']
 
@@ -22,13 +22,13 @@ config['use_offsets'] =               False
 config['use_norm_loss'] =             True
 config['use_curvature'] =             True
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256'
 config['pretrained_model_iteration'] = ''
 
 config['pyramid'] = dict()
 config['pyramid']['resolutions'] = [32, 64, 128, 256]
-config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_2'
+config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['pretrained_pyramid_iteration'] = '125000'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
 config['pyramid']['final_upscale_enhancer'] = ''
 
 config['train_dir'] = '/home/workspace/local-data/train'

configs/iccv/config_abl_pyr_32_64_128_256_512.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_64_128_256_512'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_512'
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256, 512]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_2'
+config['pyramid']['pretrained_pyramid_iteration'] = '90000'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/train'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+config['frames_file'] = 'frames_00761_0.txt'
+config['frames_file_valid'] = 'frames_00761_0.txt'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = True
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_512_curv.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_64_128_256_512_curv'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'curv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             False
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256, 512]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_curv'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_512_reg.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_64_128_256_512_reg'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'reg']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          False # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             False
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256, 512]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_reg'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_512_skin.py

@@ -0,0 +1,195 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_64_128_256_512_skin'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              False # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256, 512]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_skin'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+                        
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      if config['use_skinning']:
+        config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      else:
+        config['signature_dynamic']['uv_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_512_skirt.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_64_128_256_512_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256, 512]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_skirt_2'
+config['pyramid']['pretrained_pyramid_iteration'] = '90000'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_curv.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_64_128_256_curv'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'curv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             False
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_curv'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_curv_skirt.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'iccv_pyr_32_64_128_256_curv_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'curv', 'skirt']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             False
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_curv_skirt'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_reg.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '5'
+config['name'] = 'iccv_pyr_32_64_128_256_reg'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'reg']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          False # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             False
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_reg_2'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_seq.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'iccv_pyr_32_64_128_256_seq_2_fine'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_seq_2'
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_skin.py

@@ -0,0 +1,195 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_64_128_256_skin'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              False # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128, 256]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_skin_2'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      if config['use_skinning']:
+        config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      else:
+        config['signature_dynamic']['uv_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_256_skirt.py

@@ -1,7 +1,7 @@
 config = dict()
 
-config['gpu'] = '0'
+config['gpu'] = '3'
-config['name'] = 'iccv_pyr_32_64_128_256_skirt'
+config['name'] = 'iccv_pyr_32_64_128_256_skirt_2'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv']
 
@@ -22,13 +22,13 @@ config['use_offsets'] =               False
 config['use_norm_loss'] =             True
 config['use_curvature'] =             True
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccv/iccv_pyr_32_64_128_256_skirt'
 config['pretrained_model_iteration'] = ''
 
 config['pyramid'] = dict()
 config['pyramid']['resolutions'] = [32, 64, 128, 256]
-config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_128_skirt'
+config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['pretrained_pyramid_iteration'] = '175000'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
 config['pyramid']['final_upscale_enhancer'] = ''
 
 config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
@@ -94,11 +94,10 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 512
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 7
-    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
-    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 64, 16]
     level['avg_garment_path'] = ''
     level['upscale_enhancer'] = ''
     config['pyramid']['levels'].append(level)

configs/iccv/config_abl_pyr_32_64_128_curv.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_64_128_curv'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'curv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             False
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_curv'
+config['pyramid']['pretrained_pyramid_iteration'] = '110000'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_curv_skirt.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_64_128_curv_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'curv', 'skirt']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             False
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_curv_skirt'
+config['pyramid']['pretrained_pyramid_iteration'] = '60000'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_reg.py

@@ -1,7 +1,7 @@
 config = dict()
 
-config['gpu'] = '4'
+config['gpu'] = '0'
-config['name'] = 'iccv_pyr_32_64_128_reg'
+config['name'] = 'iccv_pyr_32_64_128_reg_2'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv', 'reg']
 
@@ -22,17 +22,17 @@ config['use_offsets'] =               False
 config['use_norm_loss'] =             False
 config['use_curvature'] =             True
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccv/iccv_pyr_32_64_128_reg'
 config['pretrained_model_iteration'] = ''
 
 config['pyramid'] = dict()
 config['pyramid']['resolutions'] = [32, 64, 128]
-config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_reg'
+config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['pretrained_pyramid_iteration'] = '120000'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
 config['pyramid']['final_upscale_enhancer'] = ''
 
-config['train_dir'] = '/home/workspace/local-data/train'
+config['train_dir'] = '/home/workspace/local-data_127/train'
-config['valid_dir'] = '/home/workspace/local-data/valid'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
 config['test_dir'] = '/home/workspace/local-data_127/test_ready'
 config['batch_size'] = 4
 config['is_skirt'] = False

configs/iccv/config_abl_pyr_32_64_128_reg_skirt.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '3'
+config['name'] = 'iccv_pyr_32_64_128_reg_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'reg']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          False # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             False
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_reg_skirt'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_seq.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'iccv_pyr_32_64_128_seq_2'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_seq_2'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_skin.py

@@ -1,7 +1,7 @@
 config = dict()
 
-config['gpu'] = '5'
+config['gpu'] = '4'
-config['name'] = 'iccv_pyr_32_64_128_skin'
+config['name'] = 'iccv_pyr_32_64_128_skin_2'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv']
 
@@ -22,17 +22,17 @@ config['use_offsets'] =               False
 config['use_norm_loss'] =             True
 config['use_curvature'] =             True
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccv/iccv_pyr_32_64_128_skin'
 config['pretrained_model_iteration'] = ''
 
 config['pyramid'] = dict()
 config['pyramid']['resolutions'] = [32, 64, 128]
-config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_skin'
+config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['pretrained_pyramid_iteration'] = '130000'
+config['pyramid']['pretrained_pyramid_iteration'] = ''
 config['pyramid']['final_upscale_enhancer'] = ''
 
-config['train_dir'] = '/home/workspace/local-data_127/train'
+config['train_dir'] = '/home/workspace/local-data/train'
-config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['valid_dir'] = '/home/workspace/local-data/valid'
 config['test_dir'] = '/home/workspace/local-data_127/test_ready'
 config['batch_size'] = 4
 config['is_skirt'] = False

configs/iccv/config_abl_pyr_32_64_128_skin_skirt.py

@@ -0,0 +1,193 @@
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'iccv_pyr_32_64_128_skin_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              False # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_skin_skirt'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      if config['use_skinning']:
+        config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      else:
+        config['signature_dynamic']['uv_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_128_var.py

@@ -0,0 +1,188 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_64_128_var'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_64_var'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.1
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_25p.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'iccv_pyr_32_64_25p'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_25p'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/train'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+
+config['frames_file'] = 'frames_25p.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_25p'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_25p'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_25p'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_curv_skirt.py

@@ -86,7 +86,6 @@ config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
 config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
 config['pyramid']['freeze_encoders'] = True
 
-
 config['pyramid']['levels'] = []
 for res in config['pyramid']['resolutions']:
   if res == 512:
@@ -94,11 +93,10 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 512
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 7
-    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
-    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 64, 16]
     level['avg_garment_path'] = ''
     level['upscale_enhancer'] = ''
     config['pyramid']['levels'].append(level)
@@ -107,13 +105,12 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 256
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 5
-    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_depths'] = [3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
-    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 64, 16]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   elif res == 128:
@@ -121,13 +118,12 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 128
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 5
-    level['encoder_depths'] = [16, 9, 9, 9]
+    level['encoder_depths'] = [9, 9, 9]
-    level['encoder_dims'] = [64, 128, 128, 64]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
-    level['decoder_input'] = (4, 2, 128)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [16, 9, 9, 9]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 128, level['latent_dim']]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   elif res == 64:

configs/iccv/config_abl_pyr_32_64_reg.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '1'
+config['gpu'] = '3'
 config['name'] = 'iccv_pyr_32_64_reg'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv', 'reg']
@@ -31,8 +31,8 @@ config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_reg/'
 config['pyramid']['pretrained_pyramid_iteration'] = '150000'
 config['pyramid']['final_upscale_enhancer'] = ''
 
-config['train_dir'] = '/home/workspace/local-data/train'
+config['train_dir'] = '/home/workspace/local-data_127/train'
-config['valid_dir'] = '/home/workspace/local-data/valid'
+config['valid_dir'] = '/home/workspace/local-data_127/valid'
 config['test_dir'] = '/home/workspace/local-data_127/test_ready'
 config['batch_size'] = 4
 config['is_skirt'] = False

configs/iccv/config_abl_pyr_32_64_reg_skirt.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '2'
+config['gpu'] = '3'
 config['name'] = 'iccv_pyr_32_64_reg_skirt'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv', 'reg']
@@ -32,7 +32,7 @@ config['pyramid']['pretrained_pyramid_iteration'] = '190000'
 config['pyramid']['final_upscale_enhancer'] = ''
 
 config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
-config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
 config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
 config['batch_size'] = 4
 config['is_skirt'] = True
@@ -86,7 +86,6 @@ config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
 config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
 config['pyramid']['freeze_encoders'] = True
 
-
 config['pyramid']['levels'] = []
 for res in config['pyramid']['resolutions']:
   if res == 512:
@@ -94,11 +93,10 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 512
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 7
-    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
-    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 64, 16]
     level['avg_garment_path'] = ''
     level['upscale_enhancer'] = ''
     config['pyramid']['levels'].append(level)
@@ -107,13 +105,12 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 256
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 5
-    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_depths'] = [3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
-    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 64, 16]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   elif res == 128:
@@ -121,13 +118,12 @@ for res in config['pyramid']['resolutions']:
     level['resolution'] = 128
     level['latent_dim'] = 64 * config['bottleneck_scale']
     level['kernel_size'] = 5
-    level['encoder_depths'] = [16, 9, 9, 9]
+    level['encoder_depths'] = [9, 9, 9]
-    level['encoder_dims'] = [64, 128, 128, 64]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
-    level['decoder_input'] = (4, 2, 128)
+    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_depths'] = [16, 9, 9, 9]
+    level['decoder_dims'] = level['encoder_dims']
-    level['decoder_dims'] = [256, 128, 128, level['latent_dim']]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   elif res == 64:

configs/iccv/config_abl_pyr_32_64_skin.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '1'
+config['gpu'] = '2'
 config['name'] = 'iccv_pyr_32_64_skin'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv']

configs/iccv/config_abl_pyr_32_64_skin_skirt copy.py

@@ -0,0 +1,193 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_64_skin_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              False # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_skin_skirt'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      if config['use_skinning']:
+        config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      else:
+        config['signature_dynamic']['uv_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_64_skin_skirt.py

@@ -0,0 +1,193 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_64_skin_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              False # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32_skin_skirt'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      if config['use_skinning']:
+        config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      else:
+        config['signature_dynamic']['uv_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_batch.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '7'
+config['name'] = 'iccv_pyr_32_batch'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+
+config['batch_size'] = 64
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_jumpsuit.py

@@ -0,0 +1,190 @@
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'iccv_pyr_32_jumpsuit'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['frames_file'] = 'frames_jumpsuit.txt'
+config['frames_file_valid'] = 'frames_jumpsuit.txt'
+config['frames_file_test'] = 'frames_jumpsuit.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_seq.py

@@ -0,0 +1,187 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_seq_2'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_32'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_skirt_batch.py

@@ -0,0 +1,193 @@
+config = dict()
+
+config['gpu'] = '7'
+config['name'] = 'iccv_pyr_32_skirt_batch'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data/test_skirt_ready_2'
+config['frames_file'] = 'frames_skirt.txt'
+config['frames_file_valid'] = 'frames_skirt.txt'
+config['frames_file_test'] = 'frames_skirt.txt'
+
+config['batch_size'] = 128
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [16, 9, 9, 9]
+    level['encoder_dims'] = [64, 128, 128, 64]
+    level['decoder_input'] = (4, 2, 128)
+    level['decoder_depths'] = [16, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 128, level['latent_dim']]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_skirt_dress.py

@@ -0,0 +1,190 @@
+config = dict()
+
+config['gpu'] = '3'
+config['name'] = 'iccv_pyr_32_skirt_dress'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data/test_skirt_ready_2'
+config['frames_file'] = 'frames_dress.txt'
+config['frames_file_valid'] = 'frames_dress.txt'
+config['frames_file_test'] = 'frames_dress.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_skirt_skirt.py

@@ -0,0 +1,190 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_32_skirt_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
+config['test_dir'] = '/home/workspace/local-data/test_skirt_ready_2'
+config['frames_file'] = 'frames_skirt.txt'
+config['frames_file_valid'] = 'frames_skirt.txt'
+config['frames_file_test'] = 'frames_skirt.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_skirt'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_skirt'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_skirt'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_skirt'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_skirt'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_top.py

@@ -0,0 +1,193 @@
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'iccv_pyr_32_top'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['train_dir_skirt'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir_skirt'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir_skirt'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['frames_file'] = 'frames_top.txt'
+config['frames_file_valid'] = 'frames_top.txt'
+config['frames_file_test'] = 'frames_top.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_trousers.py

@@ -0,0 +1,190 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'iccv_pyr_32_trousers'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['frames_file'] = 'frames_trousers.txt'
+config['frames_file_valid'] = 'frames_trousers.txt'
+config['frames_file_test'] = 'frames_trousers.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_tshirt.py

@@ -0,0 +1,193 @@
+config = dict()
+
+config['gpu'] = '3'
+config['name'] = 'iccv_pyr_32_tshirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/local-data_127/test_ready'
+config['train_dir_skirt'] = '/home/workspace/local-data_128/train_skirt'
+config['valid_dir_skirt'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir_skirt'] = '/home/workspace/local-data_128/test_skirt_ready_2'
+config['frames_file'] = 'frames_tshirt.txt'
+config['frames_file_valid'] = 'frames_tshirt.txt'
+config['frames_file_test'] = 'frames_tshirt.txt'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 3, 9, 3]
+    level['encoder_dims'] = [16, 32, 64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_64_128_256_cape_f.py

@@ -0,0 +1,188 @@
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'iccv_pyr_64_128_256_cape_f'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'cape_f']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64, 128, 256]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_64_128_cape_f'
+config['pyramid']['pretrained_pyramid_iteration'] = '170000'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/cape_processed/train/female'
+config['valid_dir'] = '/home/workspace/local-data/cape_processed/test/female'
+config['test_dir'] = '/home/workspace/local-data/cape_processed/test/female'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = True
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_f'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_f'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_f'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [64, 128, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_256_2_cape_f'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_cape_f'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_cape_f'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_cape_f'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_64_128_cape_f_03223_SL.py

@@ -0,0 +1,191 @@
+config = dict()
+
+config['gpu'] = '3'
+config['name'] = 'iccv_pyr_64_128_cape_f_03223_SL'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'cape_f']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_64_cape_f_03223_SL'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/cape_processed/train/female'
+config['valid_dir'] = '/home/workspace/local-data_127/cape_processed/train/female'
+config['test_dir'] = '/home/workspace/local-data_127/cape_processed/train/female'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = True
+config['frames_file'] = 'frames_03223_SL_train_2.txt'
+config['frames_file_valid'] = 'frames_03223_SL_test_2.txt'
+config['frames_file_test'] = 'frames_03223_SL_test_2.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_f'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_f'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_f'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_cape_f'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_cape_f'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_cape_f'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_64_128_cape_f_03223_SS.py

@@ -0,0 +1,191 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'iccv_pyr_64_128_cape_f_03223_SS'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'cape_f']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_64_cape_f_03223_SS'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/cape_processed/train/female'
+config['valid_dir'] = '/home/workspace/local-data/cape_processed/train/female'
+config['test_dir'] = '/home/workspace/local-data/cape_processed/train/female'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = True
+config['frames_file'] = 'frames_03223_SS_train_2.txt'
+config['frames_file_valid'] = 'frames_03223_SS_test_2.txt'
+config['frames_file_test'] = 'frames_03223_SS_test_2.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_f'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_f'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_f'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_cape_f'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_cape_f'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_cape_f'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_64_128_cape_m.py

@@ -0,0 +1,188 @@
+config = dict()
+
+config['gpu'] = '3'
+config['name'] = 'iccv_pyr_64_128_cape_m'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'cape_m']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_64_cape_m'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data/cape_processed/train/male'
+config['valid_dir'] = '/home/workspace/local-data/cape_processed/test/male'
+config['test_dir'] = '/home/workspace/local-data/cape_processed/test/male'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = True
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_m'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_m'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_m'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_cape_m'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_cape_m'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_cape_m'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_64_128_cape_m_00032_SL.py

@@ -0,0 +1,192 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'iccv_pyr_64_128_cape_m_00032_SL'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'cape_m']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_norm_loss'] =             True
+config['use_curvature'] =             True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64, 128]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/iccv/iccv_pyr_64_cape_m_00032_SL'
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
+config['valid_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
+config['test_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = True
+
+config['frames_file'] = 'frames_00032_SL_train_2.txt'
+config['frames_file_valid'] = 'frames_00032_SL_test_2.txt'
+config['frames_file_test'] = 'frames_00032_SL_test_2.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+config['bottleneck_scale'] = 2
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['add_noise'] = False
+config['pyramid']['noise_amount'] = 0.0
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+config['pyramid']['static_model'] = 'checkpoints/iccv/static_iccv_1_cape_m'
+config['pyramid']['body_model'] = 'checkpoints/iccv/body_iccv_1_cape_m'
+config['pyramid']['curvature_model'] = 'checkpoints/iccv/curv_iccv_1_cape_m'
+config['pyramid']['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_128_2_cape_m'#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [64, level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_64_2_cape_m'#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [16]
+    level['encoder_dims'] = [level['latent_dim']]
+    level['decoder_depths'] = level['encoder_depths']
+    level['decoder_dims'] = level['encoder_dims']
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_cape_m'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae_static']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_64_cape_m_00032_SL.py

@@ -32,7 +32,7 @@ config['pyramid']['final_upscale_enhancer'] = ''
 
 config['train_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
 config['valid_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
-config['test_dir'] = '/home/workspace/local-data_127/cape_processed/train/male'
+config['test_dir'] = '/home/workspace/local-data/cape_processed/train/male'
 config['batch_size'] = 4
 config['is_skirt'] = False
 config['is_cape'] = True

configs/iccv/config_cvae_curv.py

@@ -18,8 +18,8 @@ config['use_norm_loss'] =             True
 ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
 assert ablation_count == 1 or ablation_count == 0
 
-config['gpu'] = '5'
+config['gpu'] = '0'
-config['name'] = 'cvae_curv'
+config['name'] = 'cvae_curv_3'
 config['notes'] = ''
 config['tags'] = ['iccv', 'cvae_curv']
 
@@ -35,9 +35,9 @@ config['is_skirt'] = False
 config['dataset_in_memory'] = False
 config['is_cape'] = False
 
-config['train_dir'] = '/home/workspace/local-data_127/train'
+config['train_dir'] = '/home/workspace/local-data/train'
-config['valid_dir'] = '/home/workspace/local-data_127/valid'
+config['valid_dir'] = '/home/workspace/local-data/valid'
-config['test_dir'] = '/home/workspace/data/dataset/test_ready'
+config['test_dir'] = '/home/workspace/local-data/test_ready'
 
 config['static_model'] = 'checkpoints/iccv/static_iccv_1'
 config['body_model'] = 'checkpoints/iccv/body_iccv_1'
@@ -50,12 +50,13 @@ if config['is_cape']:
 
 config['latent_dim'] = 128
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccv/cvae_curv'
+config['pretrained_model_iteration'] = ''
 
 ###############    
 config['lr'] = 0.0001#                 0.0001
 ###############
-config['starting_balancing_coeff'] = 0.01
+config['starting_balancing_coeff'] = 1.0
 
 config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
                           'pose_shape': (72 + 11,),

curvature_analysis.py

@@ -0,0 +1,381 @@
+import os
+import sys
+os.environ["CUDA_VISIBLE_DEVICES"] = '4'
+
+
+import tqdm
+import argparse
+import random
+import string
+import time
+import numpy as np
+import trimesh as tm
+import cmapy as cm
+import scipy as sp
+import scipy.io as sio
+import plotly.graph_objects as go
+from pyntcloud import PyntCloud
+from scipy.sparse import csr_matrix, coo_matrix
+from scipy.sparse.csgraph import floyd_warshall, dijkstra
+from plotly.subplots import make_subplots
+from custom_utils.custom_utils import _maskFaces
+from postprocessing import fix_collision
+
+from custom_utils.supersmpl_io import readPC2, readPC2Frame, writePC2, readOBJ
+from custom_utils.custom_utils import _maskFaces, save_stl, write_obj
+from auto_encoder_curv import dice_dense
+
+
+
+        
+
+def postprocess(mesh, faces, mask=None, body=None, do_smoothing=True):
+    if body is not None:
+        mesh_fixed = fix_collision(mesh, body[np.newaxis,:,:], mask[np.newaxis,:])[0].numpy()[mask, :]
+    else:
+        mesh_fixed = mesh
+
+    if do_smoothing:
+        m = tm.Trimesh(mesh_fixed, faces, process=False, validate=False)
+        outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
+        outliers = np.nonzero(outliers)[0]
+        outliers_n_neighbours = get_closest_n_points(mesh_fixed, outliers, 2)
+        outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
+        faces_fixed = np.concatenate((faces, outliers_faces), axis=0)
+        m = tm.Trimesh(mesh_fixed, faces_fixed, process=False, validate=False)
+        tm.smoothing.filter_humphrey(m, iterations=1, alpha=0.6, beta=0.4)
+
+        mesh = m.vertices
+    else:
+        mesh = mesh_fixed
+
+    return mesh
+
+def export_to_ply(mesh, file):
+    ply = tm.exchange.ply.export_ply(mesh, encoding='binary', vertex_normal=True, include_attributes=True)
+    output_file = open(file, "wb+")
+    output_file.write(ply)
+    output_file.close()
+
+
+def get_closest_n_points(verts, idx, n):
+    dist = sp.spatial.distance.cdist(verts[idx, :], verts)
+    dist[dist == 0] = 1e9
+    idx_sort = np.argsort(dist, axis=-1)
+    closest = idx_sort[:, :n]
+    return closest
+
+
+def calculate_dist(folder, neighbourhood):
+    out = dict()
+    frames = sorted(os.listdir(os.path.join(folder, 'mesh_posed')))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        id = frame.split('_')[0]
+        if id in out.keys():
+            continue
+
+        mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
+        k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
+        out[id] = k_neighbors
+
+    return out
+
+
+def histedges_equalN(x, nbin):
+    npt = len(x)
+    return np.interp(np.linspace(0, npt, nbin + 1),
+                     np.arange(npt),
+                     np.sort(x))
+
+
+def get_bins(values, nr_of_bins):
+    flattened = []
+    for c in values:
+        flattened.extend(c.flatten())
+    flattened = np.array(flattened)
+    bins = histedges_equalN(flattened, nr_of_bins)
+    return bins
+
+
+def generate_curvatures(v, faces, mask, neighbourhood=25, nr_of_labels=6):
+    # id = frame.split('_')[0]
+    # frame_nr = int(frame.split('_')[1].split('.')[0])
+
+    # mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
+    # _, faces = _maskFaces(np.zeros((14475,3)), F, mask)
+    # v = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
+    
+    m = tm.Trimesh(v, faces, process=False, validate=False)
+
+    outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
+    outliers = np.nonzero(outliers)[0]
+    outliers_n_neighbours = get_closest_n_points(v, outliers, 2)
+    outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
+    faces = np.concatenate((faces, outliers_faces), axis=0)
+
+    verts = v
+
+    m = tm.Trimesh(verts, faces, process=False, validate=False)
+    export_to_ply(m, temp_file)
+
+    cloud = PyntCloud.from_file(temp_file)
+
+    k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
+    #k_neighbors = k_neighbors_cache[id] # np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
+    ev = cloud.add_scalar_field("eigen_values", k_neighbors=k_neighbors)
+    cloud.add_scalar_field("curvature", ev=ev)
+    curvature = np.array(cloud.points["curvature(" + str(neighbourhood+1) + ")"])
+    
+    # bins = np.load(f'custom_data/train_bins.npy') # get_bins(curvature, nr_of_labels)
+    bins = get_bins(curvature, nr_of_labels)
+    labels = np.linspace(0, bins.shape[0] - 2, bins.shape[0] - 1)
+
+    frame_labels = np.zeros((curvature.shape[0]), dtype=np.float32)
+    for j in range(bins.shape[0] - 2):
+        frame_labels[(curvature >= bins[j]) * (curvature < bins[j+1])] = labels[j]
+    frame_labels[curvature >= bins[-2]] = labels[-1]
+       
+    return frame_labels
+
+import tensorflow as tf
+
+
+def visualize_curvature_labels(folder, results_folder, frame):
+    id = frame.split('_')[0]
+    frame_nr = frame.split('_')[1].split('.')[0]
+
+    mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
+    _, faces = _maskFaces(np.zeros((14475,3)), F, mask)
+    verts = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
+    pred = np.load(os.path.join(results_folder, frame + '.npy'))
+    pred = postprocess(pred, faces)
+
+    curvature_labels_gt = generate_curvatures(verts, faces, mask, 25)
+    curvature_labels_pred = generate_curvatures(pred, faces, mask, 25)
+    # dice = dice_dense(curvature_labels_pred[None,:], curvature_labels_gt[None,:])
+    dice = dice_dense(tf.one_hot(curvature_labels_pred, 7)[None,:], tf.one_hot(curvature_labels_gt, 7)[None,:]).numpy()
+    colors_binned_all = []
+
+    for curvature_labels in [curvature_labels_gt, curvature_labels_pred]:
+        colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, int(curvature_labels.max()+1))])
+        colors_binned = np.zeros((curvature_labels.shape[0], 3))
+        for i in range(int(curvature_labels.max())+1):
+            # print(np.count_nonzero(curvature_labels == i))
+            colors_binned[curvature_labels == i, :] = colors[i]
+        colors_binned_all.append(colors_binned)
+
+    fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
+
+    fig.add_trace(go.Mesh3d(
+                # 8 vertices of a cube
+                x=-pred[:,0],
+                y=pred[:,2],
+                z=pred[:,1],
+                # i, j and k give the vertices of triangles
+                i = faces[:,0],
+                j = faces[:,1],
+                k = faces[:,2],
+                vertexcolor=np.ones((verts.shape[0],3))*np.array([255,200,200])[None,:]
+            ),
+            row=1, col=2)
+
+    fig.add_trace(go.Mesh3d(
+                # 8 vertices of a cube
+                x=verts[:,0],
+                y=verts[:,1],
+                z=verts[:,2],
+                # i, j and k give the vertices of triangles
+                i = faces[:,0],
+                j = faces[:,1],
+                k = faces[:,2],
+                vertexcolor=colors_binned_all[0]
+            ),
+            row=1, col=1)
+    
+    fig.add_trace(go.Mesh3d(
+                # 8 vertices of a cube
+                x=-pred[:,0],
+                y=pred[:,2],
+                z=pred[:,1],
+                # i, j and k give the vertices of triangles
+                i = faces[:,0],
+                j = faces[:,1],
+                k = faces[:,2],
+                vertexcolor=colors_binned_all[1],
+                text=f'dice: {dice}'
+            ),
+            row=1, col=3)
+
+    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
+                    scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
+                    scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
+                    # scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
+                    # scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
+                    )
+    helper = dict(xaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
+                yaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
+                zaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),)
+        
+    fig.update_layout(scene = helper,
+                        scene2 = helper,
+                        scene3 = helper,
+                        # scene4 = helper,
+                        # scene5 = helper,
+                        )
+
+
+    # meshes = [go.Mesh3d(
+    #             x=x[:,0],
+    #             y=x[:,1],
+    #             z=x[:,2],
+    #             i = faces[:,0],
+    #             j = faces[:,1],
+    #             k = faces[:,2],
+    #             vertexcolor=colors_binned
+    #             )]
+
+    # fig = go.Figure(data=meshes)
+    # fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1))
+    # fig.update_layout(
+    #     scene = dict(
+    #         xaxis = dict(nticks=4, range=[-1,1],),
+    #                     yaxis = dict(nticks=4, range=[-1,1],),
+    #                     zaxis = dict(nticks=4, range=[-1,1],),)
+    #                     )
+
+    return fig, dice
+
+import wandb
+
+def init_wandb():
+    run = wandb.init(project='plots', name='curvatures', dir='/home/workspace/local-data/temp/')
+    artifact = wandb.Artifact('code', type='code')
+    artifact.add_file('curvature_analysis.py')
+    run.log_artifact(artifact)
+
+
+def visualize_neighbourhoods(folder, frame):
+    id = frame.split('_')[0]
+    frame_nr = frame.split('_')[1].split('.')[0]
+
+    mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
+    _, faces = _maskFaces(np.zeros((14475,3)), F, mask)
+    verts = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
+
+    curvature_labels_10 = generate_curvatures(verts, faces, mask, 10)
+    curvature_labels_25 = generate_curvatures(verts, faces, mask, 25)
+    curvature_labels_100 = generate_curvatures(verts, faces, mask, 100)
+    colors_binned_all = []
+
+    for curvature_labels in [curvature_labels_10, curvature_labels_25, curvature_labels_100]:
+        colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, int(curvature_labels.max()+1))])
+        colors_binned = np.zeros((curvature_labels.shape[0], 3))
+        for i in range(int(curvature_labels.max())+1):
+            # print(np.count_nonzero(curvature_labels == i))
+            colors_binned[curvature_labels == i, :] = colors[i]
+        colors_binned_all.append(colors_binned)
+
+    fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
+
+    fig.add_trace(go.Mesh3d(
+                # 8 vertices of a cube
+                x=-verts[:,0],
+                y=verts[:,1],
+                z=verts[:,2],
+                # i, j and k give the vertices of triangles
+                i = faces[:,0],
+                j = faces[:,1],
+                k = faces[:,2],
+                vertexcolor=colors_binned_all[0]
+            ),
+            row=1, col=1)
+
+    fig.add_trace(go.Mesh3d(
+                # 8 vertices of a cube
+                x=verts[:,0],
+                y=verts[:,1],
+                z=verts[:,2],
+                # i, j and k give the vertices of triangles
+                i = faces[:,0],
+                j = faces[:,1],
+                k = faces[:,2],
+                vertexcolor=colors_binned_all[1]
+            ),
+            row=1, col=2)
+    
+    fig.add_trace(go.Mesh3d(
+                # 8 vertices of a cube
+                x=-verts[:,0],
+                y=verts[:,1],
+                z=verts[:,2],
+                # i, j and k give the vertices of triangles
+                i = faces[:,0],
+                j = faces[:,1],
+                k = faces[:,2],
+                vertexcolor=colors_binned_all[2],
+            ),
+            row=1, col=3)
+
+    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
+                    scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
+                    scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
+                    # scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
+                    # scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
+                    )
+    helper = dict(xaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
+                yaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
+                zaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),)
+        
+    fig.update_layout(scene = helper,
+                        scene2 = helper,
+                        scene3 = helper,
+                        # scene4 = helper,
+                        # scene5 = helper,
+                        )
+    
+    write_obj(f'examples/curvature_analysis/{id}_{frame_nr}_10.obj', verts, faces.astype(np.int32), colors_binned_all[0].astype(np.int32))
+    write_obj(f'examples/curvature_analysis/{id}_{frame_nr}_25.obj', verts, faces.astype(np.int32), colors_binned_all[1].astype(np.int32))
+    write_obj(f'examples/curvature_analysis/{id}_{frame_nr}_100.obj', verts, faces.astype(np.int32), colors_binned_all[2].astype(np.int32))
+    write_obj(f'examples/curvature_analysis/{id}_{frame_nr}_mesh.obj', verts, faces.astype(np.int32), np.ones((verts.shape[0], 3), dtype=np.int32) * 200)
+    save_stl(f'examples/curvature_analysis/{id}_{frame_nr}_mesh.stl', verts, faces.astype(np.int32))
+
+    fig.show()
+    return fig
+
+
+if __name__ == '__main__':
+    # init_wandb()
+
+    is_skirt = True
+    skirt_modifier = '_skirt' if is_skirt else ''
+    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
+    # k_neighbours(k=25)
+
+    folder = '/home/workspace/local-data_128/test_skirt_ready_2'
+    results_folder = '/home/workspace/data/results/iccv/iccv_pyr_32_64_128_256_512-120000'
+
+    # frames_file = 'frames_temp.txt'
+    # with open(os.path.join(folder, frames_file), 'r') as f:
+    #     lines = f.readlines()
+    #     lines = [line.strip() for line in lines]
+    # frames = lines
+    frames = os.listdir(os.path.join(folder, 'pose_shape'))
+    frames = [frame.split('.')[0] for frame in frames]
+
+    temp_file = '/home/workspace/local-data/temp/' + ''.join(random.choice(string.ascii_lowercase) for i in range(10)) + '.ply'
+    if not is_skirt:
+        dist = np.load('custom_data/dijkstra.npy')
+    else:
+        dist = np.load('custom_data/dijkstra_skirt.npy')
+
+    i = 0
+    while True:
+        frame = np.random.choice(frames)
+        print(frame)
+        # frame = '03265_193'
+        # frame = '03102_49'
+        # fig, dice = visualize_curvature_labels(folder, results_folder, frame)
+        # wandb.log({f'{frame}-dice:{dice}': fig}, step=i)
+        visualize_neighbourhoods(folder, frame)
+        i += 1

custom_utils/custom_utils.py

@@ -443,3 +443,13 @@ def save_stl(file, mesh, faces):
             obj.vectors[i][j] = mesh[f[j],:]    
 
     obj.save(file)
+
+
+def write_obj(file, vertices, faces, colors):
+    with open(file, 'w') as file:
+        for v, c in zip(vertices, colors):
+            line = 'v ' + ' '.join([str(_) for _ in v]) + ' ' + ' '.join([str(_) for _ in c]) + '\n'
+            file.write(line)
+        for f in faces:
+            line = 'f ' + ' '.join([str(_) for _ in f]) + '\n'
+            file.write(line)

cvae.py

@@ -1,7 +1,8 @@
 import os
 import sys
-from configs.iccv.config_abl_all_cape_f import config
+from configs.iccv.config_abl_all_skirt_var import config
 
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
 
@@ -479,7 +480,7 @@ def test():
 
 
 if __name__ == '__main__':
-    init_wandb()
+    # init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())

cvae_curv.py

@@ -153,11 +153,11 @@ def dice_dense(prediction, ground_truth, weight_map=None):
     return tf.reduce_mean(dice_score)
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     with tf.GradientTape() as tape:
 
-        pred, mean, logvar = model([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
+        pred, mean, logvar = model([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
 
         ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
         dice = dice_dense(pred, batch['uv_curvature'])
@@ -189,7 +189,7 @@ def train_step(batch):
 
 @tf.function
 def valid_step(batch):
-    pred, mean, logvar = model([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
+    pred, mean, logvar = model([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
     loss =  ce_uv_loss
@@ -216,7 +216,7 @@ def valid_step(batch):
 
 
 def plot_everything(batch: dict, type: str):
-    pred, mean, logvar = model([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
+    pred, mean, logvar = model([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
     
     pred = np.argmax(pred.numpy(), axis=-1)
     mesh_pred = uv2mesh(pred)
@@ -251,90 +251,54 @@ def plot_everything(batch: dict, type: str):
 
 
 
-def sample(folder):
+def sample():
-    load_model(model,folder)
+    iteration = load_model(model, f'checkpoints/iccv/cvae_curv_3', return_iteration=True)
     for batch in dataset_train:
-        batch = static_dataset_train.expand_batch(batch_to_dict(batch, signature_dynamic))
+        batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
-        uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
+        nr_of_samples = 4
-        nr_of_samples = 16
 
-        # pred = model.sample(batch['uv_static'], batch['uv_body_posed'], batch['uv_mask'])
+        for i in range(4):
-        pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
+            # pred = model.sample(batch['uv_static'], batch['uv_body_posed'], batch['uv_mask'])
+            # pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
+            pred = model.sample(tf.tile(batch['uv_static'][i][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_body_posed'][i][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_mask'][i][None,:,:], [nr_of_samples,1,1]))
+            # pred,_,_ = model([tf.tile(batch['uv_static'][0][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_body_posed'][0][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_mask'][0][None,:,:], [nr_of_samples,1,1])], training=False)
+            # pred = model.call_sample([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
         
-        ce_uv_loss = scce(tf.tile(batch['uv_curvature'][0][tf.newaxis,:,:], [nr_of_samples,1,1]), pred)
+            orig_img = np.argmax(batch['uv_curvature'][i].numpy(), axis=-1)
-
+            pred_img = np.argmax(pred.numpy(), axis=-1)
-
+            img = np.concatenate((orig_img, np.concatenate(pred_img, axis=1)), axis=1)
-        mesh_pred = uv2mesh(pred).numpy().argmax(axis=-1)
-        mesh_orig = batch['mesh_curvature'][0].numpy()
-
-        F = np.load("custom_utils/smpl_faces.npy")
-        mask = batch['mesh_mask'].numpy().astype(bool)[0]
-        _, faces = _maskFaces(np.ones((14475, 3)), F, mask)
-        mesh_pred = [mesh_pred[i, mask] for i in range(mesh_pred.shape[0])] 
-        curv_color = [np.zeros((mesh_pred[i].shape[0], 3)) for i in range(len(mesh_pred))]
-        mesh_orig = mesh_orig[mask] + 1
-
-        colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, 6+1)])
-        curv_color_gt = np.zeros((mesh_pred[0].shape[0], 3))
-        for i in range(6+1):
-            for j in range(len(mesh_pred)):
-                curv_color[j][mesh_pred[j] == i, :] = colors[i]
-            curv_color_gt[mesh_orig == i, :] = colors[i]
-
-        mesh_base = batch['mesh_posed'][0].numpy()[mask, :]
-        meshes = []
-        meshes.append(go.Mesh3d(
-                    # 8 vertices of a cube
-                    x=mesh_base[:,0],
-                    y=mesh_base[:,1],
-                    z=mesh_base[:,2],
-                    # i, j and k give the vertices of triangles
-                    i = faces[:,0],
-                    j = faces[:,1],
-                    k = faces[:,2],
-                    vertexcolor=curv_color_gt,
-                    text='gt'
-                    ))
-
-        for i in range(nr_of_samples):
-            x = mesh_base.copy()
-            x[:, 1] += 1 * (i + 1)
-            meshes.append(go.Mesh3d(
-                        # 8 vertices of a cube
-                        x=x[:,0],
-                        y=x[:,1],
-                        z=x[:,2],
-                        # i, j and k give the vertices of triangles
-                        i = faces[:,0],
-                        j = faces[:,1],
-                        k = faces[:,2],
-                        vertexcolor=curv_color[i]
-                        ))
-
-
-
-
-        fig = go.Figure(data=meshes)
-
-        fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=nr_of_samples-1, z=1))
-        fig.update_layout(
-            scene = dict(
-                xaxis = dict(nticks=4, range=[-1,1],),
-                            yaxis = dict(nticks=4, range=[-1,nr_of_samples + 1],),
-                            zaxis = dict(nticks=4, range=[-1,1],),)
-                            )
-
-        # fig.show()
-
-        pred = pred.numpy().argmax(-1)
-        frames = [Image.fromarray(pred[i]/6*255) for i in range(pred.shape[0])]
-        frames[0].save("temp/curv2.gif", format="GIF", append_images=frames[1:],
-               save_all=True, duration=500, loop=0)
 
+            colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, 6+1)])
+            color_img = np.zeros((img.shape[0], img.shape[1], 3), np.uint8)
+            for i in range(7):
+                color_img[img == i, :] = colors[i]
+            ex.imshow(color_img).show()
+            print()
         print()
 
+def sample_2(batch):
+    nr_of_samples = 4
+
+    # pred = model.sample(batch['uv_static'], batch['uv_body_posed'], batch['uv_mask'])
+    # pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
+    # pred = model.sample(tf.tile(batch['uv_static'][0][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_body_posed'][0][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_mask'][0][None,:,:], [nr_of_samples,1,1]))
+    pred,_,_ = model([tf.tile(batch['uv_static'][0][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_body_posed'][0][None,:,:,:], [nr_of_samples,1,1,1]),tf.tile(batch['uv_curvature'][0][None,:,:,:], [nr_of_samples,1,1,1]), tf.tile(batch['uv_mask'][0][None,:,:], [nr_of_samples,1,1])], training=False)
+    # pred = model.call_sample([batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
+
+    orig_img = np.argmax(batch['uv_curvature'][0].numpy(), axis=-1)
+    pred_img = np.argmax(pred.numpy(), axis=-1)
+    img = np.concatenate((orig_img, np.concatenate(pred_img, axis=1)), axis=1)
+
+    colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, 6+1)])
+    color_img = np.zeros((img.shape[0], img.shape[1], 3), np.uint8)
+    for i in range(7):
+        color_img[img == i, :] = colors[i]
+    ex.imshow(color_img).show()
+    print()
+
+
 if __name__ == '__main__':
-    init_wandb()
+    # init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())
@@ -372,6 +336,8 @@ if __name__ == '__main__':
 
     model = CVAE(config)
 
+    sample()
+
     # lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(0.0001, decay_steps=30000, decay_rate=0.1, staircase=False)
     optimizer = tf.optimizers.Adam(learning_rate=config['lr']) #0.0001
     g_balancing_coeff = config['starting_balancing_coeff']

cvae_pyramid.py

@@ -1,7 +1,8 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_64_pre_cape_f import config
+from configs.iccv.config_abl_pyr_32_64_128_256_seq import config
 
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
 
@@ -220,20 +221,104 @@ def train_step(batch):
         out_levels = model([levels_input, conds], training=True)
 
         if config['use_skinning']:
-            mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+            mesh_orig = batch['mesh_unposed']
         else:
-            mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+            mesh_orig = batch['mesh_posed']
 
         output = dict()
         reconstr_loss_total = 0
         kl_total = 0
 
-        #for i, res in enumerate(config['pyramid']['resolutions']):
+        for i, res in enumerate(config['pyramid']['resolutions']):
-        i = -1
+        # i = -1
-        res = config['pyramid']['resolutions'][-1]
+            res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512
+            res_modifier = '_' + str(res) if res != 512 else ''
+            pred, mean, logvar = out_levels[i]
+
+            if config['use_skinning']:
+                uv_orig = batch['uv_unposed' + res_modifier]
+            else:
+                uv_orig = batch['uv_posed' + res_modifier]
+
+            mesh_pred = uv2mesh(pred)
+
+            if config['use_skinning']:
+                shape = batch['pose_shape'][:, 72:]
+                gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+                shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
+
+                mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
+                mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
+            else:
+                mesh_pred_posed = mesh_pred
+
+            # is the output already masked?
+
+            e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+            c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+            c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
+            l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1) * batch['uv_mask' + res_modifier], axis=[1, 2]))
+            # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+            # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
+            l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
+            n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'])
+            kl = kl_loss(mean, logvar)
+
+            if config['use_extra_losses']:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+                if not config['is_cape']:
+                    reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+            else:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
+
+            if config['use_norm_loss'] and step > 2000:
+                reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+            
+            kl_total += kl
+
+            mean = tf.reduce_mean(mean)
+            logvar = tf.reduce_mean(logvar)
+
+            metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+
+            output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
+                                    'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
+                                    'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss' + res_modifier: n_loss,
+                                    'train/euclid_error' + res_modifier: metric, 'train/l2_mesh_loss' + res_modifier: l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
+
+        loss = reconstr_loss_total + balancing_coeff * kl_total
+
+    gradients = tape.gradient(loss, model.trainable_variables)
+    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
+    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
+
+
+@tf.function
+def valid_step(batch):
+    levels_input, conds = group_inputs_for_levels(batch, config)
+    out_levels = model([levels_input, conds], training=False)
+
+
+    if config['use_skinning']:
+        mesh_orig = batch['mesh_unposed']
+    else:
+        mesh_orig = batch['mesh_posed']
+
+    output = dict()
+    reconstr_loss_total = 0
+    kl_total = 0
+
+    for i, res in enumerate(config['pyramid']['resolutions']):
+    # i = -1
+        res = config['pyramid']['resolutions'][i] if i != len(config['pyramid']['resolutions']) - 1 else 512
         res_modifier = '_' + str(res) if res != 512 else ''
         pred, mean, logvar = out_levels[i]
 
+        if config['use_skinning']:
+            uv_orig = batch['uv_unposed' + res_modifier]
+        else:
+            uv_orig = batch['uv_posed' + res_modifier]
+
         mesh_pred = uv2mesh(pred)
 
         if config['use_skinning']:
@@ -245,13 +330,12 @@ def train_step(batch):
             mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
         else:
             mesh_pred_posed = mesh_pred
-
         # is the output already masked?
 
         e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
         c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1) * batch['uv_mask' + res_modifier], axis=[1, 2]))
         # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
         # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
         l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
@@ -275,83 +359,10 @@ def train_step(batch):
 
         metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
 
-        output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
+        output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
-                                 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
+                                    'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
-                                 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss,
+                                    'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss' + res_modifier: n_loss,
-                                 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
+                                    'valid/euclid_error' + res_modifier: metric, 'valid/l2_mesh_loss' + res_modifier: l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
-
-        loss = reconstr_loss_total + balancing_coeff * kl_total
-
-    gradients = tape.gradient(loss, model.trainable_variables)
-    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
-    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
-
-
-@tf.function
-def valid_step(batch):
-    levels_input, conds = group_inputs_for_levels(batch, config)
-    out_levels = model([levels_input, conds], training=False)
-
-
-    if config['use_skinning']:
-        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
-    else:
-        mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
-
-    output = dict()
-    reconstr_loss_total = 0
-    kl_total = 0
-
-    #for i, res in enumerate(config['pyramid']['resolutions']):
-    i = -1
-    res = config['pyramid']['resolutions'][-1]
-    res_modifier = '_' + str(res) if res != 512 else ''
-    pred, mean, logvar = out_levels[i]
-
-    mesh_pred = uv2mesh(pred)
-
-    if config['use_skinning']:
-        shape = batch['pose_shape'][:, 72:]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-        mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
-    else:
-        mesh_pred_posed = mesh_pred
-    # is the output already masked?
-
-    e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
-    c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
-    c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-    l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
-    # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-    l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
-    n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'])
-    kl = kl_loss(mean, logvar)
-
-    if config['use_extra_losses']:
-        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
-        if not config['is_cape']:
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
-    else:
-        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
-    
-    if config['use_norm_loss'] and step > 2000:
-        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
-        
-    kl_total += kl
-
-    mean = tf.reduce_mean(mean)
-    logvar = tf.reduce_mean(logvar)
-
-    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
-
-    output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
-                                 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
-                                'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
-                                'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
 
     loss = reconstr_loss_total + balancing_coeff * kl_total
 
@@ -417,6 +428,7 @@ def test_step(batch):
 
 
 def plot_everything(batch: dict, type: str):
+    nr_to_plot = 4
     if config['use_skinning']:
         mesh_orig, uv_orig = batch['mesh_unposed'].numpy(), batch['uv_unposed'].numpy()
     else:
@@ -426,8 +438,8 @@ def plot_everything(batch: dict, type: str):
     output_levels = model(levels_input, training=False)
 
     mesh_pred_levels = [uv2mesh(output_levels[i][0]).numpy() for i in range(len(output_levels))]
-    mesh_orig_posed = batch['mesh_posed'].numpy()
+    mesh_orig_posed = batch['mesh_posed'].numpy()[:nr_to_plot]
-    body = batch['mesh_body_posed'].numpy()
+    body = batch['mesh_body_posed'].numpy()[:nr_to_plot]
     
     orig_img = (uv_orig + 1) / 2
     uv_static_img = (batch['uv_static'].numpy() + 1) / 2
@@ -436,10 +448,10 @@ def plot_everything(batch: dict, type: str):
     pred_img = np.concatenate([tf.image.resize(output_levels[i][0], (512, 256), tf.image.ResizeMethod.LANCZOS5) for i in range(len(output_levels))], axis=2)
     pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis])
     img = tf.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2)
-    imgs = [wandb.Image(img[i]) for i in range(4)]
+    imgs = [wandb.Image(img[i]) for i in range(nr_to_plot)]
 
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
-    mask = batch['mesh_mask'].numpy().astype(bool)
+    mask = batch['mesh_mask'].numpy().astype(bool)[:nr_to_plot]
     _, faces = maskFacesBatch(np.ones_like(mesh_orig), F, mask)
     
     if config['use_skinning']:
@@ -448,30 +460,30 @@ def plot_everything(batch: dict, type: str):
         shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]).numpy()
 
 
-        gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])]
+        gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(nr_to_plot)]
     
-        mesh_unposed_shaped_levels = [[] for _ in range(mask.shape[0])]
+        mesh_unposed_shaped_levels = [[] for _ in range(nr_to_plot)]
         for i in range(len(output_levels)):
-            mesh_unposed_shaped = [mesh_pred_levels[i][j, mask[j], :] + shape_offsets[j, mask[j]] for j in range(mask.shape[0])]
+            mesh_unposed_shaped = [mesh_pred_levels[i][j, mask[j], :] + shape_offsets[j, mask[j]] for j in range(nr_to_plot)]
-            for k in range(mask.shape[0]):
+            for k in range(nr_to_plot):
                 mesh_unposed_shaped_levels[k].append(mesh_unposed_shaped[k])
         
         # full res version
-        mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32)
+        mesh_unposed_shaped_full = np.zeros((nr_to_plot, config['smpl_res'], 3), dtype=np.float32)
-        for i in range(mask.shape[0]):
+        for i in range(nr_to_plot):
             mesh_unposed_shaped_full[i, mask[i], :] = mesh_unposed_shaped[i]
 
-        mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_unposed_shaped_full).numpy()
+        mesh_posed = smpl.run_garment(batch['pose_shape'][:nr_to_plot, :72], batch['pose_shape'][:nr_to_plot, 72:], mesh_unposed_shaped_full).numpy()
     else:
         mesh_posed = mesh_pred_levels[-1]
-        gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])]
+        gt = [mesh_orig[i][mask[i], :] for i in range(nr_to_plot)]
-        mesh_unposed_shaped_levels = [[mesh_pred_levels[i][j, mask[j], :] for i in range(len(output_levels))] for j in range(mask.shape[0])]
+        mesh_unposed_shaped_levels = [[mesh_pred_levels[i][j, mask[j], :] for i in range(len(output_levels))] for j in range(nr_to_plot)]
 
 
-    gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(mask.shape[0])]
+    gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(nr_to_plot)]
     mesh_posed_fixed = fix_collision(mesh_posed, body, mask).numpy()
 
-    mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])]
+    mesh_posed = [mesh_posed[j, mask[j], :] for j in range(nr_to_plot)]
     
     if config['is_cape']:
         collision = mesh_posed
@@ -487,11 +499,11 @@ def plot_everything(batch: dict, type: str):
     if config['is_cape']:
         figs_coll = dict()
     else:
-        garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(body.shape[0])]
+        garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(nr_to_plot)]
         collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(mesh_posed))]
-        gt_posed = [batch['mesh_posed'].numpy()[i, mask[i], :] for i in range(mask.shape[0])]
+        gt_posed = [batch['mesh_posed'].numpy()[i, mask[i], :] for i in range(nr_to_plot)]
         collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(gt_posed))]
-        figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i]) for i in range(4) }
+        figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i]) for i in range(nr_to_plot) }
 
     return { **figs, **figs_coll, **{ type + '/images': imgs, } }
 
@@ -728,9 +740,18 @@ def generate_results():
     pass
 
 @tf.function
-def speed_step(levels_input, conds):
+def speed_step(levels_input, conds, pose_shape, mask):
+    shape = pose_shape[:, 72:]
+    gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+    shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
 
-    return model.sample([levels_input, conds], training=False)
+    # pred = model.sample([levels_input, conds])
+    out_levels = model([levels_input, conds], training=False)
+    pred = out_levels[-1][0]
+    mesh_pred = uv2mesh(pred)
+    mesh_pred_shaped = mesh_pred + shape_offsets * mask[:,:,tf.newaxis]
+    mesh_pred_posed = smpl.run_garment(pose_shape[:, :72], pose_shape[:, 72:], mesh_pred_shaped)
+    return mesh_pred_posed
 
 
 
@@ -760,8 +781,12 @@ if __name__ == '__main__':
                                         resolutions=dataset_resolutions, 
                                         in_memory=config['dataset_in_memory'], 
                                         is_cape=config['is_cape'],
-                                        frames_file=config['frames_file'] if 'frames_file' in config.keys() else None)
+                                        frames_file=config['frames_file'] if 'frames_file' in config.keys() else None,
+                                        frames_file_skirt=config['frames_file'] if 'frames_file' in config.keys() else '',
+                                        folder_skirt=config['train_dir_skirt'] if 'train_dir_skirt' in config.keys() else '',
+                                        )
     static_dataset_train = StaticDataset(folder=config['train_dir'], 
+                                        folder_skirt=config['train_dir_skirt'] if 'train_dir_skirt' in config.keys() else '',
                                         signature=config['signature_static'], 
                                         resolutions=dataset_resolutions, 
                                         in_memory=True,
@@ -772,8 +797,12 @@ if __name__ == '__main__':
                                         resolutions=dataset_resolutions, 
                                         in_memory=config['dataset_in_memory'], 
                                         is_cape=config['is_cape'],
-                                        frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None)
+                                        frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None,
+                                        frames_file_skirt=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else '',
+                                        folder_skirt=config['valid_dir_skirt'] if 'valid_dir_skirt' in config.keys() else '',
+                                        )
     static_dataset_valid = StaticDataset(folder=config['valid_dir'], 
+                                        folder_skirt=config['valid_dir_skirt'] if 'valid_dir_skirt' in config.keys() else '',
                                         signature=config['signature_static'], 
                                         resolutions=dataset_resolutions, 
                                         in_memory=True, 
@@ -803,33 +832,38 @@ if __name__ == '__main__':
     if config['pretrained_model'] != '':
         # assert len(config['pyramid']['resolutions']) == 1
         load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration'])
-
-    if len(config['pyramid']['resolutions']) == 1:
         model.static_enc.trainable = False
         model.body_enc.trainable = False
         if config['use_curvature']:
             model.curv_enc.trainable = False
     else:
-        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
+        if len(config['pyramid']['resolutions']) == 1:
-        model.static_enc.trainable = False
+            model.static_enc.trainable = False
-        model.body_enc.trainable = False
+            model.body_enc.trainable = False
-        if config['use_curvature']:
+            if config['use_curvature']:
-            model.curv_enc.trainable = False
+                model.curv_enc.trainable = False
+        else:
+            load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
+            model.static_enc.trainable = False
+            model.body_enc.trainable = False
+            if config['use_curvature']:
+                model.curv_enc.trainable = False
 
+    # load_model(model.levels[0], 'checkpoints/iccv/iccv_pyr_64_cape_f')
 
     # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
     # model.levels[0].upscale_enhancer.trainable = False
 
 
-    for i in range(len(model.levels)):
+    for i in range(len(model.levels)-1):
         load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer'])
         model.levels[i].upscale_enhancer.trainable = False
     # if config['pyramid']['resolutions'][-1] != 512:
     #     load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
     #     model.upscale_enhancer.trainable = False
 
-    for i in range(len(model.levels)-1):
+    # for i in range(len(model.levels)-1):
-        model.levels[i].trainable = False
+    #     model.levels[i].trainable = False
 
     # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
     # load_model(model.levels[0], config['pyramid']['pretrained_pyramid'])
@@ -841,10 +875,10 @@ if __name__ == '__main__':
     for batch in dataset_train:
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
 
-        # levels_input, conds = group_inputs_for_levels(batch, config)
+        levels_input, conds = group_inputs_for_levels(batch, config)
 
         # start = time.perf_counter()
-        # out = speed_step(levels_input, conds)
+        # out = speed_step(levels_input, conds, batch['pose_shape'] ,batch['mesh_mask'])
         # t = time.perf_counter() - start
         # print(t)
         # times.append(t)
@@ -889,4 +923,4 @@ if __name__ == '__main__':
 
         step += 1
     # print('mean:')
-    # print(np.mean(times[1:]))
+    # print(np.mean(times[10:]))

dataset.py

@@ -54,10 +54,11 @@ from custom_utils.custom_utils import nest_conditions, batch_to_dict
 
 
 class StaticDataset():
-    def __init__(self, folder, signature, use_filled=False, resolutions=[512], in_memory=True, is_cape=False) -> None:
+    def __init__(self, folder, signature, folder_skirt='', use_filled=False, resolutions=[512], in_memory=True, is_cape=False) -> None:
         self.store = dict()
         self.signature = signature
         self.folder = folder
+        self.folder_skirt = folder_skirt
         self.in_memory = in_memory
         assert set(resolutions).issubset(set([32, 64, 128, 256, 512]))
         self.possible_keys = ['uv_static', 'uv_static_32', 'uv_static_64', 'uv_static_128', 'uv_static_256',
@@ -85,6 +86,9 @@ class StaticDataset():
 
     def read(self, id):
         data = dict()
+        temp_folder = self.folder
+        if not os.path.exists(os.path.join(temp_folder, 'uv_mask', id + '.npz')):
+            temp_folder = self.folder_skirt
 
         for res in self.resolutions:
             res_string = ''
@@ -92,23 +96,23 @@ class StaticDataset():
                 res_string = '_' + str(res)
 
             if 'uv_static' + res_string in self.signature.keys():
-                uv_static = np.load(os.path.join(self.folder, 'uv_static' + self.filled + res_string, id +  '.npz')); uv_static = uv_static['uv_static' + self.filled]; data['uv_static' + res_string] = uv_static
+                uv_static = np.load(os.path.join(temp_folder, 'uv_static' + self.filled + res_string, id +  '.npz')); uv_static = uv_static['uv_static' + self.filled]; data['uv_static' + res_string] = uv_static
             if 'uv_mask' + res_string in self.signature.keys():
                 if self.is_cape:
                     data['uv_mask' + res_string] = self.uv_masks[res]
                 else:
-                    uv_mask = np.load(os.path.join(self.folder, 'uv_mask' + res_string, id + '.npz')); uv_mask=uv_mask['uv_mask']; uv_mask = uv_mask.astype(np.float32); data['uv_mask' + res_string] = uv_mask
+                    uv_mask = np.load(os.path.join(temp_folder, 'uv_mask' + res_string, id + '.npz')); uv_mask=uv_mask['uv_mask']; uv_mask = uv_mask.astype(np.float32); data['uv_mask' + res_string] = uv_mask
 
 
         if 'mesh_static' in self.signature.keys():
-            mesh_static = np.load(os.path.join(self.folder, 'mesh_static', id +  '.npz')); mesh_static = mesh_static['mesh_static']; data['mesh_static'] = mesh_static.astype(np.float32)
+            mesh_static = np.load(os.path.join(temp_folder, 'mesh_static', id +  '.npz')); mesh_static = mesh_static['mesh_static']; data['mesh_static'] = mesh_static.astype(np.float32)
         if 'mesh_mask' in self.signature.keys():
             if self.is_cape:
                 data['mesh_mask'] = np.ones((3638), np.float32)
             else:
-                mesh_mask = np.load(os.path.join(self.folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32); data['mesh_mask'] = mesh_mask
+                mesh_mask = np.load(os.path.join(temp_folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32); data['mesh_mask'] = mesh_mask
         if 'uv_shaped_body' in self.signature.keys():
-            uv_shaped_body = np.load(os.path.join(self.folder, 'uv_shaped_body', id + '.npz')); uv_shaped_body = uv_shaped_body['uv_shaped_body']; data['uv_shaped_body'] = uv_shaped_body
+            uv_shaped_body = np.load(os.path.join(temp_folder, 'uv_shaped_body', id + '.npz')); uv_shaped_body = uv_shaped_body['uv_shaped_body']; data['uv_shaped_body'] = uv_shaped_body
 
         return data
 
@@ -135,7 +139,7 @@ class StaticDataset():
 
 class DatasetIdx(tf.data.Dataset):
 
-    def __new__(cls, folder, shuffle=True, is_cape=False, testing=False, frames_file=None):
+    def __new__(cls, folder, shuffle=True, is_cape=False, testing=False, frames_file=None, folder_skirt=None, frames_file_skirt=''):
         if frames_file is None:
             uv_static_folder = os.path.join(folder, 'pose_shape') 
             frames = sorted(os.listdir(uv_static_folder))
@@ -156,6 +160,12 @@ class DatasetIdx(tf.data.Dataset):
                 lines = [line.strip() for line in lines]
             frames = lines
 
+            if frames_file_skirt != '':
+                with open(os.path.join(folder_skirt, frames_file_skirt), 'r') as f:
+                    lines = f.readlines()
+                    lines = [line.strip() for line in lines]
+                frames.extend(lines)
+
         if shuffle:
             random.shuffle(frames)
 
@@ -194,10 +204,12 @@ class DatasetFactory():
                     use_one_hot=False,
                     use_no_orient=True,
                     testing=False,
-                    frames_file=None):
+                    frames_file=None,
+                    frames_file_skirt='',
+                    folder_skirt='',):
         assert set(resolutions).issubset(set([32, 64, 128, 256, 512]))
 
-        dataset_idx = DatasetIdx(folder, shuffle, is_cape=is_cape, testing=testing, frames_file=frames_file)
+        dataset_idx = DatasetIdx(folder, shuffle, is_cape=is_cape, testing=testing, folder_skirt=folder_skirt, frames_file=frames_file, frames_file_skirt=frames_file_skirt)
 
         separator = '_'
         if is_cape:
@@ -222,6 +234,11 @@ class DatasetFactory():
             id, frame_nr = frame_split[0].numpy().decode("utf-8"), frame_split[1].numpy().decode("utf-8")
             # id, frame_nr = frame_split[0].numpy(), frame_split[1].numpy()
             # static_info = static_data[id]
+
+            temp_folder = folder
+            if not os.path.exists(os.path.join(temp_folder, 'pose_shape',  id + separator + frame_nr + '.npy')):
+                temp_folder = folder_skirt
+
             item = dict()
 
             if 'id' in signature.keys():
@@ -229,23 +246,23 @@ class DatasetFactory():
             if 'frame_nr' in signature.keys():
                 item['frame_nr'] = frame_nr
             if 'pose_shape' in signature.keys():
-                pose_shape = np.load(os.path.join(folder, 'pose_shape',  id + separator + frame_nr + '.npy'))
+                pose_shape = np.load(os.path.join(temp_folder, 'pose_shape',  id + separator + frame_nr + '.npy'))
                 if use_no_orient:
                     pose_shape[:3] = 0
                 item['pose_shape'] = pose_shape
             if 'mesh_body_posed' in signature.keys():
                 if use_no_orient:
-                    mesh_posed_body_no_orient = np.load(os.path.join(folder, 'mesh_posed_body_no_orient', id + separator + frame_nr + '.npz')); mesh_posed_body_no_orient = mesh_posed_body_no_orient['mesh_posed_body_no_orient']
+                    mesh_posed_body_no_orient = np.load(os.path.join(temp_folder, 'mesh_posed_body_no_orient', id + separator + frame_nr + '.npz')); mesh_posed_body_no_orient = mesh_posed_body_no_orient['mesh_posed_body_no_orient']
                     item['mesh_body_posed'] = mesh_posed_body_no_orient
                 else:
-                    mesh_body_posed = np.load(os.path.join(folder, 'mesh_body_posed', id + '_' + frame_nr + '.npy'))
+                    mesh_body_posed = np.load(os.path.join(temp_folder, 'mesh_body_posed', id + '_' + frame_nr + '.npy'))
                     item['mesh_body_posed'] = mesh_body_posed
             if 'mesh_posed' in signature.keys():
                 if use_no_orient:
-                    mesh_posed = np.load(os.path.join(folder, 'mesh_posed_no_orient', id + separator + frame_nr + '.npz')); mesh_posed = mesh_posed['mesh_posed_no_orient'].astype(np.float32)
+                    mesh_posed = np.load(os.path.join(temp_folder, 'mesh_posed_no_orient', id + separator + frame_nr + '.npz')); mesh_posed = mesh_posed['mesh_posed_no_orient'].astype(np.float32)
                     item['mesh_posed'] = mesh_posed
                 else:
-                    mesh_posed = np.load(os.path.join(folder, 'mesh_posed', id + separator + frame_nr + '.npz')); mesh_posed = mesh_posed['mesh_posed'].astype(np.float32)
+                    mesh_posed = np.load(os.path.join(temp_folder, 'mesh_posed', id + separator + frame_nr + '.npz')); mesh_posed = mesh_posed['mesh_posed'].astype(np.float32)
                     item['mesh_posed'] = mesh_posed
             # if 'mesh_unposed' in signature.keys():
             #     mesh_unposed = np.load(os.path.join(folder, 'mesh_unposed', id + '_' + frame_nr + '.npz')); mesh_unposed = mesh_unposed['mesh_unposed']
@@ -255,12 +272,12 @@ class DatasetFactory():
             #     item['uv_unposed'] = uv_unposed
             if 'mesh_unposed' in signature.keys():
                 # print('one_hot')
-                mesh_unposed_no_shape = np.load(os.path.join(folder, 'mesh_unposed_no_shape' + one_hot, id + separator + frame_nr + '.npz')); mesh_unposed_no_shape = mesh_unposed_no_shape['mesh_unposed_no_shape']
+                mesh_unposed_no_shape = np.load(os.path.join(temp_folder, 'mesh_unposed_no_shape' + one_hot, id + separator + frame_nr + '.npz')); mesh_unposed_no_shape = mesh_unposed_no_shape['mesh_unposed_no_shape']
                 item['mesh_unposed'] = mesh_unposed_no_shape
 
 
             if 'mesh_curvature' in signature.keys():
-                mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature', id + separator + frame_nr + '.npz')); mesh_curvature = mesh_curvature['mesh_curvature']
+                mesh_curvature = np.load(os.path.join(temp_folder, 'mesh_curvature', id + separator + frame_nr + '.npz')); mesh_curvature = mesh_curvature['mesh_curvature']
                 item['mesh_curvature'] = mesh_curvature.astype(np.int32)
 
 
@@ -270,7 +287,7 @@ class DatasetFactory():
                     res_string = '_' + str(res)
 
                 if 'uv_curvature' + res_string in signature.keys():
-                    uv_curvature = np.load(os.path.join(folder, 'uv_curvature' + res_string, id + separator + frame_nr + '.npz')); 
+                    uv_curvature = np.load(os.path.join(temp_folder, 'uv_curvature' + res_string, id + separator + frame_nr + '.npz')); 
                     if res_string != '':
                         uv_curvature = uv_curvature['uv_curvature'] 
                     else:
@@ -279,24 +296,24 @@ class DatasetFactory():
                     item['uv_curvature' + res_string] = uv_curvature
 
                 if 'uv_unposed' + res_string in signature.keys():
-                    uv_unposed_no_shape = np.load(os.path.join(folder, 'uv_unposed_no_shape' + one_hot_2 + res_string, id + separator + frame_nr + '.npz')); uv_unposed_no_shape = uv_unposed_no_shape['uv_unposed_no_shape']
+                    uv_unposed_no_shape = np.load(os.path.join(temp_folder, 'uv_unposed_no_shape' + one_hot_2 + res_string, id + separator + frame_nr + '.npz')); uv_unposed_no_shape = uv_unposed_no_shape['uv_unposed_no_shape']
                     item['uv_unposed' + res_string] = uv_unposed_no_shape
 
                 if 'uv_body_posed' + res_string in signature.keys():
                     if use_no_orient:
-                        uv_posed_body_no_orient = np.load(os.path.join(folder, uv_posed_body_no_orient_folder_name + res_string, id + separator + frame_nr + '.npz'))
+                        uv_posed_body_no_orient = np.load(os.path.join(temp_folder, uv_posed_body_no_orient_folder_name + res_string, id + separator + frame_nr + '.npz'))
                         uv_posed_body_no_orient = uv_posed_body_no_orient['uv_posed_body_no_orient']
                         item['uv_body_posed' + res_string] = uv_posed_body_no_orient
                     else:
-                        uv_body_posed = np.load(os.path.join(folder, 'uv_body_posed', id + '_' + frame_nr + '.npz')); uv_body_posed = uv_body_posed['uv_body']
+                        uv_body_posed = np.load(os.path.join(temp_folder, 'uv_body_posed', id + '_' + frame_nr + '.npz')); uv_body_posed = uv_body_posed['uv_body']
                         item['uv_body_posed' + res_string] = uv_body_posed
 
                 if 'uv_posed' + res_string in signature.keys():
                     if use_no_orient:
-                        uv_posed = np.load(os.path.join(folder, 'uv_posed_no_orient' + res_string, id + separator + frame_nr + '.npz')); uv_posed = uv_posed['uv_posed_no_orient']
+                        uv_posed = np.load(os.path.join(temp_folder, 'uv_posed_no_orient' + res_string, id + separator + frame_nr + '.npz')); uv_posed = uv_posed['uv_posed_no_orient']
                         item['uv_posed' + res_string] = uv_posed
                     else:
-                        uv_posed = np.load(os.path.join(folder, 'uv_posed' + res_string, id + separator + frame_nr + '.npz')); uv_posed = uv_posed['uv_gt']
+                        uv_posed = np.load(os.path.join(temp_folder, 'uv_posed' + res_string, id + separator + frame_nr + '.npz')); uv_posed = uv_posed['uv_gt']
                         item['uv_posed' + res_string] = uv_posed
 
             # print('here')

evaluate_ae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_post import config
+from configs.iccv.config_abl_all import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -103,11 +103,13 @@ if __name__ == '__main__':
     ids = set(ids)
 
     iteration = ''
-
+    if iteration == '':
-    load_model(model, 'checkpoints/post/' + checkpoint_name, iteration=iteration)
+        iteration = load_model(model, 'checkpoints/iccv/' + checkpoint_name, return_iteration=True)
+    else:
+        load_model(model, 'checkpoints/iccv/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')
 
-    output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/local-data_128/results/iccv/' + checkpoint_name + '-' + iteration
 
 
     os.makedirs(output_folder, exist_ok=True)

evaluate_ae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_64_128_cape_f import config
+from configs.iccv.config_abl_pyr_32_64_128_seq import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf

evaluate_cape_unif_pyr.py

@@ -0,0 +1,191 @@
+import os
+import sys
+from configs.iccv.config_abl_pyr_64_cape_m_00032_SL import config
+
+os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
+import tensorflow as tf
+
+gpus = tf.config.experimental.list_physical_devices('GPU')
+if gpus:
+    try:
+        # Currently, memory growth needs to be the same across GPUs
+        for gpu in gpus:
+            tf.config.experimental.set_memory_growth(gpu, True)
+        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
+        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
+    except RuntimeError as e:
+        # Memory growth must be set before GPUs have been initialized
+        print(e)
+
+import glob
+import time
+import argparse
+import wandb
+import tqdm
+import random
+import numpy as np
+import plotly.graph_objects as go
+import plotly.express as ex
+from PIL import Image
+from postprocessing import fix_collision
+
+if config['is_skirt']:
+    from losses import edge_loss_skirt as edge_loss
+else:
+    from losses import edge_loss
+
+
+
+from losses import collision_ratio, kl_loss #, concept_loss
+# from losses import collision_penalty as collision_penalty
+from losses import collision_loss as collision_penalty
+from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
+from dataset import DatasetFactory, StaticDataset
+from custom_utils.smpl import SMPL
+from models.pyramid_model_optimized import PyramidNew as Pyramid
+from custom_utils.supersmpl_io import writeOBJ
+from unif_metric import chamfer_and_score
+
+
+uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
+
+def group_inputs_for_levels(batch):
+    levels_input = []
+    for res in config['pyramid']['resolutions']:
+        res_modifier = '_' + str(res) if res != 512 else ''
+        levels_input.append([batch['uv_unposed' + res_modifier], batch['uv_static' + res_modifier], batch['uv_body_posed' + res_modifier], batch['uv_curvature' + res_modifier], batch['uv_mask' + res_modifier], batch['uv_mask']])
+    conds = [batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature']]
+    return levels_input, conds
+
+
+@tf.function
+def step(batch):
+    levels_input, conds = group_inputs_for_levels(batch)
+    out_levels = model([levels_input, conds], training=False)
+    pred = uv2mesh(out_levels[-1][0])
+
+    mesh_pred = uv2mesh(pred)
+
+    # if config['use_skinning']:
+    #     shape = batch['pose_shape'][:, 72:]
+    #     gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+    #     shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
+
+    #     mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
+    #     mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
+    # else:
+    #     mesh_pred_posed = mesh_pred
+        
+    # mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+
+    # return mesh_pred_posed, None #mesh_pred_posed_fixed
+    return mesh_pred
+
+
+if __name__ == '__main__':
+    # init_wandb()
+    parser = argparse.ArgumentParser(description='')
+    parser.add_argument('--name', type=str)
+    args = vars(parser.parse_args())
+
+    skirt_modifier = '_skirt' if config['is_skirt'] else ''
+
+    folder = config['test_dir']
+    smpl = SMPL(use_one_hot=False, orig_smpl=config['is_cape'])
+    model = Pyramid(config)
+
+    # str_split = config['name'].split('_')
+    # test_idx = str_split.index('test')
+    # checkpoint_name = '_'.join(str_split[:test_idx])
+    checkpoint_name = config['name']
+
+    if config['is_cape']:
+        F = np.load("custom_utils/smpl_faces_orig.npy").astype(np.int32)
+    else:
+        F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
+
+
+    # ids = os.listdir(os.path.join(folder, 'pose_shape'))
+    # ids = [id.split('_')[0] for id in ids]
+    # ids = set(ids)
+
+    iteration = ''
+    if iteration == '':
+        iteration = load_model(model, 'checkpoints/iccv/' + checkpoint_name, return_iteration=True)
+    else:
+        load_model(model, 'checkpoints/iccv/' + checkpoint_name, iteration=iteration)
+   
+
+    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
+
+
+    # os.makedirs(output_folder, exist_ok=True)
+
+    # if config['use_skinning']:
+    #     config['signature_dynamic'].pop('mesh_posed')
+    #     config['signature_dynamic'].pop('mesh_unposed')
+    # config['signature_dynamic'].pop('mesh_body_posed')
+    dataset_resolutions = config['pyramid']['resolutions'].copy()
+    if 512 not in dataset_resolutions:
+        dataset_resolutions.append(512)
+    factory = DatasetFactory()
+    # dataset_test = factory.get_dataset(folder=config['test_dir'], 
+    #                                    batch_size=config['batch_size'], 
+    #                                    signature=config['signature_dynamic'], 
+    #                                    resolutions=[config['resolution']], 
+    #                                    in_memory=False, 
+    #                                    do_repeat=False,
+    #                                    use_no_orient=config['remove_global_orientation'],
+    #                                    frames_file=config['frames_file_test'] if 'frames_file_test' in config.keys() else None, 
+    #                                    is_cape=config['is_cape'])
+    # static_dataset_test = StaticDataset(folder=config['test_dir'], 
+    #                                     signature=config['signature_static'], 
+    #                                     resolutions=[config['resolution']], 
+    #                                     in_memory=True,
+    #                                     is_cape=config['is_cape'])
+    
+    dataset_test = factory.get_dataset(folder=config['test_dir'], 
+                                       batch_size=config['batch_size'], 
+                                       signature=config['signature_dynamic'], 
+                                       resolutions=dataset_resolutions, 
+                                       in_memory=False, 
+                                       do_repeat=False,
+                                       use_no_orient=True, 
+                                       frames_file=config['frames_file_test'] if 'frames_file_test' in config.keys() else None, 
+                                       is_cape=config['is_cape'])
+    static_dataset_test = StaticDataset(folder=config['test_dir'], 
+                                        signature=config['signature_static'], 
+                                        resolutions=dataset_resolutions, 
+                                        in_memory=True, 
+                                       is_cape=config['is_cape'])
+    # faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')
+    # ids = os.listdir(faces_folder)
+    # ids = [id.split('.')[0] for id in ids]
+    # faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
+    errors = []
+    euclid = []
+
+    for batch in tqdm.tqdm(dataset_test):
+        batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
+
+        mesh_pred = step(batch)
+        # mesh_pred_posed, mesh_pred_posed_fixed = mesh_pred_posed.numpy(), mesh_pred_posed_fixed.numpy()
+
+        mask = batch['mesh_mask'].numpy().astype(bool)
+
+        for i in range(mask.shape[0]):
+            id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8")
+            x = chamfer_and_score(mesh_pred.numpy()[i, mask[i], :], batch['mesh_unposed'].numpy()[i, mask[i], :])
+            y = np.mean(np.sqrt(np.sum((mesh_pred.numpy()[i, mask[i], :] - batch['mesh_unposed'].numpy()[i, mask[i], :])**2, axis=-1)))
+            errors.append(x[1])
+            euclid.append(y)
+
+            # writeOBJ(os.path.join(output_folder, id + '_' + frame_nr + '.obj'), mesh_pred_posed[i, mask[i], :], faces[id])
+            # np.save(os.path.join(output_folder, id + '_' + frame_nr + '.npy'), mesh_pred_posed[i, mask[i], :])
+            # np.save(os.path.join(output_folder, id + '_' + frame_nr + '_fixed_coll.npy'), mesh_pred_posed_fixed[i, mask[i], :])
+            # writeOBJ(os.path.join(output_folder, id + '_' + frame_nr + '_fixed_coll.obj'), mesh_pred_posed_fixed[i, mask[i], :], faces[id])
+
+    print(np.mean(errors))
+    print(np.mean(euclid))
+    print()
+

get_error.py

@@ -1,5 +1,6 @@
 import os
 import csv
+import glob
 import numpy as np
 
 
@@ -7,15 +8,12 @@ if __name__ == '__main__':
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
     folder = '/home/workspace/data/results/errors/iccv'
 
-    checkpoint_name = 'iccv_pyr_32_64_curv'
+    checkpoint_name = 'iccv_pyr_32_64_128_256_seq_2'
-    checkpoint_name_skirt = 'iccv_pyr_32_64_curv_skirt'
+    checkpoint_name_skirt = 'iccv_pyr_32_64_128_skin_skirt'
-    iteration = '100000'
+    iteration = '185' + '000'
-    iteration_skirt : str = '60000'
+    iteration_skirt : str = '155' + '000'
+    error_type = 'euclidean' # 'euclidean' 'collision' edge normal
 
-    # checkpoint_name = 'abl_skin'
-    # checkpoint_name_skirt = checkpoint_name + '_skirt'
-    # iteration = '70000'
-    # iteration_skirt : str = iteration
 
     errors = []
     errors_skirt = []
@@ -23,48 +21,50 @@ if __name__ == '__main__':
     per_garment_errors_skirt  = { 'Tshirt': [], 'Dress': [], 'Skirt': [], 'Top': [] }
 
 
-    with open(os.path.join(folder, checkpoint_name + '-' + iteration + '.csv'), 'r') as f:
+    with open(os.path.join(folder, f'{checkpoint_name}-{iteration}-{error_type}.csv'), 'r') as f:
         csv_reader = csv.reader(f, delimiter=',')
         for row in csv_reader:
             per_garment_errors[garment_type_table[row[0].split('_')[0]]].append(float(row[1]))
 
-    with open(os.path.join(folder, checkpoint_name_skirt + '-' + iteration_skirt + '.csv'), 'r') as f:
-        csv_reader = csv.reader(f, delimiter=',')
-        for row in csv_reader:
-            per_garment_errors_skirt[garment_type_table[row[0].split('_')[0]]].append(float(row[1]))
-
     print('\nNon-skirt:')
     for key in per_garment_errors.keys():
         avg = np.mean(per_garment_errors[key])
         errors.append(avg)
         print(key + ': ' + str(avg))
-    print('\nSkirt:')
-    for key in per_garment_errors_skirt.keys():
-        avg = np.mean(per_garment_errors_skirt[key])
-        errors_skirt.append(avg)
-        print(key + ': ' + str(avg))
 
     print('\nAvg non-skirt: ' + str(np.mean(errors)))
-    print('Avg skirt: ' + str(np.mean(errors_skirt)))
 
-    cum_avg_shirt = np.mean(per_garment_errors['Tshirt'] + per_garment_errors_skirt['Tshirt'])
+    # with open(os.path.join(folder, f'{checkpoint_name_skirt}-{iteration_skirt}-{error_type}.csv'), 'r') as f:
-    cum_avg_top = np.mean(per_garment_errors['Top'] + per_garment_errors_skirt['Top'])
+    #     csv_reader = csv.reader(f, delimiter=',')
+    #     for row in csv_reader:
+    #         per_garment_errors_skirt[garment_type_table[row[0].split('_')[0]]].append(float(row[1]))
 
-    print('Global tshirt avg: ' + str(cum_avg_shirt))
+    # print('\nSkirt:')
-    print('Global top avg: ' + str(cum_avg_top))
+    # for key in per_garment_errors_skirt.keys():
+    #     avg = np.mean(per_garment_errors_skirt[key])
+    #     errors_skirt.append(avg)
+    #     print(key + ': ' + str(avg))
 
-    print('\nGlobal per garment: ')
+    # print('Avg skirt: ' + str(np.mean(errors_skirt)))
 
-    global_errors = []
+    # cum_avg_shirt = np.mean(per_garment_errors['Tshirt'] + per_garment_errors_skirt['Tshirt'])
-    per_garment_errors['Tshirt'].extend(per_garment_errors_skirt['Tshirt'])
+    # cum_avg_top = np.mean(per_garment_errors['Top'] + per_garment_errors_skirt['Top'])
-    per_garment_errors['Top'].extend(per_garment_errors_skirt['Top'])
-    per_garment_errors['Skirt'] = per_garment_errors_skirt['Skirt']
-    per_garment_errors['Dress'] = per_garment_errors_skirt['Dress']
-    for key in per_garment_errors.keys():
-        avg = np.mean(per_garment_errors[key])
-        global_errors.append(avg)
-        print(key + ': ' + str(avg), 'samples: ' + str(len(per_garment_errors[key])))
 
-    print('Global avg: ' + str(np.mean(global_errors)))
+    # print('Global tshirt avg: ' + str(cum_avg_shirt))
-    print(len(global_errors))
+    # print('Global top avg: ' + str(cum_avg_top))
+
+    # print('\nGlobal per garment: ')
+
+    # global_errors = []
+    # per_garment_errors['Tshirt'].extend(per_garment_errors_skirt['Tshirt'])
+    # per_garment_errors['Top'].extend(per_garment_errors_skirt['Top'])
+    # per_garment_errors['Skirt'] = per_garment_errors_skirt['Skirt']
+    # per_garment_errors['Dress'] = per_garment_errors_skirt['Dress']
+    # for key in per_garment_errors.keys():
+    #     avg = np.mean(per_garment_errors[key])
+    #     global_errors.append(avg)
+    #     print(key + ': ' + str(avg), 'samples: ' + str(len(per_garment_errors[key])))
+
+    # print('Global avg: ' + str(np.mean(global_errors)))
+    # print(len(global_errors))
     

losses.py

@@ -44,7 +44,7 @@ def _nearest_neighbour(V, B):
 def _tf_nn_parallel(V, B):
 	return tf.map_fn(fn=lambda elem: tf.py_function(func=_nearest_neighbour, inp=elem, Tout=tf.int32), elems=(V,B), fn_output_signature=tf.int32, parallel_iterations=V.shape[0])
 
-# @tf.function
+@tf.function
 def collision_loss(V, B, mask, thr=.004):
     B_vn = vertex_normals(B, tf.tile(F_coll[None], [B.shape[0], 1, 1]))
    
@@ -96,6 +96,7 @@ edges_skirt = np.stack(np.nonzero(laplacian_loss.todense())).transpose()
 def get_edge_mask(masks):
     return tf.reduce_min(tf.gather(masks, edges, axis=1), axis=-1)
 
+@tf.function
 def edge_loss(x, y, mask):
     e_mask = get_edge_mask(mask)
     x_e = tf.gather(x, edges[:,0], axis=1) - tf.gather(x, edges[:,1], axis=1)
@@ -237,13 +238,14 @@ def kl_loss(mean, logvar):
     kl_loss *= -0.5
     return kl_loss
 
-
+@tf.function
 def normal_loss(pred, gt, mask, is_skirt=False, is_smpl_orig=False):
     f_norm = None
     if not is_skirt and not is_smpl_orig:
         f_norm = F_norm
     elif is_skirt:
-        f_norm = F_norm_skirt
+        # f_norm = F_norm_skirt
+        f_norm = tf.tile(F_coll_skirt[None,:,:], [pred.shape[0],1,1])
     elif is_smpl_orig:
         f_norm = F_norm_orig
     else:

models/cvae_curv_model.py

@@ -50,7 +50,7 @@ class CVAE(tf.keras.Model):
     # @tf.function
     def sample_single(self, uv_template, uv_body_posed, uv_mask, eps=None, nr_of_samples=4):
         if eps is None:
-            eps = tf.random.normal(shape=(nr_of_samples, self.latent_dim))
+            eps = tf.random.normal(shape=(nr_of_samples, 8, 4, self.latent_dim))
 
         uv_template = tf.tile(tf.transpose(uv_template, [1,2,0])[tf.newaxis,:,:,:], [nr_of_samples,1,1,1])
         uv_body_posed = tf.tile(tf.transpose(uv_body_posed, [1,2,0])[tf.newaxis,:,:,:], [nr_of_samples,1,1,1])
@@ -79,16 +79,17 @@ class CVAE(tf.keras.Model):
 
         return z_cond
 
+
     def sample(self, uv_template, uv_body_posed, uv_mask, noise=None):
         if noise is None:
-            eps = tf.random.normal(shape=(uv_template.shape[0], self.latent_dim))
+            eps = tf.random.normal(shape=(uv_template.shape[0], 8, 4, self.latent_dim))
         else:
             eps = noise
 
         z_cond = self.encode_conds(uv_template, uv_body_posed, training=False)
         z = tf.concat([eps, z_cond], axis=-1)
 
-        x = self.decoder(z, training=False)
+        x = self.decoder([z, uv_mask], training=False)
 
         # x = x * uv_mask[:,:,:,tf.newaxis]
 
@@ -148,3 +149,15 @@ class CVAE(tf.keras.Model):
         # x = tf.math.softmax(x)
 
         return x, mean, logvar
+
+    def call_sample(self, inputs):
+        uv_template, uv_body_posed, uv_curv, uv_mask = inputs
+
+        z = tf.random.normal(shape=(uv_template.shape[0], 8, 4, self.latent_dim))
+
+        z_cond = self.encode_conds(uv_template, uv_body_posed, training=False)
+
+        z = tf.concat([z, z_cond], axis=-1)
+        x = self.decoder([z, uv_mask], training=False)
+
+        return x

models/cvae_model.py

@@ -203,7 +203,7 @@ class CVAENew(tf.keras.Model):
     # @tf.function
     def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
         if noise is None:
-            eps = tf.random.normal(shape=(uv_template.shape[0], self.latent_dim))
+            eps = tf.random.normal(shape=(uv_template.shape[0], 8, 4, self.latent_dim))
         else:
             eps = noise
 

models/pyramid_level.py

@@ -101,6 +101,7 @@ class PyramidLevelNew(tf.keras.Model):
     def __init__(self, config):
         super(PyramidLevelNew, self).__init__()
         self.size = config['resolution']
+        self.latent_dim=config['latent_dim']
 
         self.encoder = VariationalEncoderNew(config['encoder_depths'], config['encoder_dims'], kernel_size=config['kernel_size'], latent_dim=config['latent_dim'])
         self.decoder = DecoderNew(config['decoder_depths'], config['decoder_dims'], config['kernel_size'])
@@ -126,13 +127,12 @@ class PyramidLevelNew(tf.keras.Model):
 
     def sample(self, z_cond, uv_mask, noise=None):
         if noise is None:
-            eps = tf.random.normal(shape=(uv_mask.shape[0], self.latent_dim))
+            eps = tf.random.normal(shape=(uv_mask.shape[0], 8, 4, self.latent_dim))
         else:
             eps = noise
 
         z = tf.concat([eps, z_cond], axis=-1)
-
+        x = self.decoder(z, training=False)
-        x = self.decoder(z)
         
         if self.avg_garment is not None:
             x = x + self.avg_garment[tf.newaxis,:,:,:]
@@ -155,15 +155,18 @@ class PyramidLevelNew(tf.keras.Model):
         return out
 
 
-    def call(self, inputs, z_cond, training=None):
+    def call(self, inputs, z_cond, prev_latent=None, training=None):
         uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs
 
         x = tf.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], axis=-1)
         mean, logvar = self.encoder(x, training=training)
         z = self.reparameterize(mean, logvar, training)
-        z = self.reshape(z)
+        z_latent = self.reshape(z)
     
-        z = tf.concat([z, z_cond], axis=-1)
+        if prev_latent is not None:
+            z_latent = tf.concat([z_latent, prev_latent], axis=-1)
+            
+        z = tf.concat([z_latent, z_cond], axis=-1)
         x = self.decoder(z, training=training)
 
         if self.avg_garment is not None:
@@ -177,4 +180,4 @@ class PyramidLevelNew(tf.keras.Model):
         
         # x = x * uv_mask_high[:,:,:,tf.newaxis]
 
-        return x, mean, logvar
+        return x, mean, logvar, z_latent

models/pyramid_model_optimized.py

@@ -12,244 +12,6 @@ from models.pyramid_level import PyramidLevel, PyramidLevelNew
 from models.upscaler import UpscalerBasic, UpscalerBasicConv, UpscalerBasicNew
 
 
-class Pyramid(tf.keras.Model):
-    
-    def __init__(self, config):
-        super(Pyramid, self).__init__()
-
-        self.static_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-        if config['pyramid']['static_model'] != '':
-            load_model(self.static_enc, config['pyramid']['static_model'] + '_enc')
-
-        self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['latent_dim'], config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['bottleneck_size'], config['cond_ae_body']['kernel_size'])
-        if config['pyramid']['body_model'] != '':
-            load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
-
-        self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-        if config['pyramid']['curvature_model'] != '':
-            load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
-
-        if config['pyramid']['freeze_encoders']:
-            self.static_enc.trainable = False
-            self.body_enc.trainable = False
-            self.curv_enc.trainable = False
-
-        self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
-                                                 tf.keras.layers.Dense(256, activation='relu'),
-                                                 tf.keras.layers.Dense(128, activation='relu'),
-                                                 tf.keras.layers.Dense(config['pyramid']['latent_dim'], activation='tanh'),])
-
-        self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae': config['cond_ae']} }) for i in range(len(config['pyramid']['levels']))]
-
-        # if config['is_cape']:
-        #     if len(config['pyramid']['resolutions']) == 2:
-        #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        #     if len(config['pyramid']['resolutions']) == 3:
-        #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        #         self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        #     if len(config['pyramid']['resolutions']) == 4:
-        #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        #         self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        #         self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # else:
-        if len(config['pyramid']['resolutions']) == 2:
-            self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        if len(config['pyramid']['resolutions']) == 3:
-            self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-            self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        if len(config['pyramid']['resolutions']) == 4:
-            self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-            self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-            self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        if len(config['pyramid']['resolutions']) == 5:
-            self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)])
-            self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-            self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-            self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-
-        self.add_noise = config['pyramid']['add_noise']
-        self.noise_amount = config['pyramid']['noise_amount']
-        self.use_offsets = config['use_offsets']
- 
-        self.upscale_enhancer = None
-        if config['pyramid']['final_upscale_enhancer'] != '':
-            k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-            self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
-            load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-            self.upscale_enhancer.trainable = False
-
-    def enhance(self, low, mask, training):
-        x = self.upscale_enhancer([low, mask], training=training)
-        return x
-
-    def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
-        z_static = self.static_enc(uv_template, training)
-        z_body = self.body_enc(uv_body_posed, training)
-        z_curv = self.curv_enc(uv_curv, training)
-
-        z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
-        z_cond = self.cond_encoder(z_cond, training=training)
-
-        return z_cond
-
-    def call(self, inputs, training):
-        levels_input, conds = inputs
-        uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
-
-        z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training)
-
-        if self.add_noise == True and training == True:
-            z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
-
-        out_levels = []
-        pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
-        if self.use_offsets:
-            pred = pred + levels_input[0][2] # uv_body_posed_32
-        if 1 != len(self.levels):
-            pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training)  # levels_input[i][-2]=uv_mask_res
-            pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
-            out_levels.append([pred, mean, logvar])
-            pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
-        else:
-            pred = self.enhance(pred, levels_input[0][-2], training=training)
-            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
-            pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
-            out_levels.append([pred, mean, logvar])
-
-        for i in range(1, len(self.levels)):
-            pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
-            pred = pred + pred_level
-            if i != len(self.levels) - 1:
-                pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
-                out_levels.append([pred, mean, logvar])
-                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
-                pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
-            else:
-                if self.upscale_enhancer is not None:
-                    pred = self.enhance(pred, levels_input[-1][-2], training=training)
-                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
-                pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
-                out_levels.append([pred, mean, logvar])
-
-        return out_levels
-
-        # # 32
-        # pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training)
-        # pred_0 = self.enhance(pred_0, levels_input[0][-2], training=training)
-        # pred_0 = tf.image.resize(pred_0, (512, 256), tf.image.ResizeMethod.LANCZOS5)
-        # pred_0 = pred_0 * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
-        # return [ [pred_0, mean_0, logvar_0] ]
-
-        # # 32 64
-        # pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training)
-        # pred_0 = self.levels[0].enhance(pred_0, levels_input[0][-2], training=training)  # levels_input[i][-2]=uv_mask_res
-        # pred_0 = tf.image.resize(pred_0, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
-        # pred = pred_0 * levels_input[1][-2][:,:,:,tf.newaxis]
-
-        # pred_1, mean_1, logvar_1 = self.levels[1](levels_input[1], z_cond, training=training)
-        # pred_1 = pred + pred_1
-        # pred_1 = self.enhance(pred_1, levels_input[-1][-2], training=training)
-        # pred_1 = tf.image.resize(pred_1, (512, 256), tf.image.ResizeMethod.LANCZOS5)
-        # pred_1 = pred_1 * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
-
-        # return [ [pred_0, mean_0, logvar_0], [pred_1, mean_1, logvar_1] ]
-
-
-# class Pyramid(tf.keras.Model):
-    
-#     def __init__(self, config):
-#         super(Pyramid, self).__init__()
-
-#         self.static_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-#         if config['pyramid']['static_model'] != '':
-#             load_model(self.static_enc, config['pyramid']['static_model'] + '_enc')
-
-#         self.body_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-#         if config['pyramid']['body_model'] != '':
-#             load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
-
-#         self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-#         if config['pyramid']['curvature_model'] != '':
-#             load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
-
-#         if config['pyramid']['freeze_encoders']:
-#             self.static_enc.trainable = False
-#             self.body_enc.trainable = False
-#             self.curv_enc.trainable = False
-
-#         self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
-#                                                  tf.keras.layers.Dense(256, activation='relu'),
-#                                                  tf.keras.layers.Dense(128, activation='relu'),
-#                                                  tf.keras.layers.Dense(config['pyramid']['latent_dim']),])
-
-#         self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae': config['cond_ae']} }) for i in range(len(config['pyramid']['levels']))]
-
- 
-#         self.upscale_enhancer = None
-#         if config['pyramid']['final_upscale_enhancer'] != '':
-#             self.upscale_enhancer = UpscalerBasicNew(low_res=config['pyramid']['resolutions'][-1])
-#             load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-#             self.upscale_enhancer.trainable = False
-
-#     def enhance(self, low, mask, training):
-#         x = self.upscale_enhancer([low, mask], training=training)
-#         return x
-
-#     def encode_conds(self, uv_template, uv_body_posed, uv_curv):
-#         z_static = self.static_enc(uv_template)
-#         z_body = self.body_enc(uv_body_posed)
-#         z_curv = self.curv_enc(uv_curv)
-
-#         z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
-#         z_cond = self.cond_encoder(z_cond)
-
-#         return z_cond
-
-#     def call(self, inputs, training):
-#         levels_input, conds = inputs
-#         uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
-#         z_cond = self.encode_conds(uv_static, uv_body, uv_curv)
-
-#         out_levels = []
-#         pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training)
-#         pred_0 = self.levels[0].enhance(pred_0, levels_input[0][-2], training=training)  # levels_input[i][-2]=uv_mask_res
-#         # pred_0 = self.enhance(pred_0, levels_input[0][-2], training=training)
-            
-#         ##################    
-#         # if more than 1 level
-#         # x = tf.image.resize(pred_0, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
-#         # x = x * levels_input[1][-2][:,:,:,tf.newaxis]
-
-#         # if only 1 level
-#         pred_0 = tf.image.resize(pred_0, (512, 256), tf.image.ResizeMethod.LANCZOS5)
-#         ##################
-
-
-#         # pred_1, mean_1, logvar_1 = self.levels[1](levels_input[1], z_cond, training=training)
-#         # pred_1 = pred_0 + pred_1
-#         # pred_1 = self.levels[1].enhance(pred, levels_input[1][-2], training=training)
-
-#         # for i in range(1, len(self.levels)):
-#         #     pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
-#         #     pred = pred + pred_level
-#         #     if i != len(self.levels) - 1:
-#         #         pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
-#         #         out_levels.append([pred, mean, logvar])
-#         #         pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
-#         #         pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
-#         #     else:
-#         #         if self.upscale_enhancer is not None:
-#         #             pred = self.enhance(pred, levels_input[-1][-2], training=training)
-#         #             pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
-#         #         out_levels.append([pred, mean, logvar])
-#         #         pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
-
-#         out_levels = [
-#             [pred_0, mean_0, logvar_0]
-#         ]
-
-#         return out_levels
-
 
 class PyramidNew(tf.keras.Model):
     
@@ -278,21 +40,6 @@ class PyramidNew(tf.keras.Model):
         self.levels = [PyramidLevelNew({ **config['pyramid']['levels'][i] }) for i in range(len(config['pyramid']['levels']))]
 
 
-        # if len(config['pyramid']['resolutions']) == 2:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 3:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 4:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 5:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-
         self.add_noise = config['pyramid']['add_noise']
         self.noise_amount = config['pyramid']['noise_amount']
         self.use_offsets = config['use_offsets']
@@ -320,6 +67,87 @@ class PyramidNew(tf.keras.Model):
 
         return z_cond
 
+    def sample(self, inputs):
+        levels_input, conds = inputs
+        uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
+        z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training=False)
+    
+        pred = [None, None, None, None, None]
+        for i in range(len(self.levels)):
+            pred[i] = self.levels[i].sample(z_cond, levels_input[i][-2])
+        
+        pred_1 = pred[0]
+        pred_2 = pred[1]
+        pred_3 = pred[2]
+        pred_4 = pred[3]
+        pred_5 = pred[4]
+
+        pred_1 = self.levels[0].enhance(pred_1, levels_input[0][-2], training=False)
+        pred_1 = tf.image.resize(pred_1, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_1 = pred_1 * levels_input[1][-2][:,:,:,tf.newaxis]
+        
+        pred_2 = pred_1 + pred_2
+        pred_2 = self.levels[1].enhance(pred_2, levels_input[1][-2], training=False)
+        pred_2 = tf.image.resize(pred_2, (self.levels[2].size, self.levels[2].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_2 = pred_2 * levels_input[2][-2][:,:,:,tf.newaxis]
+
+        pred_3 = pred_2 + pred_3
+        pred_3 = self.levels[2].enhance(pred_3, levels_input[2][-2], training=False)
+        pred_3 = tf.image.resize(pred_3, (self.levels[3].size, self.levels[3].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_3 = pred_3 * levels_input[3][-2][:,:,:,tf.newaxis]
+
+        pred_4 = pred_3 + pred_4
+        pred_4 = self.levels[3].enhance(pred_4, levels_input[3][-2], training=False)
+        pred_4 = tf.image.resize(pred_4, (self.levels[4].size, self.levels[4].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_4 = pred_4 * levels_input[4][-2][:,:,:,tf.newaxis]
+
+        pred_5 = pred_4 + pred_5
+        pred_5 = pred_5 * levels_input[4][-2][:,:,:,tf.newaxis]
+
+        return pred_5
+
+
+    def sample_seq(self, inputs):
+        levels_input, conds = inputs
+        uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
+        z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training=False)
+    
+        # level 1
+        pred_1 = self.levels[0].sample(z_cond, levels_input[0][-2])
+        pred_1 = self.levels[0].enhance(pred_1, levels_input[0][-2], training=False)
+        pred_1 = tf.image.resize(pred_1, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_1 = pred_1 * levels_input[1][-2][:,:,:,tf.newaxis]
+
+        # level 2
+        pred_2 = self.levels[1].sample(z_cond, levels_input[1][-2])
+        pred_2 = pred_1 + pred_2
+        pred_2 = self.levels[1].enhance(pred_2, levels_input[1][-2], training=False)
+        pred_2 = tf.image.resize(pred_2, (self.levels[2].size, self.levels[2].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_2 = pred_2 * levels_input[2][-2][:,:,:,tf.newaxis]
+
+        # level 3
+        pred_3 = self.levels[2].sample(z_cond, levels_input[2][-2])
+        pred_3 = pred_2 + pred_3
+        pred_3 = self.levels[2].enhance(pred_3, levels_input[2][-2], training=False)
+        pred_3 = tf.image.resize(pred_3, (self.levels[3].size, self.levels[3].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_3 = pred_3 * levels_input[3][-2][:,:,:,tf.newaxis]
+
+        # level 4
+        pred_4 = self.levels[3].sample(z_cond, levels_input[3][-2])
+        pred_4 = pred_3 + pred_4
+        pred_4 = self.levels[3].enhance(pred_4, levels_input[3][-2], training=False)
+        pred_4 = tf.image.resize(pred_4, (self.levels[4].size, self.levels[4].size//2), tf.image.ResizeMethod.BILINEAR)
+        pred_4 = pred_4 * levels_input[4][-2][:,:,:,tf.newaxis]
+
+        # level 5
+        pred_5 = self.levels[4].sample(z_cond, levels_input[4][-2])
+        pred_5 = pred_5 * levels_input[4][-2][:,:,:,tf.newaxis]
+
+        pred_5 = pred_4 + pred_5
+
+        return pred_5
+    
+
     def call(self, inputs, training):
         levels_input, conds = inputs
         uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
@@ -330,13 +158,13 @@ class PyramidNew(tf.keras.Model):
             z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
 
         out_levels = []
-        pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
+        pred, mean, logvar, z_latent = self.levels[0](levels_input[0], z_cond, training=training)
         if self.use_offsets:
             pred = pred + levels_input[0][2] # uv_body_posed_32
         if 1 != len(self.levels):
             pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training)  # levels_input[i][-2]=uv_mask_res
-            pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
             out_levels.append([pred, mean, logvar])
+            pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
             pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
         else:
             # pred = self.enhance(pred, levels_input[0][-2], training=training)
@@ -348,7 +176,7 @@ class PyramidNew(tf.keras.Model):
         for i in range(1, len(self.levels)):
             input = levels_input[i]
             input[0] = input[0] - pred
-            pred_level, mean, logvar = self.levels[i](input, z_cond, training=training)
+            pred_level, mean, logvar, z_latent = self.levels[i](input, z_cond, z_latent, training=training)
             pred = pred + pred_level
             if i != len(self.levels) - 1:
                 pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
@@ -358,8 +186,9 @@ class PyramidNew(tf.keras.Model):
             else:
                 # if self.upscale_enhancer is not None:
                     # pred = self.enhance(pred, levels_input[-1][-2], training=training)
-                pred = self.levels[-1].enhance(pred, levels_input[-1][-2], training=training)
+                if len(self.levels) != 5:
-                pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
+                    pred = self.levels[-1].enhance(pred, levels_input[-1][-2], training=training)
+                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
                 pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
                 out_levels.append([pred, mean, logvar])
 

plot_ablation.py

@@ -1,5 +1,5 @@
 import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "6"
+os.environ["CUDA_VISIBLE_DEVICES"] = "1"
 import sys
 import time
 import cv2
@@ -128,7 +128,11 @@ def get_experiment_plots(folder, frames, experiments, skirt_mods, bodies, faces,
         frame_out = []
         id = frame.split('_')[0]
         for exp in experiments:
-            garment = np.load(os.path.join(folder, exp[0] + skirt_mods[id] + '-' + exp[1], frame + '.npy'))
+            path = os.path.join(folder, exp[0] + skirt_mods[id] + '-' + exp[1], frame + '.npy')
+            if not os.path.exists(path):
+                path = os.path.join('/home/workspace/local-data_128/results/iccv', exp[0] + skirt_mods[id] + '-' + exp[1], frame + '.npy')
+                assert os.path.exists(path), path
+            garment = np.load(path)
             if exp == 'abl_orient':
                 garment = deorient(garment, frame, skirt_mods[id] == '_skirt')
             garment = postprocess(garment, bodies[frame], id, skirt_mods[id] == '_skirt')
@@ -190,11 +194,11 @@ if __name__ == '__main__':
 
     faces = get_faces()
 
-    frames = ['00079_135']
+    frames = ['00079_135', '00505_23', '00688_25', '01693_128', '00408_34']
     # frames = [ '00075_4', '00475_273', '00761_295', '00793_3', '00993_220', '01134_112', '01278_108', '00718_38', '00951_34', '00962_60','01065_38','01191_83','01240_168']
-    # rand_frames = [frame.split('.')[0] for frame in os.listdir('/home/workspace/data/dataset/test_ready/pose_shape')]
+    rand_frames = [frame.split('.')[0] for frame in os.listdir('/home/workspace/data/dataset/test_ready/pose_shape')]
-    # random.shuffle(rand_frames)
+    random.shuffle(rand_frames)
-    # rand_frames = rand_frames[:25]
+    rand_frames = rand_frames[:25]
     # frames.extend(rand_frames)
     # rand_frames = [frame.split('.')[0] for frame in os.listdir('/home/workspace/data/dataset/test_skirt_ready_2/pose_shape')]
     # random.shuffle(rand_frames)
@@ -207,34 +211,38 @@ if __name__ == '__main__':
     cameras = {frame: camera_1 for frame in frames}
 
     # abl_all replace abl_norm maybe
-    experiments = [['iccv_pyr_32', '335000'], ['iccv_pyr_32_skin', '330000'], ['iccv_pyr_32_curv', '155000'], ['iccv_pyr_32_reg', '150000']] # , 'pyra_32_res'
+    # experiments = [['iccv_pyr_32_64_128_256_512', '120000'], ['iccv_pyr_32_64_128_256_512_curv', '80000'], ['iccv_pyr_32_64_128_256_512_skin', '115000'], ['iccv_pyr_32_64_128_256_512_reg', '75000']] # , 'pyra_32_res'
+    # experiments = [['iccv_pyr_32_64_128_256_512', '120000'], ['iccv_pyr_32_64_128_256_curv', '80000'], ['iccv_pyr_32_64_128_256_skin', '145000'], ['iccv_pyr_32_64_128_256_reg', '35000']] # , 'pyra_32_res'
+    # experiments = [['iccv_pyr_32_64_128_256_512', '120000'], ['iccv_pyr_32_64_128_curv', '20000'], ['iccv_pyr_32_64_128_skin_2', '20000'], ['iccv_pyr_32_64_128_reg_2', '80000']] # , 'pyra_32_res'
+    experiments = [['abl_all_3', '130000']] # , 'pyra_32_res'
     skirt_mods = { frame.split('_')[0]: ('_skirt' if os.path.exists('/home/workspace/data/dataset/test_skirt_ready_2/pose_shape/' + frame + '.npy') else '') for frame in frames }
 
     bodies = get_bodies(frames, skirt_mods)
-    # gts = get_gt_image(frames, bodies, faces, cameras, skirt_mods)
-    gts = get_gt_meshes(frames, bodies, faces, cameras, skirt_mods)
 
     results_folder_base = '/home/workspace/data/results/iccv/'
 
-    output_folder = os.path.join(results_folder_base, 'ablation_plots')
+    output_folder = os.path.join('examples/ablation/img_3')
+    output_folder_stl = os.path.join('examples/ablation/stl_3')
     os.makedirs(output_folder, exist_ok=True)
+    os.makedirs(output_folder_stl, exist_ok=True)
 
+    # gts_img = get_gt_image(frames, bodies, faces, cameras, skirt_mods)
     # images = get_experiment_plots(results_folder_base, frames, experiments, skirt_mods, bodies, faces, cameras)
+    # rows = [np.concatenate((gt, exp), axis=1) for gt, exp in zip(gts_img, images)]
+    # for frame, row in zip(frames, rows):
+    #     custom_imshow(row).write_image(os.path.join(output_folder, frame + '_ablation.png'))
+
+    gts = get_gt_meshes(frames, bodies, faces, cameras, skirt_mods)
     meshes = get_experiment_meshes(results_folder_base, frames, experiments, skirt_mods, bodies, faces, cameras)
     for mesh, frame in zip(meshes, frames):
         for exp, (garment, body, faces) in zip(experiments, mesh):
-            save_stl(f'examples/{frame}_{exp[0]}_garment.stl', garment, faces)
+            save_stl(f'{output_folder_stl}/{frame}_{exp[0]}_garment.stl', garment, faces)
-            save_stl(f'examples/{frame}_{exp[0]}_body.stl', body, F)
+            save_stl(f'{output_folder_stl}/{frame}_{exp[0]}_body.stl', body, F)
-
     for mesh, frame in zip(gts, frames):
         garment, body, faces = mesh
-        save_stl(f'examples/{frame}_gt_garment.stl', garment, faces)
+        save_stl(f'{output_folder_stl}/{frame}_gt_garment.stl', garment, faces)
-        save_stl(f'examples/{frame}_gt_body.stl', body, F)
+        save_stl(f'{output_folder_stl}/{frame}_gt_body.stl', body, F)
 
-    # rows = [np.concatenate((gt, exp), axis=1) for gt, exp in zip(gts, images)]
-
-    # for frame, row in zip(frames, rows):
-    #     custom_imshow(row).write_image(os.path.join(output_folder, frame + '_ablation.png'))
 
     # final = np.concatenate(rows, axis=0)
 

plot_ablation_pyramid.py

@@ -1,5 +1,5 @@
 import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "5"
+os.environ["CUDA_VISIBLE_DEVICES"] = "4"
 
 import tensorflow as tf
 
@@ -30,15 +30,15 @@ from plotly.subplots import make_subplots
 from scipy.spatial.transform import Rotation
 
 from dataset import DatasetFactory, StaticDataset
-from custom_utils.custom_utils import batch_to_dict, UV2Mesh, _maskFaces, load_model, group_inputs_for_levels
+from custom_utils.custom_utils import batch_to_dict, UV2Mesh, _maskFaces, load_model, group_inputs_for_levels, save_stl
 from custom_utils.smpl import SMPL
 from convert_to_uv_api import convert_to_uv_api
 from models.upscaler import UpscalerBasicConv as Upscaler
 from postprocessing import fix_collision
-from models.pyramid_model_optimized import Pyramid
+from models.pyramid_model_optimized import PyramidNew as Pyramid
 
-from configs.config_abl_2_pyr_32_64_128_256_512 import config as config_regular
+from configs.iccv.config_abl_pyr_32_64_128_256_512 import config as config_regular
-from configs.config_abl_2_pyr_32_64_128_256_512_skirt import config as config_skirt
+from configs.iccv.config_abl_pyr_32_64_128_256_512_skirt import config as config_skirt
 
 
 def color_labels(img):
@@ -182,7 +182,7 @@ def convert_to_mesh(uvs, is_skirt, mask):
     out = []
     for i in range(len(uvs)):
         if uvs[i].shape[1] != 512:
-            uvs[i] = tf.image.resize(uvs[i], (512, 256), tf.image.ResizeMethod.LANCZOS5) 
+            uvs[i] = tf.image.resize(uvs[i], (512, 256), tf.image.ResizeMethod.BILINEAR) 
         if is_skirt:
             mesh = uv2mesh_skirt(uvs[i])
         else:
@@ -239,9 +239,9 @@ def get_closest_n_points(verts, idx, n):
 
 def get_experiment_plots(frames, skirt_mods, bodies, faces, masks, cameras):
     model: Pyramid = Pyramid(config_regular)
-    load_model(model, 'checkpoints/' + config_regular['name'])
+    load_model(model, 'checkpoints/iccv/' + config_regular['name'])
     model_skirt: Pyramid = Pyramid(config_skirt)
-    load_model(model_skirt, 'checkpoints/' + config_skirt['name'])
+    load_model(model_skirt, 'checkpoints/iccv/' + config_skirt['name'])
     result = []
     for frame in frames:
         id = frame.split('_')[0]
@@ -267,6 +267,10 @@ def get_experiment_plots(frames, skirt_mods, bodies, faces, masks, cameras):
             img = cv2.imread('/tmp/exp_temp.png')
             frame_out.append(img[:, 50:-50, :])
 
+        for i, mesh in enumerate(meshes):
+            save_stl(os.path.join(output_folder, f'{frame}_{i+1}.stl'), mesh, faces[id].astype(np.int32))
+        save_stl(os.path.join(output_folder, f'{frame}_final.stl'), final_mesh_fixed, faces[id].astype(np.int32))
+
         # fig = plot_fixed(final_mesh, faces[id], cameras[frame], bodies[frame])
         # fig.write_image('/tmp/exp_temp.png')
         # img = cv2.imread('/tmp/exp_temp.png')
@@ -297,6 +301,10 @@ def get_gt_image(frames, bodies, faces, cameras, skirt_mods):
         fig.write_image('/tmp/exp_temp.png')
         img_unposed = cv2.imread('/tmp/exp_temp.png')
 
+        save_stl(os.path.join(output_folder, f'{frame}_gt.stl'), gt_unposed[mask,:], faces[id].astype(np.int32))
+        save_stl(os.path.join(output_folder, f'{frame}_gt_unposed.stl'), gt[mask,:], faces[id].astype(np.int32))
+        save_stl(os.path.join(output_folder, f'{frame}_body.stl'), bodies[frame], F)
+
         out.append(np.concatenate((img[:, 50:-50, :], img_unposed[:, 50:-50, :]), axis=1))
 
     return out
@@ -322,33 +330,36 @@ if __name__ == '__main__':
     # garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
     garment_type_table = np.load('custom_data/garment_type_table_train.npy', allow_pickle=True).item()
 
+    camera_1 =  dict(up=dict(x=0, y=0, z=1), center=dict(x=0, y=0, z=-0.05), eye=dict(x=0.3, y=1.0, z=0.05))
+    camera_2 =  dict(up=dict(x=0, y=0, z=1), center=dict(x=0, y=0, z=-0.05), eye=dict(x=-0.9, y=0.7, z=0.05))
 
-    frames = ['05656_221', '00300_69', '06955_117']
+    frames = ['01070_13']
+    cameras = {'01070_13': camera_1}
+    # frames = ['05656_221', '00300_69', '06955_117']
     # frames = ['02184_157', '02241_142', '06955_117', '06804_192']
     # frames = ['01763_259', '007292_282', '00539_296', '00075_4']
     # frames = [ '01763_259']
-    camera_1 =  dict(up=dict(x=0, y=0, z=1), center=dict(x=0, y=0, z=-0.05), eye=dict(x=0.3, y=1.0, z=0.05))
-    camera_2 =  dict(up=dict(x=0, y=0, z=1), center=dict(x=0, y=0, z=-0.05), eye=dict(x=-0.9, y=0.7, z=0.05))
     # cameras = {'01763_259': camera_1, '007292_282': camera_1, '00539_296': camera_1, '00075_4': camera_2}
-    cameras = {'05656_221': camera_1, '00300_69': camera_1, '06955_117': camera_1}
+    # cameras = {'05656_221': camera_1, '00300_69': camera_1, '06955_117': camera_1}
     # cameras = {'02184_157': camera_1, '02241_142': camera_1, '06955_117': camera_1, '06804_192': camera_1}
 
     # abl_all replace abl_norm maybe
-    experiment = 'abl_2_pyr_32_64_128_256_512'
+    experiment = 'abl_pyr_32_64_128_256_512'
     skirt_mods = { frame.split('_')[0]: ('_skirt' if (garment_type_table[frame.split('_')[0]] == 'Skirt' or garment_type_table[frame.split('_')[0]] == 'Dress') else '') for frame in frames }
 
     data_folder = '/home/workspace/local-data/train'
-    data_folder_skirt = '/home/workspace/local-data/train_skirt'
+    data_folder_skirt = '/home/workspace/local-data_128/train_skirt'
+
+    results_folder_base = 'examples/pyramid'
+
+    output_folder = os.path.join(results_folder_base)
+    os.makedirs(output_folder, exist_ok=True)
     
     bodies = get_bodies(frames, skirt_mods)
     masks = get_masks(frames)
     faces = { frame.split('_')[0]: _maskFaces(np.zeros((14475,3)), F_skirt if skirt_mods[frame.split('_')[0]] == '_skirt' else F, masks[frame.split('_')[0]])[1] for frame in frames }
     gts = get_gt_image(frames, bodies, faces, cameras, skirt_mods)
 
-    results_folder_base = '/home/workspace/data/results'
-
-    output_folder = os.path.join(results_folder_base, 'ablation_plots')
-    os.makedirs(output_folder, exist_ok=True)
 
     images = get_experiment_plots(frames, skirt_mods, bodies, faces, masks, cameras)
 

plot_examples.py

@@ -11,10 +11,11 @@ import tensorflow as tf
 import cmapy as cm
 import plotly.graph_objects as go
 import plotly.express as ex
+import scipy.io as sio
 from plotly.subplots import make_subplots
 
 from dataset import DatasetFactory, StaticDataset
-from custom_utils.custom_utils import batch_to_dict, UV2Mesh, _maskFaces, load_model
+from custom_utils.custom_utils import batch_to_dict, UV2Mesh, _maskFaces, load_model, save_stl
 from custom_utils.smpl import SMPL
 from convert_to_uv_api import convert_to_uv_api
 from models.upscaler import UpscalerBasicConv as Upscaler
@@ -121,6 +122,69 @@ def uv_mapping_example(mesh, faces, colors, mask):
     print()
 
 
+def faces2graph(F, v=None):
+    if v: v = set(v) # Only this verts
+    G = {}
+    for f in F:
+        for i in f:
+            if v and i not in v: continue
+            if not i in G:
+                G[i] = {}
+            for j in f:
+                if v and j not in v: continue
+                if i == j: continue
+                G[i][j] = 1
+    return G
+
+SMOOTH_IT = 100
+SMOOTH_EXHAUST_IT = 100
+def smooth(M, F, segm):
+    f_skirt = []
+    for f in F:
+        f_skirt.append(f[0])
+
+    G = faces2graph(f_skirt)
+    # Segmentation for skirt smoothing
+
+    # Laplacian smoothing
+    for _ in range(SMOOTH_EXHAUST_IT):
+        for v in segm['exhaustive'].reshape(-1):
+            M[v] = M[list(G[v].keys())].mean(0)
+    for _ in range(SMOOTH_IT):
+        # aux = M.copy()
+        # FRONT
+        for v in segm['front'].reshape(-1):
+            M[v] = M[list(G[v].keys())].mean(0)
+        for v in segm['frontBoundary'].reshape(-1):
+            M[v,:2] = M[list(G[v].keys()),:2].mean(0) # No z-smoothing
+        # BACK
+        for v in segm['back'].reshape(-1):
+            M[v] = M[list(G[v].keys())].mean(0)
+        for v in segm['backBoundary'].reshape(-1):
+            M[v,:2] = M[list(G[v].keys()),:2].mean(0) # No z-smoothing
+        # M = aux.copy()
+
+    return M
+
+
+def uv_mapping_example_skirt(mesh, faces, colors, mask):
+    segm = sio.loadmat('custom_utils/vg_skirt_smoothing')
+    F = sio.loadmat("custom_utils/faces_skirt.mat")['F'][0]
+    faces = np.load('custom_utils/smpl_faces_skirt.npy')
+    mesh = smooth(mesh, F, segm)
+    fig = plot_fixed(mesh, faces, colors)
+    fig.write_image('examples/' + type + '_' + id_str + '_' + frame_nr + '_body.png')
+
+    # stop inbetween
+    uv = convert_to_uv_api(mesh, mask, is_skirt=True)
+    plot = custom_imshow((uv+1)/2)
+    # plot = custom_imshow(result)
+    # plot.write_image('examples/' + type + '_' + id_str + '_' + frame_nr + '_uv_body_pre.png')
+    plot.write_image('examples/' + type + '_' + id_str + '_' + frame_nr + '_uv_body_inpainted.png')
+
+    print()
+
+
 def curvature_example(mesh_curvature, uv_curvature, posed, faces, mask):
     colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, mesh_curvature.max()+1)]) / 255.0
     color_mesh = np.zeros((mesh_curvature.shape[0], 3), np.float32)
@@ -172,7 +236,7 @@ def plot_upscaling(uv_low, uv_high, uv_mask_low, uv_mask_high, faces, color, mas
     print()
 
 
-    if __name__ == '__main__':
+if __name__ == '__main__':
 
     uv2mesh = UV2Mesh()
     smpl = SMPL()
@@ -209,8 +273,9 @@ def plot_upscaling(uv_low, uv_high, uv_mask_low, uv_mask_high, faces, color, mas
                                   do_repeat=False,
                                   resolutions=[512, 32],
                                 #   frames_file='/home/workspace/data/dataset/test_ready/frames_pose_cluster_20_sample_10.txt', 
-                                #   frames_file='/home/workspace/data/dataset/test_ready/frames_00438_146.txt', 
+                                  frames_file='/home/workspace/data/dataset/test_ready/frames_00438_146.txt', 
-                                  frames_file='/home/workspace/data/dataset/test_ready/frames_00228_137.txt', 
+                                #   frames_file='/home/workspace/data/dataset/test_ready/frames_00228_137.txt', 
+                                #   frames_file='/home/workspace/data/dataset/test_ready/frames_02572_1.txt', 
                                   )
     static_dataset = StaticDataset(folder='/home/workspace/data/dataset/test_ready',
                                    resolutions=[512, 32],
@@ -264,30 +329,33 @@ def plot_upscaling(uv_low, uv_high, uv_mask_low, uv_mask_high, faces, color, mas
 
         x = np.concatenate((body, posed), axis=0)
 
+        # calcualte the sum of face ares of posed mesh that has faces_garment faces
+        # face_areas = np.linalg.norm(np.cross((x[faces[:,0],:] - x[faces[:,1],:]), (x[faces[:,0],:] - x[faces[:,2],:])), axis=1)
+
         # m = tm.Trimesh(x, faces, process=False, validate=False, vertex_colors=colors)
         
-        # x = posed
+        x = posed
-        # x_1 = unposed.copy()
+        x_1 = unposed.copy()
-        # x_1[:, 0] = x_1[:, 0] + 0.75
+        x_1[:, 0] = x_1[:, 0] + 0.75
-        # x_2 = unposed_shaped.copy()
+        x_2 = unposed_shaped.copy()
-        # x_2[:, 0] = x_2[:, 0] + 1.75
+        x_2[:, 0] = x_2[:, 0] + 1.75
-        # garments = np.concatenate((x, x_1, x_2), axis=0)
+        garments = np.concatenate((x, x_1, x_2), axis=0)
-        # all_faces = np.concatenate((faces_garment, faces_garment + x.shape[0], faces_garment + 2*x.shape[0]), axis=0).astype(np.int32)
+        all_faces = np.concatenate((faces_garment, faces_garment + x.shape[0], faces_garment + 2*x.shape[0]), axis=0).astype(np.int32)
-        # mesh = garments
+        mesh = garments
-        # faces = all_faces
+        faces = all_faces
-        # fig = go.Figure()
+        fig = go.Figure()
-        # fig.add_trace(go.Mesh3d(
+        fig.add_trace(go.Mesh3d(
-        #         x=mesh[:,0],
+                x=mesh[:,0],
-        #         y=mesh[:,2],
+                y=mesh[:,2],
-        #         z=mesh[:,1],
+                z=mesh[:,1],
-        #         i = faces[:,0],
+                i = faces[:,0],
-        #         j = faces[:,1],
+                j = faces[:,1],
-        #         k = faces[:,2],
+                k = faces[:,2],
-        #         text="",
+                text="",
-        #         lighting={ 'ambient':0.8, 'diffuse':0.5, 'roughness':0.5 },
+                lighting={ 'ambient':0.8, 'diffuse':0.5, 'roughness':0.5 },
                 
-        #     ),)
+            ),)
-        # fig.show()
+        fig.show()
 
 
         # fig = plot_fixed(x, faces, colors)
@@ -302,7 +370,8 @@ def plot_upscaling(uv_low, uv_high, uv_mask_low, uv_mask_high, faces, color, mas
         # fig.write_image('examples/' + type + '_' + id_str + '_' + frame_nr + '_unposed_shaped.svg')
 
         # uv_mapping_example(body, F, colors[:14475, :], np.ones((14475), bool))
+        # uv_mapping_example_skirt(body, F, colors[:14475, :], np.ones((14475), bool))
         # curvature_example(batch['mesh_curvature'][0].numpy(), uv_curvature, posed, faces_garment, mask)
-        plot_upscaling(batch['uv_unposed_32'].numpy()[0], batch['uv_unposed'].numpy()[0], batch['uv_mask_32'].numpy()[0], batch['uv_mask'].numpy()[0], faces_garment, colors_garment, mask)
+        # plot_upscaling(batch['uv_unposed_32'].numpy()[0], batch['uv_unposed'].numpy()[0], batch['uv_mask_32'].numpy()[0], batch['uv_mask'].numpy()[0], faces_garment, colors_garment, mask)
 
         print()

preprocessing.py

@@ -216,7 +216,7 @@ def generate_faces():
         np.save(os.path.join(output_folder, id + '.npy'), faces.astype(np.int32))
 
 
-def generate_frames_file(folder, ratio=0.1):
+def generate_frames_file(folder, ratio=0.1, garment='', file_name='frames.txt'):
     all_frames = os.listdir(os.path.join(folder, 'pose_shape'))
     ids = [frame.split('_')[0] for frame in all_frames]
     all_frames = [frame.split('.')[0] for frame in all_frames]
@@ -232,17 +232,15 @@ def generate_frames_file(folder, ratio=0.1):
     selected = []
 
     for id in tqdm.tqdm(sub_ids):
-        if garment_type_table[id] != 'Dress':
+        if garment_type_table[id] != garment:
             continue
-        if len(selected) > 30000:
-            break
 
         # frames = glob.glob(os.path.join(folder, 'pose_shape', id + '_*'))
         frames = [frame for frame in all_frames if frame.startswith(id + '_')]
         frames = [frame.split('/')[-1].split('.')[0] for frame in frames]
         selected.extend(frames)
 
-    with open(os.path.join(folder, 'frames_dress_30k.txt'), 'w') as f:
+    with open(os.path.join(folder, file_name), 'w') as f:
         for i, frame in enumerate(selected):
             f.write(frame + '\n')
 
@@ -293,7 +291,7 @@ def generate_frames_file_filtered_cape():
 
 if __name__ == '__main__':
 
-    src_folder = '/home/workspace/local-data/train_skirt' #cloth3d_skirt
+    src_folder = '/home/workspace/local-data/train' #cloth3d_skirt
     # src_folder = r'D:\Work\Dataset\validation_2'
     dest_folder = '/home/workspace/data/dataset/validation' 
 
@@ -306,5 +304,17 @@ if __name__ == '__main__':
     # verify_poses(src_folder)
     # create_garment_type_table()
     # generate_faces()
-    generate_frames_file(src_folder, ratio=1)
+    # generate_frames_file(src_folder, ratio=1)
     # generate_frames_file_filtered_cape()
+
+
+    # # folders = ['/home/workspace/local-data/train', '/home/workspace/local-data/test_ready', '/home/workspace/local-data/valid']
+    # folders = ['/home/workspace/local-data/valid_skirt']
+    # # garments = ['Jumpsuit', 'Trousers', 'Tshirt', 'Top']
+    # # filename = ['frames_jumpsuit.txt', 'frames_trousers.txt', 'frames_tshirt.txt', 'frames_top.txt']
+    # garments = ['Skirt', 'Dress', 'Tshirt', 'Top']
+    # filename = ['frames_skirt.txt', 'frames_dress.txt', 'frames_tshirt.txt', 'frames_top.txt']
+
+    # for folder in folders:
+    #     for garment, file in zip(garments, filename):
+    #         generate_frames_file(folder, garment=garment, file_name=file, ratio=1)

sample_pro_2.py

@@ -1,5 +1,5 @@
 import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "6"
+os.environ["CUDA_VISIBLE_DEVICES"] = "4"
 import tensorflow as tf
 
 gpus = tf.config.experimental.list_physical_devices('GPU')
@@ -31,7 +31,7 @@ from PIL import Image
 from plotly.subplots import make_subplots
 
 from custom_utils.smpl import SMPL
-from custom_utils.custom_utils import load_model
+from custom_utils.custom_utils import load_model, save_stl
 from plotly.subplots import make_subplots
 from scipy.spatial.transform import Rotation
 
@@ -44,10 +44,13 @@ from postprocessing import fix_collision
 from models.pyramid_model_optimized import Pyramid
 
 # from configs.config_abl_overfit_dress_var_3 import config as config_main
-from configs.config_abl_overfit_jumpsuit_2 import config as config_main
+# from configs.config_abl_overfit_jumpsuit_2 import config as config_main
-from configs.config_cvae_curv import config as config_curv
+# from configs.config_cvae_curv import config as config_curv
+# from configs.iccv.config_abl_all_skirt_var import config as config_main
+from configs.iccv.config_abl_skin_var import config as config_main
+from configs.iccv.config_cvae_curv import config as config_curv
 # from models.cvae_model_overfit_jumpsuit import CVAE
-from models.cvae_model import CVAE
+from models.cvae_model import CVAENew as CVAE
 from models.cvae_curv_model import CVAE as CVAECurv
 from convert_to_uv_api import convert_to_uv_api
 from tensorflow_graphics.geometry.representation.mesh.normals import vertex_normals
@@ -287,23 +290,24 @@ def postprocess(mesh, body, faces, mask, do_smoothing=True):
     return mesh
 
 
-def sampling_example(frame, camera, nr=10):
+def sampling_example(frame, camera, nr=15):
 
     batch = get_temp_batch(frame, config_main)
     mask = batch['mesh_mask'][0].numpy().astype(bool)
     _, faces = _maskFaces(np.zeros((14475, 3)), F, mask)
 
-    noise = tf.random.normal(shape=(nr, 128))
+    noise = tf.random.normal(shape=(nr, 8, 4, 128))
     out = model.sample(tf.tile(batch['uv_static'], [nr,1,1,1]), tf.tile(batch['uv_body_posed'], [nr,1,1,1]), tf.tile(batch['uv_curvature'], [nr,1,1,1]), tf.tile(batch['uv_mask'], [nr,1,1]), noise)
     # out,_,_ = model([tf.tile(batch['uv_unposed'], [nr,1,1,1]), tf.tile(batch['uv_static'], [nr,1,1,1]), tf.tile(batch['uv_body_posed'], [nr,1,1,1]), tf.tile(batch['uv_curvature'], [nr,1,1,1]), tf.tile(batch['uv_mask'], [nr,1,1])], training=False)
     
-
+    if config_main['use_skinning']:
-    posed_mesh = [get_posed_mesh(uv, batch['pose_shape'], batch['mesh_body_posed'], mask) for uv in tf.unstack(out)]
+        posed_mesh = [get_posed_mesh(uv, batch['pose_shape'], batch['mesh_body_posed'], mask) for uv in tf.unstack(out)]
-    # posed_mesh = [uv2mesh(uv[tf.newaxis,:,:,:]) for uv in tf.unstack(out)]
+    else:
+        posed_mesh = [uv2mesh(uv[tf.newaxis,:,:,:]) for uv in tf.unstack(out)]
     gt_mesh = batch['mesh_posed'][0].numpy()[mask, :]
 
     body = batch['mesh_body_posed'][0].numpy()
-    posed_mesh_fixed = [postprocess(mesh, body, faces, mask, do_smoothing=False) for mesh in posed_mesh]
+    posed_mesh_fixed = [postprocess(mesh, body, faces, mask, do_smoothing=True) for mesh in posed_mesh]
     # posed_mesh_fixed = [mesh[0].numpy()[mask, :] for mesh in posed_mesh]
 
     # error = [np.sqrt(((gt_mesh-m) ** 2).sum(-1)).mean() for m in posed_mesh_fixed]
@@ -321,11 +325,23 @@ def sampling_example(frame, camera, nr=10):
 
 
     # custom_imshow(np.concatenate(row_sampling, axis=1)).show()
+    os.makedirs(os.path.join(out_folder, frame), exist_ok=True)
 
-    plot_fixed(np.zeros_like(gt_mesh), body, faces, camera).write_image(os.path.join(out_folder, frame + '_body.png'))
+    plot_fixed(np.zeros_like(gt_mesh), body, faces, camera).write_image(os.path.join(out_folder, frame, frame + '_body.png'))
-    plot_fixed(gt_mesh, body, faces, camera).write_image(os.path.join(out_folder, frame + '_gt.png'))
+    plot_fixed(gt_mesh, body, faces, camera).write_image(os.path.join(out_folder, frame, frame + '_gt.png'))
     for i in range(nr):
-        plot_fixed(posed_mesh_fixed[i], body, faces, camera).write_image(os.path.join(out_folder, frame + '_' + str(i) + '.png'))
+        plot_fixed(posed_mesh_fixed[i], body, faces, camera).write_image(os.path.join(out_folder, frame, frame + '_' + str(i) + '.png'))
+    
+    # save_stl(os.path.join(out_folder, frame, frame + '_body.stl'), body, F_body)
+    # save_stl(os.path.join(out_folder, frame, frame + '_gt.stl'), gt_mesh, faces.astype(np.int32))
+    # for i in range(nr):
+    #     save_stl(os.path.join(out_folder, frame, frame + '_' + str(i) + '.stl'), posed_mesh_fixed[i], faces.astype(np.int32))
+    np.save(os.path.join(out_folder, frame, frame + '_gt.npy'), gt_mesh)
+    np.save(os.path.join(out_folder, frame, frame + '_body.npy'), body)
+    np.save(os.path.join(out_folder, frame, frame + '_faces.npy'), faces.astype(np.int32))
+    for i in range(nr):
+        np.save(os.path.join(out_folder, frame, frame + '_' + str(i) + '.npy'), posed_mesh_fixed[i])
+
 
     # custom_imshow(np.concatenate(row_sampling, axis=1)).write_image(os.path.join(out_folder, frame + '_sampling.png'))
     print()
@@ -407,19 +423,25 @@ if __name__ == '__main__':
     args = vars(parser.parse_args())
     
     smpl = SMPL()
-    F = np.load("custom_utils/smpl_faces.npy")
+
+    if config_main['is_skirt']:
+        F = np.load("custom_utils/smpl_faces_skirt.npy")
+        folder = os.path.join('/home/workspace/local-data_128/train_skirt')
+    else:
+        F = np.load("custom_utils/smpl_faces.npy")
+        folder = os.path.join('/home/workspace/local-data/train')
     # F = np.load("custom_utils/smpl_faces_skirt.npy")
     F_body = np.load("custom_utils/smpl_faces.npy")
     # folder = os.path.join('/home/workspace/data/dataset', ('test_skirt_ready_2' if is_skirt else 'test_ready'))
     # folder = os.path.join('/home/workspace/local-data/train_skirt')
-    folder = os.path.join('/home/workspace/local-data/train')
     
 
     model = CVAE(config_main)
-    curv_model = CVAECurv(config_curv)
+    # curv_model = CVAECurv(config_curv)
+
+    load_model(model, 'checkpoints/iccv/' + config_main['name'])
+    # load_model(curv_model, 'checkpoints/iccv/' + config_curv['name'])
     
-    load_model(model, 'checkpoints/' + config_main['name'])
-    load_model(curv_model, 'checkpoints/' + config_curv['name'])
 
     camera_1 =  dict(up=dict(x=0, y=0, z=1), center=dict(x=0, y=0, z=-0.05), eye=dict(x=0.3, y=1.0, z=0.05))
     # faces_folder = '/home/workspace/data/results/support/faces'
@@ -432,12 +454,12 @@ if __name__ == '__main__':
     curv_frames = ['01763_259' , '007292_282']
     static_frames = ['01763_259' , '007292_282']
 
-    with open('/home/workspace/local-data/train_skirt/frames_dress_30k.txt') as f:
+    # with open('/home/workspace/local-data/train_skirt/frames_dress_30k.txt') as f:
-        frames = f.readlines()
+    #     frames = f.readlines()
 
-    random.shuffle(frames)
+    # random.shuffle(frames)
-    frames = [frame.strip() for frame in frames]
+    # frames = [frame.strip() for frame in frames]
-    frames = frames[:150]
+    # frames = frames[:150]
 
     # input_batch = get_temp_batch(frame, config_main)
     # _, faces = _maskFaces(np.zeros((14475, 3)), F, input_batch['mesh_mask'][0].numpy().astype(bool))
@@ -453,8 +475,10 @@ if __name__ == '__main__':
     # camera_01082_109 = dict(up=dict(x=0.0, y=0, z=1), center=dict(x=-0.15, y=0, z=-0.05), eye=dict(x=0.9, y=0.8, z=-0.1))
     # frame = '04925_272'
 
-    frames = ['01070_13']
+    # frames = ['01070_13', '02276_232', '02978_242', '04008_295', '04173_193']
-    out_folder = '/home/workspace/local-data/results/sampling_plots_jumpsuits'
+    frames = ['02276_232', '02978_242', '04173_193']
+    
+    out_folder = 'examples/sampling_analysis'
     os.makedirs(out_folder, exist_ok=True)
     for frame in tqdm.tqdm(frames):
         sampling_example(frame, camera_1)

upscale_test.py

@@ -1,5 +1,5 @@
 import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "2"
+os.environ["CUDA_VISIBLE_DEVICES"] = "3"
 import tensorflow as tf
 
 gpus = tf.config.experimental.list_physical_devices('GPU')
@@ -36,10 +36,10 @@ from models.upscaler import UpscalerBasicConv as Upscaler
 # !!!!!!!!!! CHANGE SKIRT OR NOT
 
 
-low_res = 128
+low_res = 256
 is_skirt = False
 is_cape = True
-is_male = False
+is_male = True
 skirt_modifier = '_skirt' if is_skirt else ''
 cape_modifier = '_cape' if is_cape else ''
 gender_modifier = '' if not is_cape else ('_m' if is_male else '_f')