Merge remote-tracking branch 'origin/main' into main

configs/iccvw/abl_all.py

@@ -3,15 +3,15 @@ from utils.convnext_utils import CNBlockConfig
 config = dict()
 
 config['gpu'] = '2'
-config['name'] = 'abl_iccvw_all_1'
+config['name'] = 'abl_iccvw_all_2'
-config['notes'] = ''
+config['notes'] = 'fixed collision loss'
 config['tags'] = ['iccv', 'abl_all', 'torch']
 config['script'] = 'scripts/cvae.py'
 
-config['pretrained_model'] = ''
+config['pretrained_model'] = 'checkpoints/iccvw/abl_iccvw_all_1'
 
 config['use_skinning'] =              True # and deshaping
-config['use_normals'] =             True
+config['use_normals'] =               True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
 
 config['use_norm_loss'] =             True
@@ -34,14 +34,16 @@ config['device'] = 'cuda'
 
 config['train_dir'] = '/data-local/127/cloth3d_processed'
 config['valid_dir'] = '/data-local/127/cloth3d_processed'
-config['test_dir'] = '/data-net/dataset/test_ready'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
 
 if config['is_skirt']:
   config['train_frames'] = 'frames_train_skirt.txt'
   config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
 else:
   config['train_frames'] = 'frames_train.txt'
   config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
 
 config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
 config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'

configs/iccvw/abl_all_3.py

@@ -0,0 +1,196 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'abl_iccvw_all_3'
+config['notes'] = 'fixed collision loss, train from zero'
+config['tags'] = ['iccv', 'abl_all', 'torch']
+config['script'] = 'scripts/cvae.py'
+
+config['pretrained_model'] = ''
+
+config['use_skinning'] =              True # and deshaping
+config['use_normals'] =               True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['use_normals'], config['use_extra_losses']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['avg_garment_path'] = 'custom_data/avg/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['avg_garment_path'] != '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+config['balancing_activation_limit'] = 0.01
+
+config['signature']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['device'] = config['device']
+config['cvae']['is_label'] = False
+config['cvae']['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+config['cvae']['kernel_size'] = 7
+config['cvae']['bottleneck_size'] = 64 * config['bottleneck_scale']
+config['cvae']['latent_dim'] = config['cvae']['bottleneck_size']
+
+block_setting = [
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 3),
+    CNBlockConfig(128, 256, 3),
+    CNBlockConfig(256, config['cvae']['bottleneck_size'], 9),
+    CNBlockConfig(config['cvae']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cvae']['bottleneck_size'] * 2, 256, 3),
+    CNBlockConfig(256, 128, 9),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 3),
+    CNBlockConfig(32, 3, 3),
+]
+
+config['cvae']['encoder_block_settings'] = block_setting
+config['cvae']['decoder_block_settings'] = block_setting_reverse
+
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/abl_all_4.py

@@ -0,0 +1,196 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'abl_iccvw_all_4'
+config['notes'] = 'fixed collision loss, train from zero'
+config['tags'] = ['iccv', 'abl_all', 'torch']
+config['script'] = 'scripts/cvae.py'
+
+config['pretrained_model'] = 'checkpoints/iccvw/abl_iccvw_all_3'
+
+config['use_skinning'] =              True # and deshaping
+config['use_normals'] =               True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['use_normals'], config['use_extra_losses']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['avg_garment_path'] = 'custom_data/avg/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['avg_garment_path'] != '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+config['balancing_activation_limit'] = 0.01
+
+config['signature']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['device'] = config['device']
+config['cvae']['is_label'] = False
+config['cvae']['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+config['cvae']['kernel_size'] = 7
+config['cvae']['bottleneck_size'] = 64 * config['bottleneck_scale']
+config['cvae']['latent_dim'] = config['cvae']['bottleneck_size']
+
+block_setting = [
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 3),
+    CNBlockConfig(128, 256, 3),
+    CNBlockConfig(256, config['cvae']['bottleneck_size'], 9),
+    CNBlockConfig(config['cvae']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cvae']['bottleneck_size'] * 2, 256, 3),
+    CNBlockConfig(256, 128, 9),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 3),
+    CNBlockConfig(32, 3, 3),
+]
+
+config['cvae']['encoder_block_settings'] = block_setting
+config['cvae']['decoder_block_settings'] = block_setting_reverse
+
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/abl_all_5.py

@@ -0,0 +1,196 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '4'
+config['name'] = 'abl_iccvw_all_5'
+config['notes'] = 'fixed collision loss, train from zero, fixed latest checkpoint loading'
+config['tags'] = ['iccv', 'abl_all', 'torch']
+config['script'] = 'scripts/cvae.py'
+
+config['pretrained_model'] = 'checkpoints/iccvw/abl_iccvw_all_3'
+
+config['use_skinning'] =              True # and deshaping
+config['use_normals'] =               True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['use_normals'], config['use_extra_losses']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['avg_garment_path'] = 'custom_data/avg/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['avg_garment_path'] != '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+config['balancing_activation_limit'] = 0.01
+
+config['signature']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['device'] = config['device']
+config['cvae']['is_label'] = False
+config['cvae']['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+config['cvae']['kernel_size'] = 7
+config['cvae']['bottleneck_size'] = 64 * config['bottleneck_scale']
+config['cvae']['latent_dim'] = config['cvae']['bottleneck_size']
+
+block_setting = [
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 3),
+    CNBlockConfig(128, 256, 3),
+    CNBlockConfig(256, config['cvae']['bottleneck_size'], 9),
+    CNBlockConfig(config['cvae']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cvae']['bottleneck_size'] * 2, 256, 3),
+    CNBlockConfig(256, 128, 9),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 3),
+    CNBlockConfig(32, 3, 3),
+]
+
+config['cvae']['encoder_block_settings'] = block_setting
+config['cvae']['decoder_block_settings'] = block_setting_reverse
+
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/abl_all_skirt.py

@@ -0,0 +1,196 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'abl_iccvw_all_skirt'
+config['notes'] = 'fixed collision loss, train from zero'
+config['tags'] = ['iccv', 'abl_all', 'torch']
+config['script'] = 'scripts/cvae.py'
+
+config['pretrained_model'] = ''
+
+config['use_skinning'] =              True # and deshaping
+config['use_normals'] =               True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+
+ablation_count = [config['use_skinning'], config['use_normals'], config['use_extra_losses']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['avg_garment_path'] = 'custom_data/avg/train_skirt_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['avg_garment_path'] != '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = True
+config['dataset_in_memory'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_1_skirt'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1_skirt'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1_skirt'
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+config['balancing_activation_limit'] = 0.01
+
+config['signature']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['device'] = config['device']
+config['cvae']['is_label'] = False
+config['cvae']['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+config['cvae']['kernel_size'] = 7
+config['cvae']['bottleneck_size'] = 64 * config['bottleneck_scale']
+config['cvae']['latent_dim'] = config['cvae']['bottleneck_size']
+
+block_setting = [
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 3),
+    CNBlockConfig(128, 256, 3),
+    CNBlockConfig(256, config['cvae']['bottleneck_size'], 9),
+    CNBlockConfig(config['cvae']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cvae']['bottleneck_size'] * 2, 256, 3),
+    CNBlockConfig(256, 128, 9),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 3),
+    CNBlockConfig(32, 3, 3),
+]
+
+config['cvae']['encoder_block_settings'] = block_setting
+config['cvae']['decoder_block_settings'] = block_setting_reverse
+
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_32.py

@@ -0,0 +1,302 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'pyr_iccvw_32'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'mesh_unposed',
+                            'uv_unposed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64.py

@@ -0,0 +1,302 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '3'
+config['name'] = 'pyr_iccvw_64'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'mesh_unposed',
+                            'uv_unposed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64_2.py

@@ -0,0 +1,302 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '5'
+config['name'] = 'pyr_iccvw_64_2'
+config['notes'] = 'continue from previous'
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = 'checkpoints/iccvw/pyr_iccvw_64'
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'mesh_unposed',
+                            'uv_unposed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64_cape_f.py

@@ -0,0 +1,295 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '2'
+config['name'] = 'pyr_iccvw_64_cape_f'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = True
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127_2/cape_processed/train/female'
+config['valid_dir'] = '/data-local/127_2/cape_processed/test/female'
+config['test_dir'] = '/data-local/127_2/cape_processed/test/female'
+config['train_frames'] = None
+config['valid_frames'] = None
+
+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['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'mesh_unposed',
+                            'uv_unposed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_cape_f'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_cape_f'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_cape_f'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64_cape_m.py

@@ -0,0 +1,295 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'pyr_iccvw_64_cape_m'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = True
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127_2/cape_processed/train/male'
+config['valid_dir'] = '/data-local/127_2/cape_processed/test/male'
+config['test_dir'] = '/data-local/127_2/cape_processed/test/male'
+config['train_frames'] = None
+config['valid_frames'] = None
+
+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['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'mesh_unposed',
+                            'uv_unposed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_cape_m'
+config['body_model'] = 'checkpoints/iccvw/body_torch_cape_m'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_cape_m'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64_norm.py

@@ -0,0 +1,288 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '5'
+config['name'] = 'pyr_iccvw_64_norm'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               False
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2 - 40*2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2 - 40*2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2 - 40*2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2 - 40*2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    raise NotImplementedError
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64_reg.py

@@ -0,0 +1,306 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'pyr_iccvw_64_reg'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          False # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64_skin.py

@@ -0,0 +1,309 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'pyr_iccvw_64_skin'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              False # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+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]
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+for res in config['pyramid']['resolutions']:
+    if res != 512:
+        res_modifier = '_' + str(res)
+        config['signature'].add('uv_body_posed' + res_modifier)
+        if config['use_skinning']:
+          config['signature'].add('uv_unposed' + res_modifier)
+        else:
+          config['signature'].add('uv_posed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_4'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

configs/iccvw/pyr_64_skirt.py

@@ -0,0 +1,302 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'pyr_iccvw_64_skirt'
+config['notes'] = ''
+config['tags'] = ['pyr', 'iccv', 'torch']
+config['script'] = 'scripts/cvae_pyramid.py'
+
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+
+config['use_skinning'] =              True # and deshaping
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_norm_loss'] =             True
+config['use_normals'] =               True
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [64]
+config['pyramid']['pretrained_pyramid'] = ''
+config['pyramid']['pretrained_pyramid_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = ''
+
+config['train_dir'] = '/data-local/127/cloth3d_processed'
+config['valid_dir'] = '/data-local/127/cloth3d_processed'
+config['test_dir'] = '/data-local/127_2/cloth3d_processed_test'
+
+if config['is_skirt']:
+  config['train_frames'] = 'frames_train_skirt.txt'
+  config['valid_frames'] = 'frames_valid_skirt.txt'
+  config['test_frames'] = 'frames_test_skirt.txt'
+else:
+  config['train_frames'] = 'frames_train.txt'
+  config['valid_frames'] = 'frames_valid.txt'
+  config['test_frames'] = 'frames_test.txt'
+
+config['dataset_in_memory'] = False
+config['resolution'] = None
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.001
+config['balancing_activation_limit'] = 0.012
+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']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'mesh_unposed',
+                            'uv_unposed',
+                            'uv_normals',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+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'].add('uv_body_posed' + res_modifier)
+        config['signature'].add('uv_unposed' + res_modifier)
+        config['signature'].add('uv_normals' + res_modifier)
+        config['signature'].add('uv_static' + res_modifier)
+        config['signature'].add('uv_mask' + res_modifier)
+
+
+config['static_model'] = 'checkpoints/iccvw/static_iccvw_1_skirt'
+config['body_model'] = 'checkpoints/iccvw/body_iccvw_1_skirt'
+config['normals_model'] = 'checkpoints/iccvw/norm_iccvw_1_skirt'
+config['freeze_encoders'] = True
+
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['kernel_size'] = 7
+    level['upscale_enhancer'] = ''
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(16, 32, 3),
+        CNBlockConfig(32, 64, 3),
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 64, 9),
+        CNBlockConfig(64, 32, 3),
+        CNBlockConfig(32, 16, 3),
+        CNBlockConfig(16, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_256_skirt'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 3),
+        CNBlockConfig(128, 128, 3),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 3),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(128, 65, 3),
+        CNBlockConfig(64, 3, 3),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['kernel_size'] = 5
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_128_skirt'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, 128, 9),
+        CNBlockConfig(128, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
+        CNBlockConfig(128, 128, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_64_skirt'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(64, level['bottleneck_size'], 9),
+        CNBlockConfig(level['bottleneck_size'], None, 9),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
+        CNBlockConfig(64, 3, 9),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['kernel_size'] = 3
+    level['upscale_enhancer'] = 'checkpoints/iccvw/iccv_32_skirt'
+    level['upscale_enhancer_freeze'] = True
+    level['bottleneck_size'] = 64 * config['bottleneck_scale']
+    level['input_features'] = 3+3+3+3 if config['use_normals'] else 3+3+3
+
+    block_setting = [
+        CNBlockConfig(level['bottleneck_size'], None, 16),
+    ]
+
+    block_setting_reverse = [
+        CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
+    ]
+
+    level['encoder_block_settings'] = block_setting
+    level['decoder_block_settings'] = block_setting_reverse
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+####################### cond_ae_norm ############################
+config['cond_ae_norm'] = dict()
+config['cond_ae_norm']['device'] = config['device']
+config['cond_ae_norm']['is_label'] = False
+# config['cond_ae_norm']['latent_dim'] = config['latent_dim']
+config['cond_ae_norm']['kernel_size'] = 7
+config['cond_ae_norm']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_norm']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_norm']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_norm']['encoder_block_settings'] = block_setting
+config['cond_ae_norm']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_norm']['activation'] = 'tanh'
+
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+# config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+# config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

data/dataset.py

@@ -140,7 +140,7 @@ class DatasetCloth3D(torch.utils.data.Dataset):
         self.resolutions = resolutions
 
         self.transforms = tv.transforms.ToTensor()
-        self.frames = read_frames_file(os.path.join(folder, frames_file), shuffle=True)
+        self.frames = read_frames_file(os.path.join(folder, frames_file), shuffle=False)
 
         self.static_cache = StaticCache(folder, signature, is_cape=is_cape, resolutions=resolutions, device=device)
 
@@ -208,7 +208,7 @@ class DatasetCloth3D(torch.utils.data.Dataset):
                 item['uv_unposed' + res_string] = uv_unposed_no_shape
 
             if 'uv_body_posed' + res_string in self.signature:
-                uv_body_posed_no_orient = np.load(os.path.join(self.folder, 'uv_body_posed_no_orient' + res_string, f'{frame.id}_{frame.frame_nr}.npz')); uv_body_posed_no_orient = uv_body_posed_no_orient['uv_body_posed']
+                uv_body_posed_no_orient = np.load(os.path.join(self.folder, 'uv_body_posed_no_orient' + res_string[1:], f'{frame.id}_{frame.frame_nr}.npz')); uv_body_posed_no_orient = uv_body_posed_no_orient['uv_body_posed']
                 item['uv_body_posed' + res_string] = uv_body_posed_no_orient
 
             if 'uv_posed' + res_string in self.signature:
@@ -244,6 +244,9 @@ if __name__ == '__main__':
     import plotly.express as ex
     from plotly.subplots import make_subplots
     from custom_utils.custom_utils import _maskFaces
+    from losses.losses import collision_loss, normal_loss
+    from smpl.smpl_torch import SMPL
+    from torch.profiler import profile, record_function, ProfilerActivity
 
     F = np.load('smpl/smpl_faces.npy')
     F_skirt = np.load('smpl/smpl_faces_skirt.npy')
@@ -267,61 +270,98 @@ if __name__ == '__main__':
     
     dataset = Dataset('/data-local/127/cloth3d_processed', signature, resolutions=[512], device=device, frames_file='frames_train.txt')
     train_dataloader = DataLoader(dataset, batch_size=4, drop_last=True, shuffle=False)
+    smpl = SMPL(orig_smpl=False, path='smpl', device='cuda')
 
+    # create a profiler object
+    profiler = torch.profiler.profile(
+        activities=[ProfilerActivity.CPU, ProfilerActivity.CUDA],
+        schedule=torch.profiler.schedule(wait=2, warmup=1, active=3, repeat=2),
+        on_trace_ready=torch.profiler.tensorboard_trace_handler("log_dir"),
+        with_stack=True,
+        profile_memory=True,
+    )
+
+
+    step = 0
     for batch in train_dataloader:
         batch
-        b = 0
+        print(batch['id'][0])
-        mesh_mask = batch['mesh_mask'][b].cpu().numpy()
+        with profiler:
-        faces = F_skirt if batch['garment'][b] in ['Skirt', 'Dress'] else F
+            m = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], batch['mesh_unposed'])[0]
-        _, faces = _maskFaces(np.zeros((14475, 3)), faces, mesh_mask)
+            profiler.step()
+        step += 1
+        if step > 25:
+            break
 
-        mesh_static = batch['mesh_static'][b].cpu().numpy()[mesh_mask]
+    profiler.stop()
-        mesh_posed = batch['mesh_posed'][b].cpu().numpy()[mesh_mask]
+    print(profiler.key_averages().table(sort_by="cpu_time_total", row_limit=25))
-        mesh_unposed = batch['mesh_unposed'][b].cpu().numpy()[mesh_mask]
+    print(profiler.key_averages().table(sort_by="cuda_time_total", row_limit=25))
-        mesh_body_posed = batch['mesh_body_posed'][b].cpu().numpy()
+    print(profiler.key_averages(group_by_stack_n=5).table(sort_by='self_cpu_time_total', row_limit=10))
-
-        fig = make_subplots(rows=2, cols=2,
-                            specs=[[{'type': 'mesh3d'}, {'type': 'mesh3d'}],
-                                [{'type': 'mesh3d'}, {'type': 'mesh3d'}]])
-
-        fig.add_trace(go.Mesh3d(x=mesh_static[:,0], y=mesh_static[:,2], z=mesh_static[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], opacity=1), row=1, col=1)
-        fig.add_trace(go.Mesh3d(x=mesh_posed[:,0], y=mesh_posed[:,2], z=mesh_posed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], opacity=1), row=1, col=2)
-        fig.add_trace(go.Mesh3d(x=mesh_unposed[:,0], y=mesh_unposed[:,2], z=mesh_unposed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], opacity=1), row=2, col=1)
-        fig.add_trace(go.Mesh3d(x=mesh_body_posed[:,0], y=mesh_body_posed[:,2], z=mesh_body_posed[:,1], i=F[:,0], j=F[:,1], k=F[:,2], opacity=1), row=2, col=2)
-
-        fig.update_layout(scene=dict(xaxis=dict(range=[-1, 1], autorange=False),
-                                    yaxis=dict(range=[-1, 1], autorange=False),
-                                    zaxis=dict(range=[-1, 1], autorange=False),
-                                    aspectmode='cube'),
-                        scene2=dict(xaxis=dict(range=[-1, 1], autorange=False),
-                                    yaxis=dict(range=[-1, 1], autorange=False),
-                                    zaxis=dict(range=[-1, 1], autorange=False),
-                                    aspectmode='cube'),
-                        scene3=dict(xaxis=dict(range=[-1, 1], autorange=False),
-                                    yaxis=dict(range=[-1, 1], autorange=False),
-                                    zaxis=dict(range=[-1, 1], autorange=False),
-                                    aspectmode='cube'),
-                        scene4=dict(xaxis=dict(range=[-1, 1], autorange=False),
-                                    yaxis=dict(range=[-1, 1], autorange=False),
-                                    zaxis=dict(range=[-1, 1], autorange=False),
-                                    aspectmode='cube'))
-
-        fig.show()
 
 
-        uv_mask = batch['uv_mask'][b].cpu().numpy()
+        # b = 0
-        uv_mask = np.repeat(uv_mask[np.newaxis, :, :], 3, axis=0)
+        # mesh_mask = batch['mesh_mask'][b].cpu().numpy()
-        uv_static = (batch['uv_static'][b].cpu().numpy() + 1) / 2
+        # faces = F_skirt if batch['garment'][b] in ['Skirt', 'Dress'] else F
-        uv_posed = (batch['uv_posed'][b].cpu().numpy() + 1) / 2
+        # _, faces = _maskFaces(np.zeros((14475, 3)), faces, mesh_mask)
-        uv_unposed = (batch['uv_unposed'][b].cpu().numpy() + 1) / 2
-        uv_body_posed = (batch['uv_body_posed'][b].cpu().numpy() + 1) / 2
-        uv_normals = (batch['uv_normals'][b].cpu().numpy() + 1.5) / 3
 
-        img = np.concatenate([uv_mask, uv_static, uv_posed, uv_unposed, uv_body_posed, uv_normals], axis=2)
+        # c = collision_loss(batch['mesh_posed'], batch['mesh_body_posed'], batch['mesh_mask'])
-        img = np.transpose(img, (1, 2, 0))
+        # fig = go.Figure(data=[go.Mesh3d(x=batch['mesh_posed'].cpu().numpy()[0,mesh_mask,0], y=batch['mesh_posed'].cpu().numpy()[0,mesh_mask,1], z=batch['mesh_posed'].cpu().numpy()[0,mesh_mask,2], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=1),
-        ex.imshow(img).show()
+        #                         go.Mesh3d(x=batch['mesh_body_posed'].cpu().numpy()[0,:,0], y=batch['mesh_body_posed'].cpu().numpy()[0,:,1], z=batch['mesh_body_posed'].cpu().numpy()[0,:,2], i=F[:,0], j=F[:,1], k=F[:,2], color='lightblue', opacity=1),
+        # ])
+        # fig.update_layout(scene_aspectmode='cube')
+        # fig.update_layout(scene=dict(xaxis=dict(range=[-1,1]), yaxis=dict(range=[-1,1]), zaxis=dict(range=[-1,1])))
+        # fig.show()
 
-        pass
+
+
+
+        # mesh_static = batch['mesh_static'][b].cpu().numpy()[mesh_mask]
+        # mesh_posed = batch['mesh_posed'][b].cpu().numpy()[mesh_mask]
+        # mesh_unposed = batch['mesh_unposed'][b].cpu().numpy()[mesh_mask]
+        # mesh_body_posed = batch['mesh_body_posed'][b].cpu().numpy()
+
+        # fig = make_subplots(rows=2, cols=2,
+        #                     specs=[[{'type': 'mesh3d'}, {'type': 'mesh3d'}],
+        #                         [{'type': 'mesh3d'}, {'type': 'mesh3d'}]])
+
+        # fig.add_trace(go.Mesh3d(x=mesh_static[:,0], y=mesh_static[:,2], z=mesh_static[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], opacity=1), row=1, col=1)
+        # fig.add_trace(go.Mesh3d(x=mesh_posed[:,0], y=mesh_posed[:,2], z=mesh_posed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], opacity=1), row=1, col=2)
+        # fig.add_trace(go.Mesh3d(x=mesh_unposed[:,0], y=mesh_unposed[:,2], z=mesh_unposed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], opacity=1), row=2, col=1)
+        # fig.add_trace(go.Mesh3d(x=mesh_body_posed[:,0], y=mesh_body_posed[:,2], z=mesh_body_posed[:,1], i=F[:,0], j=F[:,1], k=F[:,2], opacity=1), row=2, col=2)
+
+        # fig.update_layout(scene=dict(xaxis=dict(range=[-1, 1], autorange=False),
+        #                             yaxis=dict(range=[-1, 1], autorange=False),
+        #                             zaxis=dict(range=[-1, 1], autorange=False),
+        #                             aspectmode='cube'),
+        #                 scene2=dict(xaxis=dict(range=[-1, 1], autorange=False),
+        #                             yaxis=dict(range=[-1, 1], autorange=False),
+        #                             zaxis=dict(range=[-1, 1], autorange=False),
+        #                             aspectmode='cube'),
+        #                 scene3=dict(xaxis=dict(range=[-1, 1], autorange=False),
+        #                             yaxis=dict(range=[-1, 1], autorange=False),
+        #                             zaxis=dict(range=[-1, 1], autorange=False),
+        #                             aspectmode='cube'),
+        #                 scene4=dict(xaxis=dict(range=[-1, 1], autorange=False),
+        #                             yaxis=dict(range=[-1, 1], autorange=False),
+        #                             zaxis=dict(range=[-1, 1], autorange=False),
+        #                             aspectmode='cube'))
+
+        # fig.show()
+
+
+        # uv_mask = batch['uv_mask'][b].cpu().numpy()
+        # uv_mask = np.repeat(uv_mask[np.newaxis, :, :], 3, axis=0)
+        # uv_static = (batch['uv_static'][b].cpu().numpy() + 1) / 2
+        # uv_posed = (batch['uv_posed'][b].cpu().numpy() + 1) / 2
+        # uv_unposed = (batch['uv_unposed'][b].cpu().numpy() + 1) / 2
+        # uv_body_posed = (batch['uv_body_posed'][b].cpu().numpy() + 1) / 2
+        # uv_normals = (batch['uv_normals'][b].cpu().numpy() + 1.5) / 3
+
+        # img = np.concatenate([uv_mask, uv_static, uv_posed, uv_unposed, uv_body_posed, uv_normals], axis=2)
+        # img = np.transpose(img, (1, 2, 0))
+        # ex.imshow(img).show()
+
+        # pass
 
     pass 
 

data/dataset_cape.py

@@ -82,7 +82,7 @@ class StaticCache():
                 res_string = '_' + str(res)
 
             if 'uv_static' + res_string in self.signature:
-                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(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.astype(np.float32)
             if 'uv_mask' + res_string in self.signature:
                 if self.is_cape:
                     data['uv_mask' + res_string] = self.uv_masks[res]
@@ -158,6 +158,7 @@ class DatasetCape(torch.utils.data.Dataset):
             item['id'] = frame.id
         if 'frame_nr' in self.signature:
             item['frame_nr'] = frame.frame_nr
+            item['garment'] = 'cape'
         if 'pose_shape' in self.signature:
             pose_shape = np.load(os.path.join(self.folder, 'pose_shape', frame.id + separator + frame.frame_nr + '.npy')).astype(np.float32)
             pose_shape[:3] = 0
@@ -183,27 +184,18 @@ class DatasetCape(torch.utils.data.Dataset):
             if res != 512:
                 res_string = '_' + str(res)
 
-            if 'uv_curvature' + res_string in self.signature:
-                uv_curvature = np.load(os.path.join(self.folder, 'uv_curvature' + res_string, frame.id + separator + frame.frame_nr + '.npz')); 
-                if res_string != '':
-                    uv_curvature = uv_curvature['uv_curvature'] 
-                else:
-                    uv_curvature = uv_curvature['curvature_uv']
-                uv_curvature = torch.nn.functional.one_hot(torch.tensor(uv_curvature, device=self.device, dtype=torch.long), 7).float().to(self.device)
-                item['uv_curvature' + res_string] = uv_curvature
-
             if 'uv_unposed' + res_string in self.signature:
                 uv_unposed_no_shape = np.load(os.path.join(self.folder, 'uv_unposed_no_shape' + res_string, frame.id + separator + frame.frame_nr + '.npz')); uv_unposed_no_shape = uv_unposed_no_shape['uv_unposed_no_shape']
-                item['uv_unposed' + res_string] = uv_unposed_no_shape
+                item['uv_unposed' + res_string] = uv_unposed_no_shape.astype(np.float32)
 
             if 'uv_body_posed' + res_string in self.signature:
                 uv_posed_body_no_orient = np.load(os.path.join(self.folder, uv_posed_body_no_orient_folder_name + res_string, frame.id + separator + frame.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
+                item['uv_body_posed' + res_string] = uv_posed_body_no_orient.astype(np.float32)
 
             if 'uv_posed' + res_string in self.signature:
                 uv_posed = np.load(os.path.join(self.folder, 'uv_posed_no_orient' + res_string, frame.id + separator + frame.frame_nr + '.npz')); uv_posed = uv_posed['uv_posed_no_orient']
-                item['uv_posed' + res_string] = uv_posed
+                item['uv_posed' + res_string] = uv_posed.astype(np.float32)
 
             if 'uv_normals' + res_string in self.signature:
                 uv_normals = np.load(os.path.join(self.folder, 'uv_normals' + res_string, frame.id + separator + frame.frame_nr + '.npz')); uv_normals = uv_normals['uv_normals']

data/downscale_cape.py

@@ -0,0 +1,207 @@
+import argparse
+import os
+import tqdm
+import cv2
+import scipy.interpolate as spi
+import numpy as np
+import plotly.graph_objects as go
+import plotly.express as ex
+import torch
+from torchvision.transforms import Resize
+from torchvision.transforms.functional import InterpolationMode
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+
+
+def get_img_idxs():
+    img_idxs = dict()
+    img_coords = dict()
+    uv_masks = dict()
+    uv_mask = np.load('custom_data/garment_uv_mask_full.npy')
+    coords = np.transpose(np.stack(np.nonzero((1 - uv_mask))), (1,0))
+    img_idx = np.transpose(np.stack(np.nonzero((uv_mask))), (1,0))
+    img_idxs[512] = img_idx
+    img_coords[512] = coords
+    uv_masks[512] = uv_mask.astype(np.int32)
+    for res in [32, 64, 128, 256]:
+        down = resizers_nearest[res](torch.from_numpy(uv_mask[None,:,:]).to(device)).cpu().numpy()
+        down = np.squeeze(down.astype(bool))
+        coords = np.transpose(np.stack(np.nonzero((1 - down))), (1,0))
+        img_idx = np.transpose(np.stack(np.nonzero((down))), (1,0))
+        img_idxs[res] = img_idx
+        img_coords[res] = coords
+        uv_masks[res] = down.astype(np.int32)
+
+
+    uv_masks_body = dict()
+    uv_mask_body = np.load('custom_utils/mask_256x512.npy')
+    uv_mask_body = cv2.dilate(uv_mask_body.astype(np.float32), cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2)
+    uv_masks_body[512] = uv_mask_body
+    for res in [32, 64, 128, 256]:
+        down = resizers_nearest[res](torch.from_numpy(uv_mask_body[None,:,:]).to(device)).cpu().numpy()
+        down = np.squeeze(down.astype(bool))
+        uv_masks_body[res] = down
+
+    return img_idxs, img_coords, uv_masks, uv_masks_body
+
+
+def fill(img, mask):
+    coords = img_coords[img.shape[0]]
+    img_idx = img_idxs[img.shape[0]]
+    # coords = np.transpose(np.stack(np.nonzero((1 - uv_masks[img.shape[0]]))), (1,0))
+    # img_idx = np.transpose(np.stack(np.nonzero((uv_masks[img.shape[0]]))), (1,0))
+    img_data = img[img_idx[:,0], img_idx[:,1], :]
+
+    interpolator =  spi.NearestNDInterpolator(x=img_idx, y=img_data)
+    img_2 = interpolator(coords)
+    res = np.zeros((512,256,3), dtype=np.float32)
+    res[coords[:,0], coords[:,1], :] = img_2
+    res[img_idx[:,0], img_idx[:,1], :] = img_data
+
+    return res
+
+
+def fill_label(img, mask):
+    coords = img_coords[img.shape[0]]
+    img_idx = img_idxs[img.shape[0]]
+    img_data = img[img_idx[:,0], img_idx[:,1]]
+
+    interpolator =  spi.NearestNDInterpolator(x=img_idx, y=img_data)
+    img_2 = interpolator(coords)
+    res = np.zeros((512,256), dtype=np.float32)
+    res[coords[:,0], coords[:,1]] = img_2
+    res[img_idx[:,0], img_idx[:,1]] = img_data
+
+    return res
+
+
+def generate_downscaled_uv_map(folder, id, size):
+    img = np.load(os.path.join(folder, 'uv_mask', id + '.npz')); img = img['uv_mask'].astype(np.float32)
+    down = tf.image.resize(img[:,:,tf.newaxis], size=(size, int(size/2)), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+    down = np.squeeze(down.numpy().astype(bool))
+    np.savez_compressed(os.path.join(folder, 'uv_mask' + '_' + str(size), id + '.npz'), uv_mask = down)
+
+
+class UVMaskStore():
+    def __init__(self, folder, size):
+        self.size = size
+
+    def __getitem__(self, id) -> dict:
+        return uv_masks[self.size]
+
+
+def downscale_uv_maps_posed_body(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_posed_body_no_orient']
+        img = fill(img, uv_masks_body[512])
+        for size in sizes:
+            mask = uv_masks_body[size]
+            down = resizers[size](torch.from_numpy(img.transpose((2,0,1))).to(device)).cpu().numpy()
+            down = down * mask[None,:,:]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_posed_body_no_orient = down)
+
+
+def downscale_uv_normals(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_normals']
+        img = fill(img, uv_masks_body[512])
+        for size in sizes:
+            mask = uv_masks_body[size]
+            down = resizers[size](torch.from_numpy(img.transpose((2,0,1))).to(device)).cpu().numpy()
+            down = down * mask[None,:,:]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_normals = down)
+
+
+
+def downscale_uv_maps_unposed(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_unposed_no_shape']
+        mask_full = uv_mask_store[512][None]
+        img = fill(img, mask_full)
+        for size in sizes:
+            mask = uv_mask_store[size][None]
+            down = resizers[size](torch.from_numpy(img.transpose((2,0,1))).to(device)).cpu().numpy()
+            down = down * mask[None,:,:]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_unposed_no_shape = down)
+
+
+def downscale_uv_maps_static(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_static']
+        mask_full = uv_mask_store[512][None]
+        img = fill(img, mask_full)
+
+        for size in sizes:
+            down = resizers[size](torch.from_numpy(img.transpose((2,0,1))).to(device)).cpu().numpy() 
+            mask = uv_mask_store[size][None]
+            down = down * mask[None,:,:]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_static = down)
+
+
+def downscale_uv_maps_mask(folder, type, size):
+    os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_mask'].astype(np.float32)
+        down = tf.image.resize(img[:,:,tf.newaxis], size=(size, int(size/2)), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+        down = np.squeeze(down.numpy().astype(bool))
+        np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_mask = down)
+
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-f", "--folder", help = "end of range", default='/data-local/127_2/cape_processed/train/male')
+    parser.add_argument("-s", "--start", help = "start of range", default=0)
+    parser.add_argument("-e", "--end", help = "end of range", default=100000)
+    parser.add_argument("-n", "--name", help = "end of range", default='lhunor')
+    parser.add_argument("-d", "--debug", help = "end of range", default=False, action='store_true')
+    args = parser.parse_args()
+
+    device = 'cuda'
+
+    sizes = [32, 64, 128, 256]
+    folder = args.folder
+
+    resizers = { res: Resize(size=(res, int(res/2)), interpolation=InterpolationMode.BICUBIC).to(device) for res in sizes }
+    resizers_nearest = { res: Resize(size=(res, int(res/2)), interpolation=InterpolationMode.NEAREST_EXACT).to(device) for res in sizes }
+
+    img_idxs, img_coords, uv_masks, uv_masks_body = get_img_idxs()
+
+    uv_mask_store = { size: UVMaskStore(folder, size=size) for size in sizes }
+    uv_mask_store[512] = UVMaskStore(folder, size=512)
+
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=32)
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=64)
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=128)
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=256)
+    # downscale_uv_maps_static(folder=folder, type='uv_static', sizes=sizes)
+
+    downscale_uv_maps_unposed(folder=folder, type='uv_unposed_no_shape', sizes=sizes)
+    downscale_uv_normals(folder=folder, type='uv_normals', sizes=sizes)
+    downscale_uv_maps_posed_body(folder=folder, type='uv_posed_body_no_orient', sizes=sizes)
+
+
+    print()

data/preprocessing.py

@@ -36,94 +36,6 @@ from smpl.smpl_torch import SMPL
 from custom_utils.custom_utils import _maskFaces
 
 
-
-def clean_dataset(folder):
-    ids = os.listdir(folder)
-
-    for id in tqdm(ids):
-
-        if not os.path.isdir(os.path.join(folder, id)):
-            continue
-
-        files = os.listdir(os.path.join(folder, id))
-
-        for file in files:
-            if file.startswith('glmarks') or file.find('nricp') != -1:
-                os.remove(os.path.join(folder, id, file))
-
- 
-def generate_frames_file(folder, file_name):
-    ids = os.listdir(folder)
-    frames = []
-
-    for id in tqdm(ids):
-
-        if not os.path.isdir(os.path.join(folder, id)):
-            continue
-
-        garments = [f.replace('.obj','') for f in os.listdir(os.path.join(folder, id)) if f.endswith('.obj')]
-        info = loadInfo(os.path.join(folder, id, 'info.mat'))
-
-        for garment in garments:
-            for i in range(info['poses'].shape[1]):
-                frames.append(Frame(id, i, garment))
-
-    with open(os.path.join(folder, file_name), 'w') as f:
-        for i, frame in enumerate(frames):
-            f.write(str(frame.id) + ' ' + str(frame.frame_nr) + ' ' + str(frame.garment) + '\n')
-
-
-def split_data(folder, ratio):
-    with open(os.path.join(folder, 'frames_all.txt'), "r") as f:
-        frames = f.readlines()
-
-    ids = sorted(list(set([frame.split()[0] for frame in frames])))
-    train_last_id = round(len(ids) * ratio)
-
-    train_frames = []
-    valid_frames = []
-
-    for frame in tqdm(frames):
-        id = frame.split()[0]
-        if id in ids[:train_last_id]:
-            train_frames.append(frame)
-        else:
-            valid_frames.append(frame)
-
-    with open(os.path.join(folder, f'frames_train_{ratio}.txt'), 'w') as f:
-        f.writelines(train_frames)
-
-    with open(os.path.join(folder, f'frames_valid_{round(1-ratio,1)}.txt'), 'w') as f:
-        f.writelines(valid_frames)
-
-
-def genereated_registered_and_mask(folder, is_skirt = False):
-    ids = os.listdir(folder)
-
-    for id in tqdm(ids):
-        garment_dir = os.path.join(folder, id)
-        if not os.path.isdir(garment_dir):
-            continue
-        garments = [f.replace('.pc16','') for f in os.listdir(garment_dir) if f.find('_') == -1 and not f.endswith('.mat') and not f.endswith('.obj') and not f.startswith('Combined')]
-        
-        assert len(garments) == 1
-
-        if os.path.exists(os.path.join(garment_dir, garments[0] + '_registered.pc16')):
-            continue
-        
-        garment = garments[0]
-
-        verts = readPC2(os.path.join(garment_dir, garment + '.pc16'), True)['V']
-        map = sio.loadmat(os.path.join(garment_dir, garment + '_map.mat'))['map'].reshape((-1))
-        verts = verts[:, map, :] # ---------------> This is the garment after registration
-        raw_mask = sio.loadmat(os.path.join(garment_dir, garment + '_mask.mat'))['mask'].reshape((-1))
-        mask = raw_mask > 0
-        # boundaries = raw_mask == 2
-
-        writePC2(os.path.join(garment_dir, garment + '_registered.pc16'), verts, True)
-        np.save(os.path.join(garment_dir, garment + '_mask.npy'), mask)
-
-
 def create_extras_file(folder):
     # create a new pytables file
     root = '/'.join(folder.split('/')[:-1])
@@ -261,14 +173,15 @@ def create_mesh_body_posed_no_orient(folder, out_folder):
             continue
 
         info = sio.loadmat(os.path.join(folder, id, 'info.mat'))
-    
-
         pose, shape, gender = info['poses'], info['shape'], info['gender']
+        # if pose.shape[0] == 72:
         pose = np.transpose(pose, [1, 0]).astype(np.float32)
 
         pose[:, :3] = 0
         beta = np.squeeze(np.concatenate((shape, gender), axis=1)).astype(np.float32)
 
+        smpl = SMPL(path='smpl', device='cuda', batch_size=pose.shape[0])
+
         T = smpl(torch.tensor(pose, device=smpl.device), torch.tensor(np.tile(beta[np.newaxis, :], [pose.shape[0], 1]), device=smpl.device))[0]
         T = T.cpu().numpy()
 
@@ -456,6 +369,9 @@ def create_mesh_unposed_no_shape(folder, folder_reg, out_folder, start=0, end=1)
 
         pose = torch.tensor(pose, dtype=torch.float32, device='cuda')
         shape = torch.tensor(shape, dtype=torch.float32, device='cuda') 
+
+        smpl = SMPL(path='smpl', device='cuda', batch_size=pose.shape[0])
+
         
         for garment in garments:
             if os.path.exists(os.path.join(out_folder, f'{id}_{garment}.pc16')):
@@ -627,6 +543,49 @@ def create_frames_file(folder, out_folder, split=0.9):
                 f.write(f'{frame.id} {frame.frame_nr} {frame.garment}\n')
 
 
+def create_frames_file_test(folder, out_folder):
+    ids = os.listdir(folder)
+
+    frames_non_skirt = []
+    frames_skirt = []
+    ids_non_skirt = set()
+    ids_skirt = set()
+
+    for id in tqdm(ids):
+        garment_dir = os.path.join(folder, id)
+        if not os.path.isdir(garment_dir):
+            continue
+
+        info = sio.loadmat(os.path.join(folder, id, 'info.mat'))
+        garments = [f.replace('.obj','') for f in os.listdir(garment_dir) if f.endswith('.obj')]
+        frames = info['poses'].shape[1]
+
+        assert info['poses'].shape[0] == 72
+
+        for garment in garments:
+            for i in range(frames):
+                if garment == 'Skirt' or garment == 'Dress':
+                    frames_skirt.append(Frame(id, i, garment))
+                    ids_skirt.add(id)
+                else:
+                    frames_non_skirt.append(Frame(id, i, garment))
+                    ids_non_skirt.add(id)
+
+    ids_skirt = list(ids_skirt)
+    ids_non_skirt = list(ids_non_skirt)
+
+    with open(os.path.join(out_folder, 'frames_test.txt'), 'w') as f:
+        for frame in frames_non_skirt:
+            if frame.id in ids_non_skirt:
+                f.write(f'{frame.id} {frame.frame_nr} {frame.garment}\n')
+
+    with open(os.path.join(out_folder, 'frames_test_skirt.txt'), 'w') as f:
+        for frame in frames_skirt:
+            if frame.id in ids_skirt:
+                f.write(f'{frame.id} {frame.frame_nr} {frame.garment}\n')
+
+
+
 def create_frames_file_partial(folder, out_folder, split=0.9, part=0.1):
     ids = os.listdir(folder)
 
@@ -674,25 +633,26 @@ def create_frames_file_partial(folder, out_folder, split=0.9, part=0.1):
 
 
 def check_irregular_poses(folder, folder_reg, out_folder):
-    frame: Frame = Frame('01512', 50, 'Dress')
+    for i in range(100, 200, 5):
-    mesh_posed = readPC2Frame(os.path.join(out_folder, 'mesh_posed_no_orient', f'{frame.id}_{frame.garment}.pc16'), frame.frame_nr, True)
+        frame: Frame = Frame('01512', i, 'Dress')
-    # mesh_static = np.load(f'{out_folder}/mesh_static/{frame.id}_{frame.garment}.npy')
+        mesh_posed = readPC2Frame(os.path.join(out_folder, 'mesh_posed_no_orient', f'{frame.id}_{frame.garment}.pc16'), frame.frame_nr, True)
+        # mesh_static = np.load(f'{out_folder}/mesh_static/{frame.id}_{frame.garment}.npy')
 
-    mesh_mask = np.load(f'{out_folder}/mesh_mask/{frame.id}_{frame.garment}.npy')
+        mesh_mask = np.load(f'{out_folder}/mesh_mask/{frame.id}_{frame.garment}.npy')
-    mesh_body_posed = readPC2(os.path.join(out_folder, 'mesh_body_posed_no_orient', f'{frame.id}.pc16'), True)['V']
+        mesh_body_posed = readPC2(os.path.join(out_folder, 'mesh_body_posed_no_orient', f'{frame.id}.pc16'), True)['V']
-    mesh_body_posed = mesh_body_posed[int(mesh_body_posed.shape[0]/2)+frame.frame_nr]
+        mesh_body_posed = mesh_body_posed[::2][frame.frame_nr]
 
-    F = np.load('smpl/smpl_faces_skirt.npy')
+        F = np.load('smpl/smpl_faces_skirt.npy')
-    _, faces = _maskFaces(np.zeros((14475, 3)), F, mesh_mask)
+        _, faces = _maskFaces(np.zeros((14475, 3)), F, mesh_mask)
 
-    fig = go.Figure(data=[go.Mesh3d(x=mesh_posed[:,0], y=mesh_posed[:,2], z=mesh_posed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=1)])
+        fig = go.Figure(data=[go.Mesh3d(x=mesh_posed[:,0], y=mesh_posed[:,2], z=mesh_posed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=1)])
-    fig.add_trace(go.Mesh3d(x=mesh_body_posed[:,0], y=mesh_body_posed[:,2], z=mesh_body_posed[:,1], i=F[:,0], j=F[:,1], k=F[:,2], color='lightblue', opacity=1))
+        fig.add_trace(go.Mesh3d(x=mesh_body_posed[:,0], y=mesh_body_posed[:,2], z=mesh_body_posed[:,1], i=F[:,0], j=F[:,1], k=F[:,2], color='lightblue', opacity=1))
-    fig.update_layout(scene = dict(
+        fig.update_layout(scene = dict(
-        xaxis = dict(range=[-1,1],),
+            xaxis = dict(range=[-1,1],),
-                    yaxis = dict(range=[-1,1],),
+                        yaxis = dict(range=[-1,1],),
-                    zaxis = dict(range=[-1,1],),),)
+                        zaxis = dict(range=[-1,1],),),)
-    fig.update_layout(scene_aspectmode='cube')
+        fig.update_layout(scene_aspectmode='cube')
-    fig.show()
+        fig.show()
     pass
 
 
@@ -734,13 +694,118 @@ def calculate_average(folder, out_folder, frames_file='frames_train_skirt.txt'):
     np.save('custom_data/avg/train_skirt_no_shape_avg_uv.npy', avg_garment)
 
 
+def remove_irregular_poses(folder, folder_reg, out_folder):
+    ids = sorted(os.listdir(folder))
+
+    for id in tqdm(ids):
+
+        garment_dir = os.path.join(folder, id)
+        if not os.path.isdir(garment_dir):
+            continue
+
+        garments = [f.replace('.obj','') for f in os.listdir(garment_dir) if f.endswith('.obj')]
+        info = loadInfo(os.path.join(folder, id, 'info.mat'))
+        
+        for garment in garments:
+       
+            verts_count = readPC2(os.path.join(garment_dir, garment + '.pc16'), True)['V'].shape[0]
+            if info['poses'].shape[1] != verts_count:
+                shutil.rmtree(os.path.join(folder, id))
+                if os.path.exists(os.path.join(out_folder, 'mesh_static', f'{id}_{garment}.pc16')):
+                    os.remove(os.path.join(out_folder, 'mesh_static', f'{id}_{garment}.pc16'))
+                if os.path.exists(os.path.join(out_folder, 'mesh_posed_no_orient', f'{id}_{garment}.pc16')):
+                    os.remove(os.path.join(out_folder, 'mesh_posed_no_orient', f'{id}_{garment}.pc16'))
+                if os.path.exists(os.path.join(out_folder, 'mesh_body_posed_no_orient', f'{id}.pc16')):
+                    os.remove(os.path.join(out_folder, 'mesh_body_posed_no_orient', f'{id}.pc16'))
+                if os.path.exists(os.path.join(out_folder, 'mesh_mask', f'{id}_{garment}.npy')):
+                    os.remove(os.path.join(out_folder, 'mesh_mask', f'{id}_{garment}.npy'))
+                # os.remove(os.path.join(out_folder, 'mesh_unposed_no_shape', f'{id}_{garment}.npy'))
+
+                if len(garments) == 2:
+                    if os.path.exists(os.path.join(out_folder, 'mesh_static', f'{id}_{garments[1]}.pc16')):
+                        os.remove(os.path.join(out_folder, 'mesh_static', f'{id}_{garments[1]}.pc16'))
+                    if os.path.exists(os.path.join(out_folder, 'mesh_posed_no_orient', f'{id}_{garments[1]}.pc16')):
+                        os.remove(os.path.join(out_folder, 'mesh_posed_no_orient', f'{id}_{garments[1]}.pc16'))
+                    if os.path.exists(os.path.join(out_folder, 'mesh_mask', f'{id}_{garments[1]}.pc16')):
+                        os.remove(os.path.join(out_folder, 'mesh_mask', f'{id}_{garments[1]}.npy'))
+                    break
+                    # os.remove(os.path.join(out_folder, 'mesh_unposed_no_shape', f'{id}_{garments[1]}.npy'))
+
+                
+def double_check_irregular_poses(folder, folder_reg, out_folder):
+    # ids = sorted(os.listdir(folder))
+
+    # for id in tqdm(ids):
+
+    #     garment_dir = os.path.join(folder, id)
+    #     if not os.path.isdir(garment_dir):
+    #         continue
+
+    #     garments = [f.replace('.obj','') for f in os.listdir(garment_dir) if f.endswith('.obj')]
+    #     info = loadInfo(os.path.join(folder, id, 'info.mat'))
+        
+    #     for garment in garments:
+    #         body_count = readPC2(os.path.join(out_folder, 'mesh_body_posed_no_orient', f'{id}.pc16'), True)['V'].shape[0]
+    #         verts_count = readPC2(os.path.join(out_folder, 'mesh_posed_no_orient', f'{id}_{garment}.pc16'), True)['V'].shape[0]
+
+    #         assert body_count == verts_count
+
+    frames = sorted(os.listdir(out_folder + '/mesh_posed_no_orient'))
+    frames = [(id.split('_')[0], id.split('_')[1].split('.')[0]) for id in frames]
+
+    for frame in tqdm(frames):
+        id = frame[0]
+        garment_dir = os.path.join(folder, id)
+        if not os.path.isdir(garment_dir):
+            continue
+
+        garment = frame[1]
+        body_count = readPC2(os.path.join(out_folder, 'mesh_body_posed_no_orient', f'{id}.pc16'), True)['V'].shape[0]
+        verts_count = readPC2(os.path.join(out_folder, 'mesh_posed_no_orient', f'{id}_{garment}.pc16'), True)['V'].shape[0]
+
+        assert body_count == verts_count
+
+
+def get_ids():
+    ids = []
+    with open(os.path.join('/data-local/127/cloth3d_processed', 'frames_train.txt'), 'r') as f:
+        for line in f:
+            ids.append(line.split()[0])
+
+    with open(os.path.join('/data-local/127/cloth3d_processed', 'frames_train_skirt.txt'), 'r') as f:
+        for line in f:
+            ids.append(line.split()[0])
+
+    ids = sorted(list(set(ids)))
+
+    with open(os.path.join('/data-local/127/cloth3d_processed', 'frames_train_ids.txt'), 'w') as f:
+        for id in ids:
+            f.write(f'{id}\n')
+
+    ids = []
+    with open(os.path.join('/data-local/127_2/cloth3d_processed_test', 'frames_test.txt'), 'r') as f:
+        for line in f:
+            ids.append(line.split()[0])
+
+    with open(os.path.join('/data-local/127_2/cloth3d_processed_test', 'frames_test_skirt.txt'), 'r') as f:
+        for line in f:
+            ids.append(line.split()[0])
+
+    ids = sorted(list(set(ids)))
+
+    with open(os.path.join('/data-local/127_2/cloth3d_processed_test', 'frames_test_ids.txt'), 'w') as f:
+        for id in ids:
+            f.write(f'{id}\n')
+
+    pass
+
 
 if __name__ == '__main__':
 
 
     # folder = '/data-net/dataset/cloth3d/test'
     # folder_reg = '/data-local/127/cloth3d_registration/test'
-    # out_folder = '/data-local/127/cloth3d_processed_test'
+    # out_folder = '/data-local/127_2/cloth3d_processed_test'
 
     folder = '/data-net/dataset/cloth3d/train'
     folder_reg = '/data-local/127/cloth3d_registration/train'
@@ -754,6 +819,8 @@ if __name__ == '__main__':
     # create_extras_file(folder)
 
     # check_irregular_poses(folder, folder_reg, out_folder)
+    # remove_irregular_poses(folder, folder_reg, out_folder)
+    # double_check_irregular_poses(folder, folder_reg, out_folder)
 
     # create_mesh_posed_no_orient_and_mask(folder, folder_reg, out_folder)
     # verify_registration_ans_mask(folder, out_folder)
@@ -762,9 +829,11 @@ if __name__ == '__main__':
     # create_mesh_body_posed_no_orient(folder, out_folder)
     # create_mesh_normals(folder, out_folder)
     # create_mesh_unposed_no_shape(folder, folder_reg, out_folder, start=args.start, end=args.end)
-    calculate_average(folder, out_folder)
+    # calculate_average(folder, out_folder)
 
     # create_frames_file(folder, out_folder)
+    get_ids()
+    # create_frames_file_test(folder, out_folder)
     # create_frames_file_partial(folder, out_folder, part=0.5)
     
     # folder = '/data-local/127_2/cape_processed/test/female'

losses/losses.py

@@ -4,9 +4,9 @@ import numpy as np
 # import tensorflow_graphics as tfg
 import scipy as sp
 import scipy.io as sio
+from scipy.spatial import KDTree
 
 from pytorch3d.structures import Meshes
-from scipy.spatial import cKDTree
 from torch_cluster import knn
 # from tensorflow_graphics.geometry.representation.mesh.normals import vertex_normals
 # from tensorflow_graphics.geometry.convolution.graph_convolution import edge_convolution_template
@@ -33,15 +33,26 @@ def _nearest_neighbour(V: torch.Tensor, B: torch.Tensor):
     batch_size = V.shape[0]
     vertices_count = V.shape[1]
     batch_x = torch.arange(batch_size, device=V.get_device()).repeat_interleave(V.shape[1])
-    batch_y = torch.arange(batch_size, device=B.get_device()).repeat_interleave(B.shape[1])
     V = V.reshape(-1, V.shape[-1])
     B = B.reshape(-1, B.shape[-1])
-    idx = knn(V, B.to(V.dtype), k=1, batch_x=batch_x, batch_y=batch_y)[1]
+    idx = knn(B.to(V.dtype), V, k=1, batch_x=batch_x, batch_y=batch_x)[1]
     idx = (idx - batch_x * vertices_count).reshape(batch_size, vertices_count)
     return idx
 
+# def _nearest_neighbour(V: torch.Tensor, B: torch.Tensor):
+#     # create an empty tensor to store the indices of the nearest neighbors
+#     batch_size = V.shape[0]
+#     vertices_count = V.shape[1]
+#     idx = torch.zeros((batch_size, vertices_count), dtype=torch.long, device=V.device)
+
+#     # loop over the batch dimension and find the nearest neighbor for each point in B
+#     for i in range(batch_size):
+#         tree = KDTree(B[i].cpu().numpy())
+#         _, nearest = tree.query(V[i].cpu().numpy(), k=1)
+#         idx[i] = torch.from_numpy(nearest)
+
+#     return idx
 
-# @tf.function
 def collision_loss(V: torch.Tensor, B: torch.Tensor, mask: torch.Tensor, thr: float = .004):
     if B.shape[1] == 14475:
         F_norm_local = F_norm

models/pyramid_level.py

@@ -100,7 +100,7 @@ from models.upscaler import Upscaler
 
 class PyramidLevel(nn.Module):
     
-    def __init__(self, config):
+    def __init__(self, config, use_normals=True):
         super(PyramidLevel, self).__init__()
         self.size = config['resolution']
 
@@ -114,6 +114,7 @@ class PyramidLevel(nn.Module):
             load_model(self.upscale_enhancer, config['upscale_enhancer'])
             for param in self.upscale_enhancer.parameters(): param.requires_grad = False
 
+        self.use_normals = use_normals
 
     def enhance(self, low, mask):
         x = self.upscale_enhancer([low, mask])
@@ -152,9 +153,13 @@ class PyramidLevel(nn.Module):
 
 
     def forward(self, inputs, z_cond):
-        uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs
+        uv_unposed, uv_template, uv_body_posed, uv_normals, uv_mask, uv_mask_high = inputs
 
-        x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1)
+        if self.use_normals:
+            x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_normals], dim=1)
+        else:   
+            x = torch.concat([uv_unposed, uv_template, uv_body_posed], dim=1)
+            
         mean, logvar = self.encoder(x)
         z = self.reparameterize(mean, logvar)
         z = torch.reshape(z, (mean.shape[0], -1, 8, 4))

models/pyramid_model.py

@@ -3,133 +3,12 @@ import time
 import random
 import torch
 from torch import nn
-import torch.nn.functional as F
-# import numpy as np
-# import scipy as sp
-# import plotly.graph_objects as go
-# import plotly.express as ex
 
 from utils.checkpoints import load_model
 from models.base import AEEncoder
 from models.pyramid_level import PyramidLevel
-
+from torchvision.transforms import Resize
-
+from torchvision.transforms.functional import InterpolationMode
-# class Pyramid(nn.Module):
-    
-#     def __init__(self, config):
-#         super(Pyramid, self).__init__()
-
-#         self.static_enc : AEEncoder = AEEncoder(config['cond_ae_static']['encoder_block_settings'], kernel_size=config['cond_ae_static']['kernel_size'], activation=config['cond_ae_static']['activation'])
-#         if config['pyramid']['static_model'] != '':
-#             load_model(self.static_enc, config['pyramid']['static_model'] + '_enc')
-
-#         self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['encoder_block_settings'], kernel_size=config['cond_ae_body']['kernel_size'], activation=config['cond_ae_body']['activation'])
-#         if config['pyramid']['body_model'] != '':
-#             load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
-
-#         self.curv_enc : AEEncoder = AEEncoder(config['cond_ae_curv']['encoder_block_settings'], kernel_size=config['cond_ae_curv']['kernel_size'], activation=config['cond_ae_curv']['activation'])
-#         if config['pyramid']['curvature_model'] != '':
-#             load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
-
-#         if config['freeze_encoders']:
-#             for param in self.static_enc.parameters(): param.requires_grad = False
-#             for param in self.body_enc.parameters(): param.requires_grad = False
-#             for param in self.curv_enc.parameters(): param.requires_grad = False
-
-
-#         self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae_static': config['cond_ae_static'], 'cond_ae_body': config['cond_ae_body'], 'cond_ae_curv': config['cond_ae_curv'], } }) for i in range(len(config['pyramid']['levels']))]
-
-#         # if config['is_cape']:
-#         #     if len(config['pyramid']['resolutions']) == 2:
-#         #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #     if len(config['pyramid']['resolutions']) == 3:
-#         #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #         self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #     if len(config['pyramid']['resolutions']) == 4:
-#         #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #         self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #         self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # else:
-
-#         # if len(config['pyramid']['resolutions']) == 2:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # if len(config['pyramid']['resolutions']) == 3:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-#         #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # if len(config['pyramid']['resolutions']) == 4:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-#         #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-#         #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # if len(config['pyramid']['resolutions']) == 5:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)])
-#         #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-#         #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-#         #     self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-
-#         # self.add_noise = config['pyramid']['add_noise']
-#         # self.noise_amount = config['pyramid']['noise_amount']
-#         self.use_offsets = config['use_offsets']
- 
-#         # self.upscale_enhancer = None
-#         # if config['pyramid']['final_upscale_enhancer'] != '':
-#         #     k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-#         #     self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
-#         #     load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-#         #     self.upscale_enhancer.trainable = False
-
-#     def enhance(self, low, mask):
-#         x = self.upscale_enhancer([low, mask])
-#         return x
-
-#     def encode_conds(self, uv_template, uv_body_posed, uv_curv):
-#         z_static = self.static_enc(uv_template)
-#         z_body = self.body_enc(uv_body_posed)
-#         z_curv = self.curv_enc(uv_curv)
-
-#         z_cond = torch.concat([z_static, z_body, z_curv], dim=-1)
-
-#         return z_cond
-
-#     def call(self, inputs):
-#         levels_input, conds = inputs
-#         uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
-
-#         z_cond = self.encode_conds(uv_static, uv_body, uv_curv)
-
-#         # if self.add_noise == True and training == True:
-#         #     z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
-
-#         out_levels = []
-#         pred, mean, logvar = self.levels[0](levels_input[0], z_cond)
-#         if self.use_offsets:
-#             pred = pred + levels_input[0][2] # uv_body_posed_32
-#         if 1 != len(self.levels):
-#             pred = self.levels[0].enhance(pred, levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
-#             pred = F.interpolate(pred, size=(self.levels[1].size, self.levels[1].size//2), mode='bilinear')
-#             out_levels.append([pred, mean, logvar])
-#             pred = pred * levels_input[1][-2][:,None,:,:]
-#         else:
-#             pred = self.enhance(pred, levels_input[0][-2])
-#             pred = F.interpolate(pred, size=(512, 256), mode='bilinear')
-#             pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
-#             out_levels.append([pred, mean, logvar])
-
-#         for i in range(1, len(self.levels)):
-#             pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond)
-#             pred = pred + pred_level
-#             if i != len(self.levels) - 1:
-#                 pred = self.levels[i].enhance(pred, levels_input[i][-2])
-#                 out_levels.append([pred, mean, logvar])
-#                 pred = F.interpolate(pred, size=(self.levels[i+1].size, self.levels[i+1].size//2), mode='bilinear')
-#                 pred = pred * levels_input[i+1][-2][:,None,:,:]
-#             else:
-#                 pred = self.enhance(pred, levels_input[i][-1])
-#                 pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
-#                 pred = F.interpolate(pred, size=(512, 256), mode='bilinear')
-#                 out_levels.append([pred, mean, logvar])
-
-#         return out_levels
-
 
 
 class Pyramid(nn.Module):
@@ -145,65 +24,41 @@ class Pyramid(nn.Module):
         if config['body_model'] != '':
             load_model(self.body_enc, config['body_model'] + '_enc')
 
-        self.curv_enc : AEEncoder = AEEncoder(config['cond_ae_curv']['encoder_block_settings'], kernel_size=config['cond_ae_curv']['kernel_size'], activation=config['cond_ae_curv']['activation'], is_label=True, nr_of_labels=7)
+        if config['use_normals']:
-        if config['curvature_model'] != '':
+            self.norm_enc : AEEncoder = AEEncoder(config['cond_ae_norm']['encoder_block_settings'], config['cond_ae_norm']['kernel_size'], config['cond_ae_norm']['activation'], device=config['device'])
-            load_model(self.curv_enc, config['curvature_model'] + '_enc')
+            if config['normals_model'] != '':
+                load_model(self.norm_enc, config['normals_model'] + '_enc')
 
         if config['freeze_encoders']:
             for param in self.static_enc.parameters(): param.requires_grad = False
             for param in self.body_enc.parameters(): param.requires_grad = False
-            for param in self.curv_enc.parameters(): param.requires_grad = False
+            if config['use_normals']:
+                for param in self.norm_enc.parameters(): param.requires_grad = False
 
-        self.levels = nn.ModuleList([PyramidLevel({ **config['pyramid']['levels'][i] }) for i in range(len(config['pyramid']['levels']))])
+        self.levels = nn.ModuleList([PyramidLevel({ **config['pyramid']['levels'][i] }, use_normals=config['use_normals']) for i in range(len(config['pyramid']['levels']))])
 
+        self.resizers = { res: Resize(size=(res, int(res/2)), interpolation=InterpolationMode.BILINEAR).to(config['device']) for res in config['pyramid']['resolutions'] }
+        self.resizers[512] = Resize(size=(512, 256), interpolation=InterpolationMode.BILINEAR).to(config['device'])
 
-        # if len(config['pyramid']['resolutions']) == 2:
+        self.use_normals = config['use_normals']
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 3:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 4:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 5:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
 
-        # self.add_noise = config['pyramid']['add_noise']
+    def encode_conds(self, uv_template, uv_body_posed, uv_norm):
-        # self.noise_amount = config['pyramid']['noise_amount']
-        # self.use_offsets = config['use_offsets']
- 
-        # self.upscale_enhancer = None
-        # if config['pyramid']['final_upscale_enhancer'] != '':
-        #     k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-        #     self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
-        #     load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-        #     self.upscale_enhancer.trainable = False
-
-    # def enhance(self, low, mask, training):
-    #     x = self.upscale_enhancer([low, mask], training=training)
-    #     return x
-
-    def encode_conds(self, uv_template, uv_body_posed, uv_curv):
         z_static = self.static_enc(uv_template)
         z_body = self.body_enc(uv_body_posed)
-        z_curv = self.curv_enc(uv_curv)
 
-        z_cond = torch.concat([z_static, z_body, z_curv], dim=1)
+        if self.use_normals:
+            z_norm = self.norm_enc(uv_norm)
+            z_cond = torch.concat([z_static, z_body, z_norm], dim=1)
+        else:
+            z_cond = torch.concat([z_static, z_body], dim=1)
 
         return z_cond
 
     def forward(self, inputs):
         levels_input, conds = inputs
-        uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
+        uv_static, uv_body, uv_norm = conds[0], conds[1], conds[2]
 
-        z_cond = self.encode_conds(uv_static, uv_body, uv_curv)
+        z_cond = self.encode_conds(uv_static, uv_body, uv_norm)
-
-        # if self.add_noise == True and training == True:
-        #     z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
 
         out_levels = []
         pred, mean, logvar = self.levels[0](levels_input[0], z_cond)
@@ -211,35 +66,28 @@ class Pyramid(nn.Module):
         #     pred = pred + levels_input[0][2] # uv_body_posed_32
         if 1 != len(self.levels):
             pred = self.levels[0].enhance(pred, levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
-            pred = F.interpolate(pred, size=(self.levels[1].size, self.levels[1].size//2), mode='bilinear')
+            pred = self.resizers[self.levels[1].size](pred)
             out_levels.append([pred, mean, logvar])
             pred = pred * levels_input[1][-2][:,None,:,:]
         else:
-            # pred = self.enhance(pred, levels_input[0][-2], training=training)
             pred = self.levels[0].enhance(pred, levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
-            pred = F.interpolate(pred, size=(512, 256), mode='bilinear') 
+            pred = self.resizers[512](pred)
             pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
             out_levels.append([pred, mean, logvar])
 
         for i in range(1, len(self.levels)):
             input = levels_input[i]
-            # input[0] = input[0] - pred
+            input[0] = input[0] - pred
-            # input_min, input_max = tf.reduce_min(input[0], axis=[1,2,3]), tf.reduce_max(input[0], axis=[1,2,3])
-            # input[0] = (input[0] - input_min[:,None,None,None]) / (input_max - input_min)[:,None,None,None]
-            # input[0] = input[0] * input[-2][:,None,:,:] # uv_mask_res
             pred_level, mean, logvar = self.levels[i](input, z_cond)
-            # pred_level = ( (pred_level * (input_max - input_min)[:,None,None,None]) + input_min[:,None,None,None] ) * input[-2][:,:,:,None] # uv_mask_res
             pred = pred + pred_level
             if i != len(self.levels) - 1:
                 pred = self.levels[i].enhance(pred, levels_input[i][-2])
                 out_levels.append([pred, mean, logvar])
-                pred = F.interpolate(pred, size=(self.levels[i+1].size, self.levels[i+1].size//2), mode='bilinear')
+                pred = self.resizers[self.levels[i+1].size](pred)
                 pred = pred * levels_input[i+1][-2][:,None,:,:]
             else:
-                # if self.upscale_enhancer is not None:
-                    # pred = self.enhance(pred, levels_input[-1][-2], training=training)
                 pred = self.levels[-1].enhance(pred, levels_input[-1][-2])
-                pred = F.interpolate(pred, size=(512, 256), mode='bilinear')
+                pred = self.resizers[512](pred)
                 pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
                 out_levels.append([pred, mean, logvar])
 

scripts/cvae.py

@@ -10,9 +10,8 @@ parser.add_argument('--config', type=str)
 parser.add_argument('--debug', action='store_true')
 args = vars(parser.parse_args())
 
-
 if args['debug']:
-    from configs.iccvw.abl_all import config
+    from configs.iccvw.abl_all_4 import config
 else:
     config_module = importlib.import_module(args['config'])
     config = config_module.config
@@ -40,6 +39,7 @@ else:
 import torch
 import torch.nn as nn
 import torch.optim as optim
+from torch.profiler import profile, record_function, ProfilerActivity
 from data.dataset import Dataset
 from models.cond_encoder import AutoEncoder
 from utils.checkpoints import CheckpointSaver, load_model
@@ -82,11 +82,13 @@ def kl_loss(mean: torch.Tensor, logvar: torch.Tensor) -> torch.Tensor:
 
 
 def train_step(batch):
+    # with profiler:
     if config['use_skinning']:
         mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
+    # with record_function("forward"):
     model.train()
     pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_normals'], batch['uv_mask']])
     mesh_pred = uv2mesh(pred)
@@ -115,20 +117,26 @@ def train_step(batch):
     if config['use_extra_losses']:
         reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss + n_loss) * config['reg_loss_coeff']
 
-    loss = reconstr_loss + g_balancing_coeff * kl
+    loss =  g_balancing_coeff * kl + reconstr_loss
 
+    # with record_function("backward"):
     optimizer.zero_grad()
     loss.backward()
     optimizer.step()
 
+    # with record_function("eval"):
     model.eval()
     with torch.inference_mode():
         mean = torch.mean(mean)
         logvar = torch.mean(logvar)
         ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1))
         metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
-    
+
-    return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
+    # profiler.step()
+
+
+    return { 'train/loss': loss, 
+             'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
              'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio,
              'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
              'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
@@ -253,8 +261,8 @@ def plot_everything(batch: dict, type: str):
     collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(garment_posed))]
     collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(garment_posed))]
 
-    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
+    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'])) 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], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) 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], flip_xy=(not config['use_skinning'])) for i in range(4) }
 
     mean_hist = wandb.Histogram(sequence=mean.cpu().numpy().mean(axis=0))
     logvar_hist = wandb.Histogram(sequence=logvar.cpu().numpy().mean(axis=0))
@@ -466,15 +474,16 @@ def train():
             valid_accumulator.reset()
             print(step)
 
-        if train_loss['train/euclid_error'] < config['balancing_activation_limit']:
+        # if train_loss['train/euclid_error'] < config['balancing_activation_limit']:
-            g_balancing_coeff += 1 / 10000 
+        #     g_balancing_coeff += 1 / 10000 
 
-        if step % 25000 == 0:
+        if step % 25000 == 0 and not args['debug']:
             ckpt_saver(model, step, optimizer, None)
 
         step += 1
 
 
+
 if __name__ == '__main__':
     if not args['debug']:
         init_wandb()
@@ -500,10 +509,22 @@ if __name__ == '__main__':
 
     step = 0
     if config['pretrained_model'] != '':
-        step = load_model(model, config['pretrained_model'])
+        step = load_model(model, config['pretrained_model'], optimizer)
 
     if not args['debug']:
         # model = torch.compile(model)
         wandb.watch(model, log='all', log_freq=10000, log_graph=True)
 
-    train()
+    # create a profiler object
+    # profiler = torch.profiler.profile(
+    #     activities=[ProfilerActivity.CPU],
+    #     schedule=torch.profiler.schedule(wait=2, warmup=1, active=3, repeat=2),
+    #     on_trace_ready=torch.profiler.tensorboard_trace_handler("log_dir"),
+    # )
+
+# with profiler:
+#     with record_function("model_inference"):
+    train()
+
+    # profiler.stop()
+    # print(profiler.key_averages().table(sort_by="cpu_time_total", row_limit=25))

scripts/cvae_pyramid.py

@@ -10,11 +10,12 @@ parser.add_argument('--config', type=str)
 parser.add_argument('--debug', action='store_true')
 args = vars(parser.parse_args())
 
-config_module = importlib.import_module(args['config'])
-config = config_module.config
 if args['debug']:
-    from configs.pyr_32 import config
+    from configs.iccvw.pyr_64_reg import config
-    # from configs.pyr_64_cape_m import config
+else:
+    config_module = importlib.import_module(args['config'])
+    config = config_module.config
+
 os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 if args['debug']:
@@ -42,6 +43,7 @@ import torch.nn.functional as F
 from data.dataset import Dataset
 from utils.checkpoints import CheckpointSaver, load_model
 from utils.utils import InfiniteDataLoader as DataLoader
+from utils.utils import text_to_html
 from utils.postprocess import fix_collision
 from losses.losses import collision_loss, normal_loss, kl_loss
 from pytorch_msssim import MS_SSIM
@@ -52,7 +54,8 @@ from models.pyramid_model import Pyramid
 
 
 def init_wandb():
-    run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags'])
+    wandb.login(host='https://wandb2.lnrweb.com', key='local-2a78b434e9bc51e9f12625f8321a9e3ee34af16d', relogin=True, force=True)
+    run = wandb.init(project='iccvw', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('scripts/cvae_pyramid.py')
     artifact.add_file('losses/losses.py')
@@ -99,8 +102,8 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col
 
     fig.add_trace(go.Mesh3d(
             x=mesh_posed[:,0],
-            y=mesh_posed[:,1],
+            y=mesh_posed[:,2],
-            z=mesh_posed[:,2],
+            z=mesh_posed[:,1],
             i = faces[:,0],
             j = faces[:,1],
             k = faces[:,2],
@@ -235,47 +238,40 @@ def train_step(batch):
     res_modifier = '_' + str(res) if res != 512 else ''
     pred, mean, logvar = out_levels[i]
 
-    mesh_pred = uv2mesh(pred)
 
-    if config['use_skinning']:
-        shape = batch['pose_shape'][:, 72:]
-        gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
-        shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
 
-        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
-        mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
-    else:
-        mesh_pred_posed = mesh_pred
-
-    # is the output already masked?
-    # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-
-    e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
-    c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
-    c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
     l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2]))
-    l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
-    n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
     kl = kl_loss(mean, logvar)
 
     if config['use_extra_losses']:
+        mesh_pred = uv2mesh(pred)
+
+        if config['use_skinning']:
+            shape = batch['pose_shape'][:, 72:]
+            gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
+            shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
+
+            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
+            mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+        else:
+            mesh_pred_posed = mesh_pred
+
+        e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+        c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+        c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
+        n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+        l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
+        
         reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
         if not config['is_cape']:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+            if config['use_norm_loss'] and step > 2000:
+                reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
     else:
         reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
-
-    if config['use_norm_loss'] and step > 2000:
-        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
     
     kl_total += kl
-    loss = reconstr_loss_total + g_balancing_coeff * kl_total
+    loss: torch.Tensor = reconstr_loss_total + g_balancing_coeff * kl_total
-
-    # scaler.scale(loss).backward()
-    # scaler.step(optimizer)
-    # scaler.update()
-    # optimizer.zero_grad()
 
     optimizer.zero_grad()
     loss.backward()
@@ -286,13 +282,33 @@ def train_step(batch):
         mean = torch.mean(mean)
         logvar = torch.mean(logvar)
 
+        if not config['use_extra_losses']:
+            mesh_pred = uv2mesh(pred)
+
+            if config['use_skinning']:
+                shape = batch['pose_shape'][:, 72:]
+                gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
+                shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
+
+                mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
+                mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+            else:
+                mesh_pred_posed = mesh_pred
+                
+            e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+            c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+            c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
+            l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
+            n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+        
         ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1))
         metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
 
     output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
                                 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
                                 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss,
-                                'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss, 'train/ms_ssim' + res_modifier: ms_ssim, } } # 
+                                'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss, 'train/ms_ssim' + res_modifier: ms_ssim,
+                                'train/collision_ratio': c_ratio } } # 
 
 
     return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
@@ -332,28 +348,24 @@ def valid_step(batch):
         else:
             mesh_pred_posed = mesh_pred
 
-        # is the output already masked?
-        # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-        # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-
         e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
         c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
         l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2]))
         l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
         n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+       
         kl = kl_loss(mean, logvar)
 
         if config['use_extra_losses']:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
             if not config['is_cape']:
                 reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+                if config['use_norm_loss'] and step > 2000:
+                    reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         else:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
 
-        if config['use_norm_loss'] and step > 2000:
-            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
-        
         kl_total += kl
         loss = reconstr_loss_total + g_balancing_coeff * kl_total
 
@@ -452,12 +464,12 @@ def plot_everything(batch: dict, type: str):
     orig_img = (torch.permute(uv_orig, [0,2,3,1]) + 1) / 2
     uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2
     uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2
-    uv_curvature = (torch.tile(torch.argmax(torch.permute(batch['uv_curvature'], [0,2,3,1]), dim=-1)[:,:,:,None], [1,1,1,3]) / 6)
+    uv_normals = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.4) / 2.8
-    pred_img = torch.concatenate([torch.permute(F.interpolate(output_levels[i][0], size=(512, 256), mode='bilinear'), [0,2,3,1]) for i in range(len(output_levels))], dim=3)
+    pred_img = torch.concatenate([torch.permute(model.resizers[512](output_levels[i][0]), [0,2,3,1]) for i in range(len(output_levels))], dim=3)
     # 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])
     pred_img = (pred_img - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) / (pred_img.flatten().reshape(pred_img.shape[0], -1).max(1)[0][:,None,None,None] - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None])
 
-    img = torch.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2)
+    img = torch.concat((uv_static_img, uv_body_posed_img, uv_normals, orig_img, pred_img), axis=2)
     imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)]
 
     _F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
@@ -521,7 +533,14 @@ def plot_everything(batch: dict, type: str):
         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) }
 
-    return { **figs, **figs_coll, **{ type + '/images': imgs, } }
+    batch_id = batch['id']
+    batch_frame_nr = batch['frame_nr']
+    batch_garment = batch['garment']
+    batch_info = [f'batch_info: id: {batch_id[i]}, frame_nr: {batch_frame_nr[i]}, garment: {batch_garment[i]}' for i in range(len(batch_id))]
+    batch_info = text_to_html(batch_info)
+    batch_info = wandb.Html(batch_info)
+
+    return { **figs, **figs_coll, **{ type + '/images': imgs, }, **{ f'{type}/batch_info': batch_info }, }
 
 
 def sample(folder):
@@ -791,9 +810,9 @@ def train():
             print(step)
 
         if train_loss['train/euclid_error'] < config['balancing_activation_limit']:
-            g_balancing_coeff += 1 / 10000 
+            g_balancing_coeff += 1 / 50000 
 
-        if step % 10000 == 0:
+        if step % 25000 == 0 and not args['debug']:
             ckpt_saver(model, step, optimizer, None)
 
         step += 1
@@ -821,7 +840,7 @@ if __name__ == '__main__':
 
     optimizer = optim.Adam(model.parameters(), lr=config['lr'])
     _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
-    ckpt_saver = CheckpointSaver('checkpoints/iccv/torch/' + config['name'], top_n=5)
+    ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=5)
     scaler = torch.cuda.amp.GradScaler(enabled=use_amp)
 
     g_balancing_coeff = config['starting_balancing_coeff']
@@ -840,12 +859,14 @@ if __name__ == '__main__':
     if len(config['pyramid']['resolutions']) == 1:
         for param in model.static_enc.parameters(): param.requires_grad = False
         for param in model.body_enc.parameters(): param.requires_grad = False
-        for param in model.curv_enc.parameters(): param.requires_grad = False
+        if config['use_normals']:
+            for param in model.norm_enc.parameters(): param.requires_grad = False
     else:
-        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
+        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=config['pyramid']['pretrained_pyramid_iteration'])
         for param in model.static_enc.parameters(): param.requires_grad = False
         for param in model.body_enc.parameters(): param.requires_grad = False
-        for param in model.curv_enc.parameters(): param.requires_grad = False
+        if config['use_normals']:
+            for param in model.norm_enc.parameters(): param.requires_grad = False
 
     # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
     # model.levels[0].upscale_enhancer.trainable = False
@@ -866,6 +887,6 @@ if __name__ == '__main__':
 
     if not args['debug']:
         # model = torch.compile(model)
-        wandb.watch(model, log='all', log_freq=1000, log_graph=True)
+        wandb.watch(model, log='all', log_freq=10000, log_graph=True)
 
     train()

scripts/generate_results.py

@@ -0,0 +1,148 @@
+import os
+import sys
+sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
+
+import importlib
+import argparse
+parser = argparse.ArgumentParser(description='')
+parser.add_argument('--name', type=str)
+parser.add_argument('--config', type=str)
+parser.add_argument('--debug', action='store_true')
+args = vars(parser.parse_args())
+
+if args['debug']:
+    from configs.iccvw.pyr_64 import config
+else:
+    config_module = importlib.import_module(args['config'])
+    config = config_module.config
+
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
+if args['debug']:
+    os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
+
+import time
+import argparse
+import wandb
+import tqdm
+import random
+import numpy as np
+import plotly.graph_objects as go
+import plotly.express as ex
+from PIL import Image
+
+
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.nn.functional as F
+from tqdm import tqdm
+from data.dataset import Dataset
+from utils.checkpoints import CheckpointSaver, load_model
+from torch.utils.data import DataLoader
+from utils.utils import text_to_html
+from utils.postprocess import fix_collision
+from losses.losses import collision_loss, normal_loss, kl_loss
+from pytorch_msssim import MS_SSIM
+from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels
+from smpl.smpl_torch import SMPL
+from plotly.subplots import make_subplots
+from models.pyramid_model import Pyramid
+from models.cvae_model import CVAE
+
+
+uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+
+
+def step_pyramid(batch):
+    model.eval()
+    with torch.inference_mode():
+        levels_input, conds = group_inputs_for_levels(batch, config)
+
+        out_levels = model([levels_input, conds])
+        pred, _, _ = out_levels[-1]
+
+        mesh_pred = uv2mesh(pred)
+
+        if config['use_skinning']:
+            shape = batch['pose_shape'][:, 72:]
+            gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
+            shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
+
+            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
+            mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+        else:
+            mesh_pred_posed = mesh_pred
+
+    return mesh_pred_posed
+
+
+def step(batch):
+    if config['use_skinning']:
+        uv_orig = batch['uv_unposed']
+    else:
+        uv_orig = batch['uv_posed']
+
+    model.eval()
+    pred, _, _ = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_normals'], batch['uv_mask']])
+    mesh_pred = uv2mesh(pred)
+
+    if config['use_skinning']:
+        shape = batch['pose_shape'][:, 72:]
+        gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long)
+        shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
+
+        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
+        mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+    else:
+        mesh_pred_posed = mesh_pred
+
+    return mesh_pred_posed
+
+
+def generate():
+    for batch in tqdm(test_dataloader):
+        if is_pyramid:
+            mesh_pred = step_pyramid(batch)
+        else: 
+            mesh_pred = step(batch)
+
+        ids = batch['id']
+        frame_nrs = batch['frame_nr']
+        garments = batch['garment']
+
+        for i in range(len(ids)):
+            np.savez_compressed(f'{out_folder}/{ids[i]}_{frame_nrs[i]}_{garments[i]}', mesh_pred[i].cpu().numpy())
+
+
+
+
+if __name__ == '__main__':
+
+    smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
+    skirt_modifier = '_skirt' if config['is_skirt'] else ''
+    dataset_resolutions = config['pyramid']['resolutions'].copy()
+    if 512 not in dataset_resolutions:
+        dataset_resolutions.append(512)
+
+    dataset_test = Dataset(config['test_dir'], config['signature'], device=config['device'], frames_file=config['test_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
+    test_dataloader = DataLoader(dataset_test, batch_size=4, drop_last=True, shuffle=True, )
+
+    is_pyramid = config['name'].startswith('pyr')
+
+    if is_pyramid:
+        model: Pyramid = Pyramid(config)
+    else:
+        model: CVAE = CVAE(config)
+
+    it = load_model(model, 'checkpoints/iccv/torch/' + config['name'])
+    # it = load_model(model, 'checkpoints/iccvw/' + config['name'])
+
+    name = config['name'] + '_' + str(it)
+
+    folder = '/data-local/127_2/results'
+    out_folder = f'{folder}/{name}'
+
+    os.makedirs(out_folder, exist_ok=True)
+
+    generate()

smpl/smpl_torch.py

@@ -10,7 +10,7 @@ from time import time
 from torch.nn import Module
 
 class SMPL(Module):
-  def __init__(self, device=None, path='', orig_smpl=False, is_skirt=False):
+  def __init__(self, device=None, path='', orig_smpl=False, is_skirt=False, batch_size=4):
     
     super(SMPL, self).__init__()
     self.J_regressor = []
@@ -56,6 +56,14 @@ class SMPL(Module):
     
     self.shape = (1,27578,3)
     self.device = device
+    self.batch_size = batch_size
+
+    self.with_zeros_ones = torch.tensor(
+        [[[0.0, 0.0, 0.0, 1.0]]], dtype=torch.float32
+      ).expand(self.batch_size,-1,-1).to(self.device)
+    self.results_zeros = torch.zeros((self.batch_size, 24, 1), dtype=torch.float32).to(self.device)
+    self.J_ones = torch.ones((self.batch_size, 24, 1), dtype=torch.float32, device=self.device)
+    self.rest_shape_h_ones_full = torch.ones((self.batch_size, self.weights_all.shape[1], 1), dtype=torch.float32).to(self.device)
 
     if orig_smpl:
         self.to_keep = self.to_keep[self.to_keep < 6890]
@@ -67,6 +75,8 @@ class SMPL(Module):
         self.weights = self.weights_all[:,self.to_keep,:]
         self.shape = (1, 6890, 3)
 
+    self.rest_shape_h_ones = torch.ones((self.batch_size, self.to_keep.shape[0], 1), dtype=torch.float32).to(self.device)
+
   @staticmethod
   def rodrigues(r):
     """
@@ -91,7 +101,7 @@ class SMPL(Module):
     m = torch.stack(
       (z_stick, -r_hat[:, 0, 2], r_hat[:, 0, 1], r_hat[:, 0, 2], z_stick,
        -r_hat[:, 0, 0], -r_hat[:, 0, 1], r_hat[:, 0, 0], z_stick), dim=1)
-    m = torch.reshape(m, (-1, 3, 3))
+    m = m.view((-1, 3, 3))
     i_cube = (torch.eye(3, dtype=torch.float32).unsqueeze(dim=0) \
              + torch.zeros((theta_dim, 3, 3), dtype=torch.float32)).to(r.device)
     A = r_hat.permute(0, 2, 1)
@@ -112,8 +122,8 @@ class SMPL(Module):
     Tensor after appending of shape [4,4]
     """
     ones = torch.tensor(
-      [[[0.0, 0.0, 0.0, 1.0]]], dtype=torch.float32
+        [[[0.0, 0.0, 0.0, 1.0]]], dtype=torch.float32
-    ).expand(x.shape[0],-1,-1).to(x.device)
+      ).expand(x.shape[0],-1,-1).to(x.device)
     ret = torch.cat((x, ones), dim=1)
     return ret
 
@@ -158,8 +168,8 @@ class SMPL(Module):
 
     # v_shaped = torch.tensordot(betas, self.shapedirs, dims=([1], [2])) + self.v_template
     v_shaped = []
-    v_shaped.append(torch.tensordot(betas[:,:10], self.shapedirs[0], dims=[[1], [2]]) + torch.reshape(self.v_template[0], shape=self.shape)) # female
+    v_shaped.append(torch.tensordot(betas[:,:10], self.shapedirs[0], dims=[[1], [2]]) + self.v_template[0].view(self.shape)) # female
-    v_shaped.append(torch.tensordot(betas[:,:10], self.shapedirs[1], dims=[[1], [2]]) + torch.reshape(self.v_template[1], shape=self.shape)) # male
+    v_shaped.append(torch.tensordot(betas[:,:10], self.shapedirs[1], dims=[[1], [2]]) + self.v_template[1].view(self.shape)) # male
     v_shaped = torch.stack(v_shaped, axis=-1)
     
     # J = torch.matmul(self.J_regressor, v_shaped)
@@ -167,7 +177,7 @@ class SMPL(Module):
       J = torch.stack([torch.matmul(self.J_regressor[g.to(torch.long)], v_shaped[i, :, :, g.to(torch.long)]) for i, g in enumerate(betas[:,-1])])
     else:
       J = torch.stack([torch.matmul(self.J_regressor[torch.greater(g, 0.5).to(torch.long)], v_shaped[i, :, :, torch.greater(g, 0.5).to(torch.long)]) for i, g in enumerate(betas[:,-1])])
-      J0 = torch.reshape(J[:,0,:], (-1, 1, 3))
+      J0 = J[:,0,:].view((-1, 1, 3))
       J = J - J0
     R_cube_big = self.rodrigues(pose.reshape(-1, 1, 3)).reshape(batch_num, -1, 3, 3)
 
@@ -177,12 +187,12 @@ class SMPL(Module):
       R_cube = R_cube_big[:, 1:, :, :]
       I_cube = (torch.eye(3, dtype=torch.float32).unsqueeze(dim=0) + \
         torch.zeros((batch_num, R_cube.shape[1], 3, 3), dtype=torch.float32)).to(self.device)
-      lrotmin = (R_cube - I_cube).reshape(batch_num, -1, 1).squeeze(dim=2)
+      lrotmin = (R_cube - I_cube).view(batch_num, -1, 1).squeeze(dim=2)
       v_posed = torch.stack([v_shaped[i, :, :, torch.greater(g, 0.5).to(torch.long)] + torch.tensordot(lrotmin[i], self.posedirs[torch.greater(g, 0.5).to(torch.long)], dims=([0], [2])) for i, g in enumerate(betas[:,-1])])
 
     results = []
     results.append(
-      self.with_zeros(torch.cat((R_cube_big[:, 0], torch.reshape(J[:, 0, :], (-1, 3, 1))), dim=2))
+      self.with_zeros(torch.cat((R_cube_big[:, 0], J[:, 0, :].view((-1, 3, 1))), dim=2))
     )
     for i in range(1, 24):
       results.append(
@@ -190,7 +200,7 @@ class SMPL(Module):
           results[self.parent[i]],
           self.with_zeros(
             torch.cat(
-              (R_cube_big[:, i], torch.reshape(J[:, i, :] - J[:, self.parent[i], :], (-1, 3, 1))),
+              (R_cube_big[:, i], (J[:, i, :] - J[:, self.parent[i], :]).view((-1, 3, 1))),
               dim=2
             )
           )
@@ -202,25 +212,25 @@ class SMPL(Module):
       self.pack(
         torch.matmul(
           stacked,
-          torch.reshape(
+            torch.cat((J, self.results_zeros), dim=2).view(
-            torch.cat((J, torch.zeros((batch_num, 24, 1), dtype=torch.float32).to(self.device)), dim=2),
             (batch_num, 24, 4, 1)
           )
         )
       )
     
-    joints = torch.matmul(results, torch.transpose(torch.concat([J, torch.ones((J.shape[0], 24, 1), dtype=torch.float32, device=J.get_device())], axis=-1)[:,:,None,:],2,3))[:,:,:3,0]
+    joints = torch.matmul(results, torch.transpose(torch.concat([J, self.J_ones], axis=-1)[:,:,None,:],2,3))[:,:,:3,0]
             
     weights = self.weights if verts is not None else self.weights_all 
+    rest_shape_h_ones_local = self.rest_shape_h_ones if verts is not None else self.rest_shape_h_ones_full
     T = torch.stack([torch.tensordot(results[i], weights[torch.greater(g, 0.5).to(torch.long)], dims=([0], [1])).permute(2, 0, 1) for i, g in enumerate(betas[:,-1])]) 
     rest_shape_h = torch.cat(
-      (v_posed, torch.ones((batch_num, v_posed.shape[1], 1), dtype=torch.float32).to(self.device)), dim=2
+      (v_posed, rest_shape_h_ones_local), dim=2
     )
-    v = torch.matmul(T, torch.reshape(rest_shape_h, (batch_num, -1, 4, 1)))
+    v = torch.matmul(T, rest_shape_h.view((batch_num, -1, 4, 1)))
-    v = torch.reshape(v, (batch_num, -1, 4))[:, :, :3]
+    v = v.view((batch_num, -1, 4))[:, :, :3]
     result = v
 
-    root_joint = torch.reshape(joints[:,0,:], (-1, 1, 3))
+    root_joint = joints[:,0,:].view((-1, 1, 3))
     result = result - root_joint
     joints = joints - root_joint
 

utils/checkpoints.py

@@ -34,11 +34,13 @@ class CheckpointSaver:
 def load_model(model: torch.nn.Module, checkpoint, optimizer: torch.nn.Module=None, scaler: torch.nn.Module=None, iteration=''):
     # list of checkpoint files in the folder checkpoints
     checkpoints = [os.path.join(checkpoint, f) for f in os.listdir(checkpoint) if f.endswith(f'{iteration}.pt')]
-    checkpoint = torch.load(checkpoints[-1])
+    iterations = np.asarray([int(f.split('_')[-1].split('.')[0]) for f in checkpoints])
-    iteration = checkpoints[-1].split('_')[-1].split('.')[0]
+    last_iteration = np.argmax(iterations)
+    checkpoint = torch.load(checkpoints[last_iteration])
+    iteration = iterations[last_iteration]
     model.load_state_dict(checkpoint['model'])
     if optimizer is not None: optimizer.load_state_dict(checkpoint['optimizer'].state_dict())
     if scaler is not None and checkpoint['scaler'] is not None: scaler.load_state_dict(checkpoint['scaler'])
-    print(f'Loaded model from {checkpoints[-1]} at iteration {iteration}')
+    print(f'Loaded model from {checkpoints[last_iteration]} at iteration {iteration}')
     return int(iteration) if iteration != '' else 0
 

utils/generate_figures.py

@@ -3,33 +3,19 @@ import sys
 sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
 
 import numpy as np
+import cmapy as cm
+
+from utils import remove_long_edges
 
 from custom_utils.custom_utils import save_stl, write_obj
 from data.cloth3d_io import readPC2Frame
 from data.utils import Frame
 from custom_utils.custom_utils import _maskFaces
 import plotly.graph_objects as go
+import plotly.express as ex
 from plotly.subplots import make_subplots
 
 
-def remove_long_edges(vertices, faces):
-    # Compute edge lengths
-    edges = np.vstack((faces[:,[0,1]], faces[:,[1,2]], faces[:,[2,0]]))
-    edge_lengths = np.linalg.norm(vertices[edges[:,0]] - vertices[edges[:,1]], axis=1)
-
-    # Find edges longer than 0.1
-    long_edges = edges[edge_lengths > 0.1]
-
-    # Find vertices that are part of long edges
-    vertices_to_remove = np.unique(long_edges)
-
-    # Remove vertices and update faces
-    mask = np.ones(vertices.shape[0], dtype=bool)
-    mask[vertices_to_remove] = False
-    new_vertices = vertices[mask]
-
-
-    return new_vertices, mask
 
 
 def plot_unposing_example():
@@ -87,7 +73,7 @@ def plot_normals_example():
     # mesh_unposed = readPC2Frame(os.path.join(folder_test, 'mesh_unposed_no_shape', f'{frame.id}_{frame.garment}.pc16'), frame.frame_nr, True)
     # mesh_unposed_shaped = readPC2Frame(os.path.join('temp', f'{frame.id}_{frame.garment}_unposed_shaped.pc16'), frame.frame_nr, True)[mesh_mask]
     mesh_normals = readPC2Frame(os.path.join(folder_test, 'mesh_normals', f'{frame.id}_{frame.garment}.pc16'), frame.frame_nr, True)
-    uv_normals = np.load(os.path.join(folder_test, 'uv_normals', f'{frame.id}_{frame.frame_nr}_{frame.garment}.npz'))
+    uv_normals = np.load(os.path.join(folder_test, 'uv_normals', f'{frame.id}_{frame.frame_nr}_{frame.garment}.npz'))['uv_normals']
 
     F = np.load('smpl/smpl_faces.npy')
     _, faces = _maskFaces(np.zeros((14475, 3)), F, mesh_mask)
@@ -101,12 +87,13 @@ def plot_normals_example():
     new_mask[mesh_mask] = v_mask
     _, faces = _maskFaces(np.zeros((14475, 3)), F, new_mask)
 
-    fig = make_subplots(rows=1, cols=4, specs=[[{'type': 'mesh3d'}, {'type': 'mesh3d'}, {'type': 'mesh3d'}, {'type': 'mesh3d'}]])
+    v_colors = (mesh_normals + 1.4) / 2.8
+    v_colors = v_colors[v_mask]
+    # v_colors = (v_colors - v_colors.min()) / (v_colors.max() - v_colors.min())
 
-    fig.add_trace(go.Mesh3d(x=mesh_static[:,0], y=mesh_static[:,2], z=mesh_static[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=1), row=1, col=1)
+    fig = go.Figure()
-    fig.add_trace(go.Mesh3d(x=mesh_posed[:,0], y=mesh_posed[:,2], z=mesh_posed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightblue', opacity=1), row=1, col=2)
+
-    fig.add_trace(go.Mesh3d(x=mesh_unposed_shaped[:,0], y=mesh_unposed_shaped[:,2], z=mesh_unposed_shaped[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightgreen', opacity=1), row=1, col=3)
+    fig.add_trace(go.Mesh3d(x=mesh_posed[:,0], y=mesh_posed[:,2], z=mesh_posed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], vertexcolor=v_colors, opacity=1),)
-    fig.add_trace(go.Mesh3d(x=mesh_unposed[:,0], y=mesh_unposed[:,2], z=mesh_unposed[:,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightyellow', opacity=1), row=1, col=4)
 
     fig.update_layout(scene=dict(
         xaxis=dict(range=[-1, 1]),
@@ -114,11 +101,29 @@ def plot_normals_example():
         zaxis=dict(range=[-1, 1]),
     ), scene_aspectmode='cube')
 
+    helper = dict(xaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
+                yaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
+                zaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),)
+    fig.update_layout(scene = helper)
+    
+    # fig.show()
+
+    uv_normals = (uv_normals + 1.4) / 2.8
+    uv_normals = np.concatenate((uv_normals[:256], uv_normals[256:]), axis=1)
+    # flip uv_normals along y axis
+    uv_normals = uv_normals[:,::-1,:]
+    ex.imshow(uv_normals).show()
+
+
+    
+
+    pass
+
 
 
 if __name__ == '__main__':
     folder_train = '/data-local/127/cloth3d_processed'
-    folder_test = '/data-local/127/cloth3d_processed_test'
+    folder_test = '/data-local/127_2/cloth3d_processed_test'
     
     # plot_unposing_example()
     plot_normals_example()