add uv normal example

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/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_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'

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/preprocessing.py

@@ -766,16 +766,50 @@ def double_check_irregular_poses(folder, folder_reg, out_folder):
         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 = '/data-net/dataset/cloth3d/test'
-    folder_reg = '/data-local/127/cloth3d_registration/test'
+    # folder_reg = '/data-local/127/cloth3d_registration/test'
-    out_folder = '/data-local/127_2/cloth3d_processed_test'
+    # out_folder = '/data-local/127_2/cloth3d_processed_test'
 
-    # folder = '/data-net/dataset/cloth3d/train'
+    folder = '/data-net/dataset/cloth3d/train'
-    # folder_reg = '/data-local/127/cloth3d_registration/train'
+    folder_reg = '/data-local/127/cloth3d_registration/train'
-    # out_folder = '/data-local/127/cloth3d_processed'
+    out_folder = '/data-local/127/cloth3d_processed'
 
     smpl = SMPL(path='smpl', device='cuda')
 
@@ -798,7 +832,8 @@ if __name__ == '__main__':
     # calculate_average(folder, out_folder)
 
     # create_frames_file(folder, out_folder)
-    create_frames_file_test(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'

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
+
+        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)
             
-        x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], 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

@@ -3,11 +3,6 @@ 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
@@ -15,123 +10,6 @@ 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):
     
@@ -146,6 +24,7 @@ class Pyramid(nn.Module):
         if config['body_model'] != '':
             load_model(self.body_enc, config['body_model'] + '_enc')
 
+        if config['use_normals']:
             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'])
             if config['normals_model'] != '':
                 load_model(self.norm_enc, config['normals_model'] + '_enc')
@@ -153,50 +32,25 @@ class Pyramid(nn.Module):
         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
+            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'])
 
-
+        self.use_normals = config['use_normals']
-        # if len(config['pyramid']['resolutions']) == 2:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 3:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 4:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 5:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-
-        # self.add_noise = config['pyramid']['add_noise']
-        # self.noise_amount = config['pyramid']['noise_amount']
-        # self.use_offsets = config['use_offsets']
- 
-        # self.upscale_enhancer = None
-        # if config['pyramid']['final_upscale_enhancer'] != '':
-        #     k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-        #     self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
-        #     load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-        #     self.upscale_enhancer.trainable = False
-
-    # def enhance(self, low, mask, training):
-    #     x = self.upscale_enhancer([low, mask], training=training)
-    #     return x
 
     def encode_conds(self, uv_template, uv_body_posed, uv_norm):
         z_static = self.static_enc(uv_template)
         z_body = self.body_enc(uv_body_posed)
-        z_norm = self.norm_enc(uv_norm)
 
+        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
 
@@ -206,9 +60,6 @@ class Pyramid(nn.Module):
 
         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)
         # if self.use_offsets:
@@ -219,7 +70,6 @@ class Pyramid(nn.Module):
             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 = self.resizers[512](pred)
             pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
@@ -227,12 +77,8 @@ class Pyramid(nn.Module):
 
         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])
@@ -240,8 +86,6 @@ class Pyramid(nn.Module):
                 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 = self.resizers[512](pred)
                 pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask

scripts/cvae.py

@@ -11,7 +11,7 @@ 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
@@ -39,6 +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
@@ -81,11 +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)
@@ -114,12 +117,14 @@ 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)
@@ -127,7 +132,11 @@ def train_step(batch):
         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,
@@ -465,8 +474,8 @@ 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 and not args['debug']:
             ckpt_saver(model, step, optimizer, None)
@@ -474,6 +483,7 @@ def train():
         step += 1
 
 
+
 if __name__ == '__main__':
     if not args['debug']:
         init_wandb()
@@ -499,10 +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)
 
+    # 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

@@ -11,7 +11,7 @@ parser.add_argument('--debug', action='store_true')
 args = vars(parser.parse_args())
 
 if args['debug']:
-    from configs.iccvw.pyr_64_cape_m import config
+    from configs.iccvw.pyr_64_reg import config
 else:
     config_module = importlib.import_module(args['config'])
     config = config_module.config
@@ -238,6 +238,12 @@ def train_step(batch):
     res_modifier = '_' + str(res) if res != 512 else ''
     pred, mean, logvar = out_levels[i]
 
+
+
+    l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2]))
+    kl = kl_loss(mean, logvar)
+
+    if config['use_extra_losses']:
         mesh_pred = uv2mesh(pred)
 
         if config['use_skinning']:
@@ -250,60 +256,23 @@ def train_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)
+        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))
         
-    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: torch.Tensor = reconstr_loss_total + g_balancing_coeff * kl_total
 
-    # scaler.scale(loss).backward()
-    # scaler.step(optimizer)
-    # scaler.update()
-    # optimizer.zero_grad()
-
-    # b = 0
-    # from custom_utils.custom_utils import _maskFaces
-    # mesh_mask = batch['mesh_mask'][b].cpu().numpy()
-    # faces = np.load('smpl/smpl_faces_skirt.npy') if batch['garment'][b] in ['Skirt', 'Dress'] else np.load('smpl/smpl_faces.npy')
-    # faces_body = np.load('smpl/smpl_faces.npy')
-    # _, faces = _maskFaces(np.zeros((14475, 3)), faces, mesh_mask)
-
-    # # 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,2], z=batch['mesh_posed'].cpu().numpy()[0,mesh_mask,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=1),
-    # #                         go.Mesh3d(x=batch['mesh_body_posed'].cpu().numpy()[0,:,0], y=batch['mesh_body_posed'].cpu().numpy()[0,:,2], z=batch['mesh_body_posed'].cpu().numpy()[0,:,1], i=faces_body[:,0], j=faces_body[:,1], k=faces_body[:,2], color='lightblue', opacity=1),
-    # # ])
-    
-    # fig = go.Figure(data=[go.Mesh3d(x=mesh_orig.cpu().numpy()[0,mesh_mask,0], y=mesh_orig.cpu().numpy()[0,mesh_mask,2], z=mesh_orig.cpu().numpy()[0,mesh_mask,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', 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()
-
-    # ex.imshow((uv_orig[b].cpu().numpy().transpose(1,2,0) + 1) / 2).show()
-    # upscaled = model.levels[0].enhance(levels_input[0][0], levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
-    # upscaled = model.resizers[512](upscaled)
-    # ex.imshow((levels_input[0][0][b].cpu().numpy().transpose(1,2,0) + 1) / 2).show()
-    # ex.imshow((upscaled[b].cpu().numpy().transpose(1,2,0) + 1) / 2).show()
-
-
     optimizer.zero_grad()
     loss.backward()
     optimizer.step()
@@ -313,13 +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 }
@@ -359,27 +348,23 @@ 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'] 
-        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']
+        else:
+            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
 
         kl_total += kl
         loss = reconstr_loss_total + g_balancing_coeff * kl_total
@@ -825,9 +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 % 25000 == 0:
+        if step % 25000 == 0 and not args['debug']:
             ckpt_saver(model, step, optimizer, None)
 
         step += 1
@@ -874,11 +859,13 @@ 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
+        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
+        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'])

scripts/generate_results.py

@@ -78,7 +78,26 @@ def step_pyramid(batch):
 
 
 def step(batch):
-    return None
+    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():

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

@@ -12,6 +12,7 @@ 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
 
 
@@ -72,7 +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)
@@ -105,7 +106,14 @@ def plot_normals_example():
                 zaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),)
     fig.update_layout(scene = helper)
     
-    fig.show()
+    # 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()
+