save

aaa_helpers.txt

@@ -77,6 +77,13 @@ nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_reg" > nohup/iccv/pyr/ic
 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_skirt" > nohup/iccv/pyr/iccv_pyr_32_64_skirt.out 2>&1 &
@@ -151,6 +158,7 @@ nohup python evaluate_ae_pyramid.py --name evaluate_ae_iccv_pyr_32_64_25p > nohu
 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 &

calculate_error.py

@@ -1,37 +1,37 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_64_25p import config
+from configs.iccv.config_abl_pyr_32_64_128_skin_skirt 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 = 'collision' # 'euclidean' 'collision' edge normal
+
     folder = config['test_dir']
 
     checkpoint_name = config['name']
@@ -65,7 +69,7 @@ if __name__ == '__main__':
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
 
 
-    output_folder = '/home/workspace/local-data_128/results/iccv/' + checkpoint_name + '-'
+    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, f'There should be only one checkpoint that starts with this name, but found {len(folders)}'
@@ -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_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_skirt_var.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'] = '0'
+config['gpu'] = '3'
-config['name'] = 'abl_all_skirt_var'
+config['name'] = 'abl_all_skirt_var_dasda'
 config['notes'] = ''
 config['tags'] = ['iccv', 'abl_all', 'skirt']
 
@@ -35,9 +35,9 @@ config['is_skirt'] = True
 config['dataset_in_memory'] = False
 config['is_cape'] = False
 
-config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
+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_128/test_skirt_ready_2'
+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'

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_64_128_256_512.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '1'
+config['gpu'] = '4'
 config['name'] = 'iccv_pyr_32_64_128_256_512'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv']

configs/iccv/config_abl_pyr_32_64_128_256_512_curv.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '2'
+config['gpu'] = '4'
 config['name'] = 'iccv_pyr_32_64_128_256_512_curv'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv', 'curv']

configs/iccv/config_abl_pyr_32_64_128_256_512_reg.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '0'
+config['gpu'] = '4'
 config['name'] = 'iccv_pyr_32_64_128_256_512_reg'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv', 'reg']

configs/iccv/config_abl_pyr_32_64_128_256_512_skin.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '1'
+config['gpu'] = '4'
 config['name'] = 'iccv_pyr_32_64_128_256_512_skin'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv']

configs/iccv/config_abl_pyr_32_64_128_256_512_skirt.py

@@ -1,6 +1,6 @@
 config = dict()
 
-config['gpu'] = '5'
+config['gpu'] = '4'
 config['name'] = 'iccv_pyr_32_64_128_256_512_skirt'
 config['notes'] = ''
 config['tags'] = ['pyr', 'iccv']

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_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'

cvae.py

@@ -2,6 +2,7 @@ import os
 import sys
 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_pyramid.py

@@ -1,7 +1,8 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_64_128_256_512 import config
+from configs.iccv.config_abl_pyr_32_tshirt import config
 
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
 
@@ -417,6 +418,7 @@ 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 +428,8 @@ 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 +438,10 @@ 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 +450,30 @@ 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 +489,11 @@ 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, } }
 
@@ -728,14 +730,23 @@ 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])
+    # 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
 
 
 
 if __name__ == '__main__':
-    # init_wandb()
+    init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str, default='lhunor')
     args = vars(parser.parse_args())
@@ -760,8 +771,12 @@ 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 +787,12 @@ 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, 
@@ -848,50 +867,50 @@ if __name__ == '__main__':
 
         levels_input, conds = group_inputs_for_levels(batch, config)
 
-        start = time.perf_counter()
+        # 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
+        # t = time.perf_counter() - start
-        print(t)
+        # print(t)
-        times.append(t)
+        # times.append(t)
 
-        if step > 200:
+        # if step > 200:
-            break
+        #     break
 
 
-        # train_loss = train_step(batch)
+        train_loss = train_step(batch)
-        # train_accumulator.update(train_loss)
+        train_accumulator.update(train_loss)
 
-        # if step % 25 == 0:
+        if step % 25 == 0:
-        #     data_valid = valid_iterator.get_next()
+            data_valid = valid_iterator.get_next()
-        #     data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
+            data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
-        #     valid_loss = valid_step(data_valid)
+            valid_loss = valid_step(data_valid)
-        #     valid_accumulator.update(valid_loss)
+            valid_accumulator.update(valid_loss)
 
-        # if train_loss['train/euclid_error'] < 0.015:
+        if train_loss['train/euclid_error'] < 0.015:
-        #     if balancing_activated_step == 0:
+            if balancing_activated_step == 0:
-        #         balancing_activated_step = step
+                balancing_activated_step = step
-        #     balancing_coeff = balancing_coeff + 1 / 20000
+            balancing_coeff = balancing_coeff + 1 / 20000
 
-        # if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
+        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
-        #     to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-        #     if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-        #         train_figs = plot_everything(batch, 'train')
+                train_figs = plot_everything(batch, 'train')
-        #         valid_figs = plot_everything(data_valid, 'valid')
+                valid_figs = plot_everything(data_valid, 'valid')
-        #         to_log = { **to_log, **train_figs, **valid_figs }
+                to_log = { **to_log, **train_figs, **valid_figs }
-        #     if step == 0:
+            if step == 0:
-        #         to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-        #     to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
+            to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
                 
-        #     wandb.log(to_log, step=step)
+            wandb.log(to_log, step=step)
-        #     train_accumulator.reset()
+            train_accumulator.reset()
-        #     valid_accumulator.reset()
+            valid_accumulator.reset()
 
-        # if step % 5000 == 0:
+        if step % 5000 == 0:
-        #     manager.save(checkpoint_number=step)
+            manager.save(checkpoint_number=step)
 
-        # print(step)
+        print(step)
 
         step += 1
-    print('mean:')
+    # print('mean:')
-    print(np.mean(times[10:]))
+    # 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_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_64_10p import config
+from configs.iccv.config_abl_pyr_32_64_128_skin_skirt import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf

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_25p'
+    checkpoint_name = 'iccv_pyr_32_64_128_skin'
-    checkpoint_name_skirt = 'iccv_pyr_32_64_128_256_512_skirt'
+    checkpoint_name_skirt = 'iccv_pyr_32_64_128_skin_skirt'
-    iteration = '155000'
+    iteration = '75' + '000'
-    iteration_skirt : str = '115000'
+    iteration_skirt : str = '155' + '000'
+    error_type = 'collision' # 'euclidean' 'collision' edge normal
 
-    # checkpoint_name = 'abl_skin'
-    # checkpoint_name_skirt = checkpoint_name + '_skirt'
-    # iteration = '70000'
-    # iteration_skirt : str = iteration
 
     errors = []
     errors_skirt = []
@@ -23,20 +21,20 @@ 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=',')
+    #     csv_reader = csv.reader(f, delimiter=',')
-        for row in csv_reader:
+    #     for row in csv_reader:
-            per_garment_errors[garment_type_table[row[0].split('_')[0]]].append(float(row[1]))
+    #         per_garment_errors[garment_type_table[row[0].split('_')[0]]].append(float(row[1]))
 
-    print('\nNon-skirt:')
+    # print('\nNon-skirt:')
-    for key in per_garment_errors.keys():
+    # for key in per_garment_errors.keys():
-        avg = np.mean(per_garment_errors[key])
+    #     avg = np.mean(per_garment_errors[key])
-        errors.append(avg)
+    #     errors.append(avg)
-        print(key + ': ' + str(avg))
+    #     print(key + ': ' + str(avg))
 
-    print('\nAvg non-skirt: ' + str(np.mean(errors)))
+    # print('\nAvg non-skirt: ' + str(np.mean(errors)))
 
-    with open(os.path.join(folder, checkpoint_name_skirt + '-' + iteration_skirt + '.csv'), 'r') as f:
+    with open(os.path.join(folder, f'{checkpoint_name_skirt}-{iteration_skirt}-{error_type}.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]))
@@ -49,24 +47,24 @@ if __name__ == '__main__':
 
     print('Avg skirt: ' + str(np.mean(errors_skirt)))
 
-    cum_avg_shirt = np.mean(per_garment_errors['Tshirt'] + per_garment_errors_skirt['Tshirt'])
+    # cum_avg_shirt = np.mean(per_garment_errors['Tshirt'] + per_garment_errors_skirt['Tshirt'])
-    cum_avg_top = np.mean(per_garment_errors['Top'] + per_garment_errors_skirt['Top'])
+    # cum_avg_top = np.mean(per_garment_errors['Top'] + per_garment_errors_skirt['Top'])
 
-    print('Global tshirt avg: ' + str(cum_avg_shirt))
+    # print('Global tshirt avg: ' + str(cum_avg_shirt))
-    print('Global top avg: ' + str(cum_avg_top))
+    # print('Global top avg: ' + str(cum_avg_top))
 
-    print('\nGlobal per garment: ')
+    # print('\nGlobal per garment: ')
 
-    global_errors = []
+    # global_errors = []
-    per_garment_errors['Tshirt'].extend(per_garment_errors_skirt['Tshirt'])
+    # per_garment_errors['Tshirt'].extend(per_garment_errors_skirt['Tshirt'])
-    per_garment_errors['Top'].extend(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['Skirt'] = per_garment_errors_skirt['Skirt']
-    per_garment_errors['Dress'] = per_garment_errors_skirt['Dress']
+    # per_garment_errors['Dress'] = per_garment_errors_skirt['Dress']
-    for key in per_garment_errors.keys():
+    # for key in per_garment_errors.keys():
-        avg = np.mean(per_garment_errors[key])
+    #     avg = np.mean(per_garment_errors[key])
-        global_errors.append(avg)
+    #     global_errors.append(avg)
-        print(key + ': ' + str(avg), 'samples: ' + str(len(per_garment_errors[key])))
+    #     print(key + ': ' + str(avg), 'samples: ' + str(len(per_garment_errors[key])))
 
-    print('Global avg: ' + str(np.mean(global_errors)))
+    # print('Global avg: ' + str(np.mean(global_errors)))
-    print(len(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:

plot_examples.py

@@ -329,30 +329,33 @@ if __name__ == '__main__':
 
         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)
@@ -367,7 +370,7 @@ if __name__ == '__main__':
         # 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))
+        # 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)
 

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

@@ -46,7 +46,8 @@ 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_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_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 CVAENew as CVAE
@@ -331,10 +332,15 @@ def sampling_example(frame, camera, nr=15):
     for i in range(nr):
         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 + '_body.stl'), body, F_body)
-    save_stl(os.path.join(out_folder, frame, frame + '_gt.stl'), gt_mesh, faces.astype(np.int32))
+    # 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):
-        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 + '_' + 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'))
@@ -470,9 +476,9 @@ if __name__ == '__main__':
     # frame = '04925_272'
 
     # frames = ['01070_13', '02276_232', '02978_242', '04008_295', '04173_193']
-    frames = ['00214_111', '01661_210', '02144_249', '02151_37', '02930_275', '03812_3']
+    frames = ['02276_232', '02978_242', '04173_193']
     
-    out_folder = 'examples/sampling_skirt'
+    out_folder = 'examples/sampling_analysis'
     os.makedirs(out_folder, exist_ok=True)
     for frame in tqdm.tqdm(frames):
         sampling_example(frame, camera_1)