fix

aaa_helpers.txt

@@ -3,12 +3,42 @@ nohup python calculate_error.py --name error_al_all_150k > nohup/error/post_al_a
 nohup python auto_encoder_static.py --name="lhunor_static_iccv_1" > nohup/iccv/encoders/static_iccv_1.out 2>&1 &
 nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_skirt" > nohup/iccv/encoders/static_iccv_1_skirt.out 2>&1 &
 nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_cape_f" > nohup/iccv/encoders/static_iccv_1_cape_f.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_cape_m" > nohup/iccv/encoders/static_iccv_1_cape_m.out 2>&1 &
 nohup python auto_encoder_body.py --name="lhunor_body_iccv_1" > nohup/iccv/encoders/body_iccv_1.out 2>&1 &
 nohup python auto_encoder_body.py --name="lhunor_body_iccv_1_skirt" > nohup/iccv/encoders/body_iccv_1_skirt.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1 " > nohup/iccv/encoders/curv_iccv_1.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_body_iccv_1_cape_m" > nohup/iccv/encoders/body_iccv_1_cape_m.out 2>&1 &
+nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1" > nohup/iccv/encoders/curv_iccv_1.out 2>&1 &
 nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_skirt" > nohup/iccv/encoders/curv_iccv_1_skirt.out 2>&1 &
 nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_cape_f" > nohup/iccv/encoders/curv_iccv_1_cape_f.out 2>&1 &
-nohup python cvae.py --name="lhunor_cvae_iccv_gnn_5" > nohup/iccv/cvae_iccv_gnn_5.out 2>&1 &
+nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_cape_m" > nohup/iccv/encoders/curv_iccv_1_cape_m.out 2>&1 &
+nohup python cvae.py --name="lhunor_cvae_iccv_gnn_1" > nohup/iccv/cvae_iccv_gnn_1.out 2>&1 &
+
+nohup python cvae.py --name="lhunor_abl_all" > nohup/iccv/ablation/abl_all.out 2>&1 &
+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_3" > nohup/iccv/ablation/abl_all_gnn_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 &
+nohup python upscale_test.py --name="iccv_128_2" > nohup/iccv/upscale/iccv_128_2.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2" > nohup/iccv/upscale/iccv_256_2.out 2>&1 &
+
+nohup python upscale_test.py --name="iccv_32_2_skirt" > nohup/iccv/upscale/iccv_32_2_skirt.out 2>&1 &
+nohup python upscale_test.py --name="iccv_64_2_skirt" > nohup/iccv/upscale/iccv_64_2_skirt.out 2>&1 &
+nohup python upscale_test.py --name="iccv_128_2_skirt" > nohup/iccv/upscale/iccv_128_2_skirt.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2_skirt" > nohup/iccv/upscale/iccv_256_2_skirt.out 2>&1 &
+
+nohup python upscale_test.py --name="iccv_32_2_cape_f" > nohup/iccv/upscale/iccv_32_2_cape_f_real.out 2>&1 &
+nohup python upscale_test.py --name="iccv_64_2_cape_f" > nohup/iccv/upscale/iccv_64_2_cape_f.out 2>&1 &
+nohup python upscale_test.py --name="iccv_128_2_cape_f" > nohup/iccv/upscale/iccv_128_2_cape_f.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2_cape_f" > nohup/iccv/upscale/iccv_256_2_cape_f.out 2>&1 &
+
+nohup python upscale_test.py --name="iccv_32_2_cape_m" > nohup/iccv/upscale/iccv_32_2_cape_m.out 2>&1 &
+nohup python upscale_test.py --name="iccv_64_2_cape_m" > nohup/iccv/upscale/iccv_64_2_cape_m.out 2>&1 &
+nohup python upscale_test.py --name="iccv_128_2_cape_m" > nohup/iccv/upscale/iccv_128_2_cape_m.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2_cape_m" > nohup/iccv/upscale/iccv_256_2_cape_m.out 2>&1 &
+
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32" > nohup/iccv/pyr/iccv_pyr_32.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skirt" > nohup/iccv/pyr/iccv_pyr_32_skirt.out 2>&1 &
 
 skirts!!!!
 pyramid next week

auto_encoder_body.py

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

auto_encoder_curv.py

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

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_ae_static_cape_f import config
+from configs.iccv.config_ae_static_cape_m import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -247,9 +247,9 @@ if __name__ == '__main__':
         load_model(model.decoder, config['pretrained_model'] + '_dec')
 
     ckpt_enc = tf.train.Checkpoint(model=model.encoder)
-    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
-    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
 
     # test()
     train()

configs/iccv/config_abl_all.py

@@ -7,7 +7,7 @@ config = dict()
 # 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['use_skinning'] =              False # and deshaping
 config['remove_global_orientation'] = True
 config['use_curvature'] =             True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
@@ -19,12 +19,12 @@ config['only_curvatures'] =           False
 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'] = '0'
-config['name'] = 'iccv_gnn_5'
+config['gpu'] = '2'
+config['name'] = 'abl_all_gnn_3'
 config['notes'] = ''
-config['tags'] = ['iccv', 'gnn']
+config['tags'] = ['iccv', 'abl_all_gnn']
 
-config['avg_garment_path'] = 'custom_data/train_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
+config['avg_garment_path'] = '' #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'] == '')
 
@@ -40,13 +40,13 @@ config['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
 config['test_dir'] = '/home/workspace/data/dataset/test_ready'
 
-# config['frames_file'] = 'frames_dress_30k.txt'
-# config['frames_file_valid'] = 'frames_dress_30k.txt'
-# config['frames_file_test'] = 'frames_dress_30k.txt'
+config['static_model'] = 'checkpoints/iccv/static_iccv_1'
+config['body_model'] = 'checkpoints/iccv/body_iccv_1'
+config['curvature_model'] = 'checkpoints/iccv/curv_iccv_1'
 
-config['static_model'] = 'checkpoints/post/static_post_2'
-config['body_model'] = 'checkpoints/post/body_post_2'
-config['curvature_model'] = 'checkpoints/post/curv_post_1'
+# config['static_model'] = 'checkpoints/post/static_post_2'
+# config['body_model'] = 'checkpoints/post/body_post_2'
+# config['curvature_model'] = 'checkpoints/post/curv_post_1'
 
 
 config['smpl_res'] = 14475
@@ -54,7 +54,7 @@ if config['is_cape']:
   config['smpl_res'] = 3638
 
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccv/abl_skin'
 
 ###############    
 config['lr'] = 0.0001#                 0.0001
@@ -83,15 +83,17 @@ else:
 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']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.001
+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, 64]
+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']
 
@@ -99,9 +101,9 @@ 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['cond_ae_static']['encoder_depths'] = [3, 3, 3, 9, 3]
-config['cond_ae_static']['encoder_dims'] = [16, 32, 64, 64, config['cond_ae_static']['bottleneck_size']]
+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'
@@ -109,7 +111,7 @@ 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['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']
@@ -119,7 +121,7 @@ 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['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']

configs/iccv/config_abl_pyr_32.py

@@ -0,0 +1,188 @@
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'iccv_pyr_32'
+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['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/data/dataset/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_'#'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.py

@@ -0,0 +1,188 @@
+config = dict()
+
+config['gpu'] = '5'
+config['name'] = 'iccv_pyr_32_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['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/data/dataset/local-cache/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
+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_'#'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'#'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_ae_body_cape_m.py

@@ -0,0 +1,52 @@
+config = dict()
+
+
+config['batch_size'] = 4
+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['use_filled'] = False
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = True
+config['remove_global_orientation'] = True
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+config['bottleneck_scale'] = 2
+
+config['cond_ae'] = dict()
+config['cond_ae']['is_label'] = False
+config['cond_ae']['upscale_output'] = False
+config['cond_ae']['latent_dim'] = config['latent_dim']
+config['cond_ae']['kernel_size'] = 7
+config['cond_ae']['bottleneck_size'] = 16 * config['bottleneck_scale']
+config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
+config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
+config['cond_ae']['activation'] = 'tanh'
+
+
+config['gpu'] = '4'
+config['lr'] = 0.0001
+config['name'] = 'body_iccv_1_cape_m'
+config['notes'] = '' 
+config['tags'] = ['iccv', 'body', 'cape_m'] 
+
+config['cond_ae']['upscale_output'] = False
+config['pretrained_model'] = ''
+
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (3, 512, 256,),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                        }
+config['signature_static'] = { 
+                         'mesh_mask': (config['smpl_res'],),
+                        }

configs/iccv/config_ae_curv_cape_m.py

@@ -0,0 +1,51 @@
+config = dict()
+
+
+config['batch_size'] = 4
+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['use_filled'] = False
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = True
+config['remove_global_orientation'] = True
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+config['bottleneck_scale'] = 2
+
+config['cond_ae'] = dict()
+config['cond_ae']['is_label'] = True
+config['cond_ae']['upscale_output'] = False
+config['cond_ae']['latent_dim'] = config['latent_dim']
+config['cond_ae']['kernel_size'] = 7
+config['cond_ae']['bottleneck_size'] = 40 * config['bottleneck_scale']
+config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
+config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
+config['cond_ae']['activation'] = 'tanh'
+
+
+config['gpu'] = '5'
+config['lr'] = 0.001
+config['name'] = 'curv_iccv_1_cape_m'
+config['notes'] = '' 
+config['tags'] = ['iccv', 'curv', 'cape_m'] 
+
+config['cond_ae']['upscale_output'] = False
+config['pretrained_model'] = ''
+
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'uv_curvature': (512, 256, 7),
+                          'mesh_curvature':  (config['smpl_res'])
+                        }
+config['signature_static'] = { 'mesh_mask': (config['smpl_res'],),
+                         'uv_mask': (512, 256,),
+                        }

configs/iccv/config_ae_static_cape_m.py

@@ -0,0 +1,51 @@
+config = dict()
+
+
+config['batch_size'] = 4
+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['use_filled'] = False
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = True
+config['is_cape'] = True
+config['remove_global_orientation'] = True
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+config['bottleneck_scale'] = 2
+
+config['cond_ae'] = dict()
+config['cond_ae']['is_label'] = False
+config['cond_ae']['upscale_output'] = False
+config['cond_ae']['latent_dim'] = config['latent_dim']
+config['cond_ae']['kernel_size'] = 7
+config['cond_ae']['bottleneck_size'] = 8 * config['bottleneck_scale']
+config['cond_ae']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae']['encoder_dims'] = [8, 16, 32, 64, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
+config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
+config['cond_ae']['activation'] = 'tanh'
+
+
+config['gpu'] = '3'
+config['lr'] = 0.0005
+config['name'] = 'static_iccv_1_cape_m'
+config['notes'] = ' ' 
+config['tags'] = ['iccv', 'static', 'cape_m'] 
+
+config['cond_ae']['upscale_output'] = False
+config['pretrained_model'] = 'checkpoints/iccv/static_iccv_1_cape_m_old'
+
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (), }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                         'mesh_static': (config['smpl_res'], 3,),
+                         'mesh_mask': (config['smpl_res'],),
+                         'uv_mask': (512, 256,),
+                        }

cvae.py

@@ -43,6 +43,7 @@ from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
 from models.cvae_model import CVAENew as CVAE
 from models.gnn import Smoother
+from custom_utils.custom_utils import Accumulator
 
 
 def init_wandb():
@@ -86,7 +87,7 @@ def train_step(batch):
         else:
             mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
+        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
         mesh_pred = uv2mesh(pred)
         mesh_pred = smoother(mesh_pred, training=True)
@@ -106,34 +107,29 @@ def train_step(batch):
         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_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'], is_smpl_orig=config['is_cape'])
-        # conc_loss = concept_loss(pred, batch['uv_unposed'])
-        kl = kl_loss(mean, logvar)
 
-        reconstr_loss = l2_loss
+        reconstr_loss = l2_mesh_loss
         if config['use_extra_losses']:
             if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True:
-                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + (e_loss) * config['reg_loss_coeff']
             else:
-                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
         if config['use_norm_loss'] and step > 2000:
             reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
-        loss = reconstr_loss + g_balancing_coeff * kl
+        loss = reconstr_loss
 
-        mean = tf.reduce_mean(mean)
-        logvar = tf.reduce_mean(logvar)
 
     # 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)))
     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'])
-    gradients = tape.gradient(loss, model.trainable_variables + smoother.trainable_variables)
-    optimizer.apply_gradients(zip(gradients, model.trainable_variables + smoother.trainable_variables))
+    gradients = tape.gradient(loss, smoother.trainable_variables)
+    optimizer.apply_gradients(zip(gradients, smoother.trainable_variables))
     return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
              'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio,
-             'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
-             'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
+             'train/mean': mean, 'train/logvar': logvar, 'train/var': np.e ** logvar,
+             'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
              # 'train/ms_ssim': ms_ssim, 
             }
 
@@ -165,22 +161,16 @@ def valid_step(batch):
     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_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'], is_smpl_orig=config['is_cape'])
-    # conc_loss = concept_loss(pred, batch['uv_unposed'])
-    kl = kl_loss(mean, logvar)
 
-    reconstr_loss = l2_loss
+    reconstr_loss = l2_mesh_loss
     if config['use_extra_losses']:
-        reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+        reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
     if config['use_norm_loss']:
         reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
-    loss = reconstr_loss + g_balancing_coeff * kl
-
-    mean = tf.reduce_mean(mean)
-    logvar = tf.reduce_mean(logvar)
+    loss = reconstr_loss
 
     # 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)))
     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'])
@@ -188,7 +178,7 @@ def valid_step(batch):
 
     return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric, 
              'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/collision_ratio': c_ratio,
-             'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
+             'valid/mean': mean, 'valid/logvar': logvar,  'valid/var': np.e ** logvar,
               'valid/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim, 
               }
 
@@ -290,7 +280,6 @@ def plot_everything(batch: dict, type: str):
 
     gt_posed = [batch['mesh_posed'].numpy()[i, mask[i], :] for i in range(mask.shape[0])]
 
-
     body = batch['mesh_body_posed'].numpy()
     mesh_posed_fixed = fix_collision(mesh_posed, body, mask).numpy()
 
@@ -524,6 +513,7 @@ if __name__ == '__main__':
                                         is_cape=config['is_cape'])
 
     model = CVAE(config)
+    model.trainable = False
     smoother = Smoother()
 
     optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
@@ -534,8 +524,9 @@ if __name__ == '__main__':
     # test()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
-
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/iccv/' + config['name'], max_to_keep=20)
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
 
     if config['pretrained_model'] != '':
         load_model(model, config['pretrained_model'])
@@ -548,30 +539,37 @@ if __name__ == '__main__':
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
 
         train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
 
-        data_valid = valid_iterator.get_next()
-        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
-        valid_loss = valid_step(data_valid)
-
-        to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
-            train_figs = plot_everything(batch, 'train')
-            valid_figs = plot_everything(data_valid, 'valid')
-            to_log = { **to_log, **train_figs, **valid_figs }
-
-        if step % 5000 == 0:
-            manager.save(checkpoint_number=step)
-        if step == 0:
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+        if step % 50 == 0:
+            data_valid = valid_iterator.get_next()
+            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            valid_loss = valid_step(data_valid)
+            valid_accumulator.update(valid_loss)
 
         if train_loss['train/euclid_error'] < (config['balancing_activation_limit'] if 'balancing_activation_limit' in config.keys() else 0.017):
             if balancing_activated_step == 0:
                 balancing_activated_step = step
             g_balancing_coeff = g_balancing_coeff + 1 / 10000      
 
-        to_log = { **to_log, **{ 'train/balancing_coeff': g_balancing_coeff } }
         
-        wandb.log(to_log, step = step)
+        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+                train_figs = plot_everything(batch, 'train')
+                valid_figs = plot_everything(data_valid, 'valid')
+                to_log = { **to_log, **train_figs, **valid_figs }
+            if step == 0:
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+
+            to_log = { **to_log, **{ 'train/balancing_coeff': g_balancing_coeff } }
+                
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
+
+        if step % 5000 == 0:
+            manager.save(checkpoint_number=step)
 
         print(step)
 

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.post.config_abl_pyr_64_128_5 import config
+from configs.iccv.config_abl_pyr_32_skirt import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -43,10 +43,11 @@ from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
 from models.pyramid_model_optimized import PyramidNew as Pyramid
 from postprocessing import fix_collision
+from custom_utils.custom_utils import Accumulator
 
 
 def init_wandb():
-    run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags'])
+    run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
 
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('cvae_pyramid.py')
@@ -61,11 +62,14 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.post.')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
 
+
 def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, collision_faces, collision_color):
     fig = make_subplots(rows=1, cols=1+len(mesh_pred_unposed_levels)+1+1, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(1+len(mesh_pred_unposed_levels)+1+1)] ])
     
@@ -791,6 +795,8 @@ if __name__ == '__main__':
 
     ckpt = tf.train.Checkpoint(model=model)
     manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -846,31 +852,33 @@ if __name__ == '__main__':
 
 
         train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
 
-        data_valid = valid_iterator.get_next()
-        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
-        valid_loss = valid_step(data_valid)
+        if step % 50 == 0:
+            data_valid = valid_iterator.get_next()
+            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            valid_loss = valid_step(data_valid)
+            valid_accumulator.update(valid_loss)
 
-        to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
-            train_figs = plot_everything(batch, 'train')
-            valid_figs = plot_everything(data_valid, 'valid')
-            to_log = { **to_log, **train_figs, **valid_figs }
-
-        if step % 5000 == 0:
-            manager.save(checkpoint_number=step)
-        if step == 0:
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
-
-        if train_loss['train/euclid_error'] < 0.004:
+        if train_loss['train/euclid_error'] < 0.015:
             if balancing_activated_step == 0:
                 balancing_activated_step = step
             balancing_coeff = balancing_coeff + 1 / 20000
 
+        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+                train_figs = plot_everything(batch, 'train')
+                valid_figs = plot_everything(data_valid, 'valid')
+                to_log = { **to_log, **train_figs, **valid_figs }
+            if step == 0:
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-        to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
-        
-        wandb.log(to_log, step = step)
+            to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
+                
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         print(step)
 

models/base.py

@@ -111,18 +111,18 @@ class Decoder(tf.keras.Model):
 
 class VariationalEncoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7):
+    def __init__(self, depths, dims, kernel_size=7, latent_dim=64):
         super(VariationalEncoderNew, self).__init__()
 
         self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
 
         self.mean_branch = tf.keras.Sequential(
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+                [Block(dim=latent_dim, drop_path=0, kernel_size=kernel_size,
                        layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
             )
 
         self.var_branch = tf.keras.Sequential(
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+                [Block(dim=latent_dim, drop_path=0, kernel_size=kernel_size,
                        layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
             )
 

models/cvae_model.py

@@ -179,10 +179,10 @@ class CVAENew(tf.keras.Model):
             if config['use_curvature']:
                 self.curv_enc.trainable = False
 
-        self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
+        self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'], latent_dim=config['cvae']['latent_dim'])
         self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
+        self.reshape = tf.keras.layers.Reshape((8, 4, config['cvae']['latent_dim']))
 
         if config['avg_garment_path'] != '':
             self.avg_garment = np.load(config['avg_garment_path'])

models/gnn.py

@@ -16,10 +16,10 @@ class Smoother(tf.keras.Model):
     def __init__(self, ):
         super().__init__()
         self.a = sp_matrix_to_sp_tensor(sio.loadmat("custom_utils/ssmpl0.mat")['L'].tocoo())
-        self.conv1 = GCNConv(3, activation='tanh', use_bias=False)
+        self.conv1 = GCNConv(16, activation='tanh', use_bias=False)
         self.conv2 = GCNConv(3, activation='tanh', use_bias=False)
-        # self.conv3 = GCNConv(3, activation='tanh', use_bias=False)
-        # self.conv4 = GCNConv(64, activation='tanh', use_bias=False)
+        # self.conv3 = GCNConv(512, activation='tanh', use_bias=False)
+        # self.conv4 = GCNConv(512, activation='tanh', use_bias=False)
         # self.conv5 = GCNConv(64, activation='tanh', use_bias=False)
         self.conv6 = GCNConv(3, activation='tanh', use_bias=False)
 

models/pyramid_level.py

@@ -102,13 +102,12 @@ class PyramidLevelNew(tf.keras.Model):
         super(PyramidLevelNew, self).__init__()
         self.size = config['resolution']
 
-        self.encoder = VariationalEncoderNew(config['encoder_depths'], config['encoder_dims'], kernel_size=config['kernel_size'])
+        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'])
 
         self.upscale_enhancer = None
         if config['upscale_enhancer'] != '':
-            k_size = config['upscale_enhancer_kernel_size'] if 'upscale_enhancer_kernel_size' in config.keys() else ((3 if config['resolution'] <= 64 else 5))
-            self.upscale_enhancer = UpscalerBasicConv(config['resolution'], kernel_size=k_size)
+            self.upscale_enhancer = UpscalerBasicConv(config['resolution'], kernel_size=config['kernel_size'])
             load_model(self.upscale_enhancer, config['upscale_enhancer'])
             self.upscale_enhancer.trainable = not config['upscale_enhancer_freeze']
 
@@ -117,7 +116,7 @@ class PyramidLevelNew(tf.keras.Model):
         else:
             self.avg_garment = None
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
+        self.reshape = tf.keras.layers.Reshape((8, 4, config['latent_dim']))
 
 
     def enhance(self, low, mask, training=None):

models/pyramid_model_optimized.py

@@ -343,11 +343,7 @@ class PyramidNew(tf.keras.Model):
         for i in range(1, len(self.levels)):
             input = levels_input[i]
             input[0] = input[0] - pred
-            input_min, input_max = tf.reduce_min(input[0], axis=[1,2,3]), tf.reduce_max(input[0], axis=[1,2,3])
-            input[0] = (input[0] - input_min[:,None,None,None]) / (input_max - input_min)[:,None,None,None]
-            input[0] = input[0] * input[-2][:,:,:,None] # uv_mask_res
             pred_level, mean, logvar = self.levels[i](input, z_cond, training=training)
-            pred_level = ( (pred_level * (input_max - input_min)[:,None,None,None]) + input_min[:,None,None,None] ) * input[-2][:,:,:,None] # uv_mask_res
             pred = pred + pred_level
             if i != len(self.levels) - 1:
                 pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)

models/upscaler.py

@@ -131,13 +131,13 @@ class UpscalerBasicConv(tf.keras.Model):
         self.low_res = low_res
 
         self.seq = tf.keras.Sequential([
-                    tf.keras.layers.Conv2D(256, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_1'),
+                    tf.keras.layers.Conv2D(64, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_1'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_1'),
-                    tf.keras.layers.Conv2D(128, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_2'),
+                    tf.keras.layers.Conv2D(64, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_2'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_2'),
-                    tf.keras.layers.Conv2D(64, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_3'),
+                    tf.keras.layers.Conv2D(16, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_3'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_3'),
-                    tf.keras.layers.Conv2D(32, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_4'),
+                    tf.keras.layers.Conv2D(16, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_4'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_4'),
                     tf.keras.layers.Dense(3, activation='tanh', name='upscale_enhancer_dense_final'),
         ])

upscale_test.py

@@ -1,5 +1,5 @@
 import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "6"
+os.environ["CUDA_VISIBLE_DEVICES"] = "2"
 import tensorflow as tf
 
 gpus = tf.config.experimental.list_physical_devices('GPU')
@@ -35,7 +35,18 @@ from models.upscaler import UpscalerBasicConv as Upscaler
 # !!!!!!!!!! CHANGE SSIM BASED ON RES
 # !!!!!!!!!! CHANGE SKIRT OR NOT
 
-name='256_512_skirt'
+
+low_res = 256
+is_skirt = True
+is_cape = False
+is_male = False
+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')
+smpl_res = 3638 if is_cape else 14475
+
+
+name=f'iccv_{low_res}_2' + skirt_modifier + cape_modifier + gender_modifier
 def init_wandb():
     run = wandb.init(project='upscale', name=name,
             notes='\
@@ -59,15 +70,10 @@ smaller features  | \
     artifact.add_file('convnext/models/convnext_tf.py')
     run.log_artifact(artifact)
 
-is_skirt = True
-is_cape = False
-skirt_modifier = '_skirt' if is_skirt else ''
-smpl_res = 3638 if is_cape else 14475
 
 uv2mesh = UV2Mesh(res=256, is_skirt=is_skirt, is_smpl_orig=is_cape)
 
 
-
 def plot_3d(mesh_gt, mesh_pred_unposed, faces):
     mesh_pred_unposed[:,2] += 1
     fig = go.Figure(data=[
@@ -105,18 +111,22 @@ def plot_3d(mesh_gt, mesh_pred_unposed, faces):
     return fig
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     with tf.GradientTape() as tape:
         pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]], training=True)
-        pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.LANCZOS5)
+        pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.BILINEAR)
 
         mesh_pred = uv2mesh(pred)
         mesh_orig = batch['mesh_unposed']
 
         l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_unposed' + high_resolution_modifier] - pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis]) )), axis=-1))
-        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2, power_factors=(0.5, 0.2, 0.2, 0.1)))
-        # ms_ssim = tf.reduce_mean(tf.image.ssim(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2))
+        
+        if low_res == 32:
+            ms_ssim = tf.reduce_mean(tf.image.ssim(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2))
+        else:
+            ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2, power_factors=(0.5, 0.2, 0.2, 0.1)))
+            
         loss = 1e3 * (1 - ms_ssim)
 
     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'])
@@ -125,29 +135,31 @@ def train_step(batch):
     return { 'train/loss': loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim }
         
 
-
 @tf.function
 def valid_step(batch):
     pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]], training=False)
-    pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.LANCZOS5)
+    pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.BILINEAR)
 
     mesh_pred = uv2mesh(pred)
     mesh_orig = batch['mesh_unposed']
 
     l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_unposed' + high_resolution_modifier] - pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis]) )), axis=-1))
-    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2, power_factors=(0.5, 0.2, 0.2, 0.1)))
-    # ms_ssim = tf.reduce_mean(tf.image.ssim(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2))
+    
+    if low_res == 32:
+        ms_ssim = tf.reduce_mean(tf.image.ssim(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2))
+    else:
+        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, batch['uv_unposed' + high_resolution_modifier] * batch['uv_mask' + high_resolution_modifier][:,:,:,tf.newaxis] + 1, max_val=2, power_factors=(0.5, 0.2, 0.2, 0.1)))
+    
     loss = 1e3 * (1 - ms_ssim)
 
     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'])
     return { 'valid/loss': loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim }
    
 
-
 def plot_everything(batch: dict, type: str):
 
     pred = model([batch['uv_unposed' + low_resolution_modifier], batch['uv_mask' + low_resolution_modifier]], training=False)
-    pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.LANCZOS5)
+    pred = tf.image.resize(pred, size=(high_res, high_res//2), method=tf.image.ResizeMethod.BILINEAR)
     
     mesh_pred = uv2mesh(pred)
     mesh_orig = batch['mesh_unposed']
@@ -168,7 +180,6 @@ def plot_everything(batch: dict, type: str):
     return { **figs, **{ type + '/images': imgs} }
 
 
-
 def train():
     valid_iterator = iter(dataset_valid)
 
@@ -177,9 +188,10 @@ def train():
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, signature_dynamic))
         train_loss = train_step(batch)
 
-        data_valid = valid_iterator.get_next()
-        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, signature_dynamic))
-        valid_loss = valid_step(data_valid)
+        if step % 100 == 0:
+            data_valid = valid_iterator.get_next()
+            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, signature_dynamic))
+            valid_loss = valid_step(data_valid)
 
         to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
         if step % 10000 == 0 or (step < 2000 and step % 500 == 0):
@@ -193,7 +205,6 @@ def train():
         if step % 5000 == 0:
             manager.save(checkpoint_number=step)
 
-
         wandb.log(to_log, step = step)
 
         print(step)
@@ -204,8 +215,8 @@ def train():
         step += 1
 
 if __name__ == '__main__':
-    # init_wandb()
-    allow_memory_growth()
+    init_wandb()
+    # allow_memory_growth()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())
@@ -214,7 +225,6 @@ if __name__ == '__main__':
     # uv_mask_body = np.load('custom_utils/mask_256x512.npy')
     # uv_mask_body = cv2.dilate(uv_mask_body.astype(np.float32), cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2)
 
-    low_res = 32
     high_res = 512
     uv_mask_body = tf.ones((low_res, low_res//2))
     low_resolution_modifier = '_' + str(low_res)
@@ -234,24 +244,44 @@ if __name__ == '__main__':
                          'uv_mask' + low_resolution_modifier: (low_res, low_res//2,),
                         }
 
-    dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
-    static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
-    dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/valid_skirt', batch_size=8, signature=signature_dynamic,resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
-    static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/valid_skirt', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+    if not is_skirt:
+        dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+        static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+        dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/valid', batch_size=8, signature=signature_dynamic,resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+        static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/valid', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
 
-    # dataset_train = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/train/male', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
-    # static_dataset_train = StaticDataset(folder='/home/workspace/local-data/cape_processed/train/male', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
-    # dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/test/male', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
-    # static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/cape_processed/test/male', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+    if is_skirt:
+        dataset_train = factory.get_dataset(folder='/home/workspace/data/dataset/local-cache/train_skirt', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+        static_dataset_train = StaticDataset(folder='/home/workspace/data/dataset/local-cache/train_skirt', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+        dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/valid_skirt', batch_size=8, signature=signature_dynamic,resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+        static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/valid_skirt', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
 
+    if is_cape:
+        if is_male:
+            dataset_train = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/train/male', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+            static_dataset_train = StaticDataset(folder='/home/workspace/local-data/cape_processed/train/male', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+            dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/test/male', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+            static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/cape_processed/test/male', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+        else:
+            dataset_train = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/train/female', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+            static_dataset_train = StaticDataset(folder='/home/workspace/local-data/cape_processed/train/female', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+            dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/cape_processed/test/female', batch_size=8, signature=signature_dynamic, resolutions=[high_res, low_res], in_memory=False, is_cape=is_cape)
+            static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/cape_processed/test/female', signature=signature_static, resolutions=[high_res, low_res], in_memory=True, is_cape=is_cape)
+                    
+
+    if low_res == 32 or low_res == 64:
+        model = Upscaler(low_res=low_res, kernel_size=3)
+    elif low_res == 128 or low_res == 256:
+        model = Upscaler(low_res=low_res, kernel_size=5)
+    else:
+        model = Upscaler(low_res=low_res, kernel_size=7)
 
-    model = Upscaler(low_res=low_res, kernel_size=3)
 
     optimizer = tf.optimizers.Adam(learning_rate=0.0001)
     folder = 'models/ae_logs/'
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + name, max_to_keep=20)
-    load_model(model, 'checkpoints/32_512_4')
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/iccv/' + name, max_to_keep=20)
+    # load_model(model, f'checkpoints/iccv/iccv_{low_res}' + skirt_modifier)
 
     train()