calcualte error second level

aaa_helpers.txt

@@ -1,9 +1,11 @@
-nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3" > nohup/review/pyr_abl_32_64_e2e_r3.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_pre" > nohup/review/pyr_abl_32_64_e2e_r3_pre.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_fine" > nohup/review/pyr_abl_32_64_e2e_r3_fine.out 2>&1 &
-nohup python evaluate_ae_pyramid.py --name evaluate_pyr_abl_32_64_e2e_r3 > nohup/evaluate/pyr_abl_32_64_e2e_r3.out 2>&1 &
-nohup python calculate_error.py --name error_pyr_abl_32_64_e2e_r3 > nohup/error/pyr_abl_32_64_e2e_r3.out 2>&1 &
-
+nohup python cvae_pyramid.py --name="lhunor_abl_pyr_32_no_curv_r1" > nohup/review/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_ae_static_orig_10p_r1" > nohup/review/static_orig_10p_r1.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_ae_body_orig_10p_r1" > nohup/review/body_orig_10p_r1.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_abl_32_64_skirt_no_curv_r1" > nohup/review/abl_pyr_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_no_curv_r1 > nohup/evaluate/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_32_64_skirt_no_curv_r1 > nohup/evaluate/abl_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_abl_pyr_32_no_curv_r1 > nohup/error/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_pyr_abl_32_64_skirt_no_curv_r1 > nohup/error/pyr_abl_32_64_skirt_no_curv_r1.out 2>&1 &
 
 one final convolutional layer for smoothing, on the final coordinates
 

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_body_post import config
+from configs.config_ae_body import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -30,7 +30,7 @@ from tf_utils import check_tf_version, allow_memory_growth
 from losses import edge_loss, uv_mask_loss
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict, plot_3d
-from models.cond_encoder import AutoEncoderNew as AutoEncoder
+from models.cond_encoder import AutoEncoder
 
 
 def init_wandb():
@@ -171,7 +171,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'],
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'],
-                                        use_no_orient=config['remove_global_orientation'],
                                         frames_file=config['frames_file'] if 'frames_file' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_train = StaticDataset(folder=config['train_dir'],
@@ -185,7 +184,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'], 
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'], 
-                                        use_no_orient=config['remove_global_orientation'], 
                                         frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_valid = StaticDataset(folder=config['valid_dir'],

auto_encoder_static.py

@@ -33,7 +33,7 @@ else:
 from tf_utils import check_tf_version, allow_memory_growth
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict, plot_3d
-from models.cond_encoder import AutoEncoderNew as AutoEncoder
+from models.cond_encoder import AutoEncoder
 
 
 def init_wandb():
@@ -205,7 +205,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'],
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'],
-                                        use_no_orient=config['remove_global_orientation'],
                                         frames_file=config['frames_file'] if 'frames_file' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_train = StaticDataset(folder=config['train_dir'],
@@ -219,7 +218,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'], 
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'], 
-                                        use_no_orient=config['remove_global_orientation'], 
                                         frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_valid = StaticDataset(folder=config['valid_dir'],

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32 import config
+from configs.config_abl_pyr_32_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,7 +59,7 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = '200000'
+    iteration = '50000'
 
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
@@ -107,7 +107,7 @@ if __name__ == '__main__':
     for key in per_garment_errors.keys():
         print(key + ': ' + str(np.mean(per_garment_errors[key])))
 
-    with open('/home/workspace/data/results/errors/post/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
+    with open('/home/workspace/data/results/errors/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
         file_writer = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
 
         for key in sorted(errors.keys()):

configs/config_abl_pyr_32.py

@@ -1,9 +1,8 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32_64_e2e_r3_fine_2'
+config['name'] = 'pyr_abl_32_r1'
 config['notes'] = ''
-config['tags'] = ['review_3']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -22,12 +21,9 @@ config['use_offsets'] =               False
 
 
 config['pyramid'] = dict()
-config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['final_upscale_enhancer'] = 'checkpoints/64_512_2'
-
-config['pretrained_model'] = 'checkpoints/pyr_abl_32_64_e2e_r3_fine'
-config['pretrained_model_iteration'] = ''
+config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_4'
 
 config['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
@@ -44,7 +40,7 @@ config['smpl_res'] = 14475
 if config['is_cape']:
   config['smpl_res'] = 3638
 
-config['lr'] = 0.00001
+config['lr'] = 0.0001
 config['starting_balancing_coeff'] = 0.0001
 config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
 config['avg_garment_path'] = ''
@@ -68,7 +64,7 @@ config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
 config['pyramid']['noise_amount'] = 0.025
 
-config['pyramid']['loss_weights'] = [2,1,1,1,1]
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
 
 for res in config['pyramid']['resolutions']:
   if res != 512:
@@ -153,7 +149,7 @@ for res in config['pyramid']['resolutions']:
     level['decoder_depths'] = [9, 9]
     level['decoder_dims'] = [256, 256]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/32_512_4'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer'] = ''#'checkpoints/up_3_d32_64_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   else:

configs/config_abl_pyr_32_64_skirt_r1.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'pyr_abl_32_64_skirt_no_curv_r1'
+config['notes'] = 'no curv, 10p data'
+config['tags'] = ['review_1']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_curvature'] =             False
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/pyr_abl_32_skirt_no_curv_r1'
+config['pyramid']['final_upscale_enhancer'] = 'checkpoints/64_512_skirt'
+
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
+config['batch_size'] = 4
+config['is_skirt'] = True
+config['is_cape'] = False
+config['frames_file'] = 'frames_skirt_10p.txt'
+config['frames_file_valid'] = 'frames_skirt_10p.txt'
+
+config['pyramid']['static_model'] = 'checkpoints/static_1_skirt'
+config['pyramid']['body_model'] = 'checkpoints/body_1_skirt_2_2'
+config['pyramid']['curvature_model'] = 'checkpoints/curv_1_skirt'
+
+config['dataset_in_memory'] = True
+config['resolution'] = None
+config['latent_dim'] = 128
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.0001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['latent_dim'] = config['latent_dim']
+config['pyramid']['add_noise'] = True
+config['pyramid']['noise_amount'] = 0.001
+
+config['pyramid']['loss_weights'] = [1,1,1,1,1]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+
+config['pyramid']['freeze_encoders'] = True
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, 256]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, 256]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [16, 9, 9, 9]
+    level['encoder_dims'] = [64, 128, 128, 256]
+    level['decoder_input'] = (4, 2, 128)
+    level['decoder_depths'] = [16, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 128, 64]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, 256]
+    level['decoder_input'] = (4, 2, 256)
+    level['decoder_depths'] = [9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = False
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [256, 256]
+    level['decoder_input'] = (4, 2, 256)
+    level['decoder_depths'] = [9, 9]
+    level['decoder_dims'] = [256, 256]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/32_512_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+
+config['cond_ae'] = dict()
+config['cond_ae']['is_label'] = False
+config['cond_ae']['upscale_output'] = False
+config['cond_ae']['latent_dim'] = config['latent_dim']
+config['cond_ae']['kernel_size'] = 7
+config['cond_ae']['bottleneck_size'] = 64
+config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['encoder_dims'] = [32, 64, 128, 256, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_input'] = (8, 4, config['cond_ae']['bottleneck_size'])
+config['cond_ae']['decoder_depths'] = [3, 3, 9, 3, 3]
+config['cond_ae']['decoder_dims'] = [config['cond_ae']['bottleneck_size'], 256, 128, 64, 16]
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['upscale_output'] = True
+config['cond_ae_body']['bottleneck_size'] = 512
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3, 3]
+config['cond_ae_body']['encoder_dims'] = [32, 64, 128, 256, 256, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_input'] = (4, 2, config['cond_ae_body']['bottleneck_size'])
+config['cond_ae_body']['decoder_depths'] = [3, 3, 9, 3]
+config['cond_ae_body']['decoder_dims'] = [config['cond_ae_body']['bottleneck_size'], 128, 64, 16]

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,9 @@
 config = dict()
 
-config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_r1'
-config['notes'] = ''
+config['gpu'] = '4'
+config['name'] = 'pyr_abl_32_skirt_no_curv_r1'
+config['notes'] = 'no curv, 10p data'
+config['tags'] = ['review_1']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -18,6 +19,7 @@ config['use_skinning'] =              True # and deshaping
 config['remove_global_orientation'] = True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
 config['use_offsets'] =               False
+config['use_curvature'] =             False
 
 config['pyramid'] = dict()
 config['pyramid']['resolutions'] = [32]
@@ -33,6 +35,8 @@ config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
 config['batch_size'] = 4
 config['is_skirt'] = True
 config['is_cape'] = False
+config['frames_file'] = 'frames_skirt_10p.txt'
+config['frames_file_valid'] = 'frames_skirt_10p.txt'
 
 config['pyramid']['static_model'] = 'checkpoints/static_1_skirt'
 config['pyramid']['body_model'] = 'checkpoints/body_1_skirt_2_2'

configs/config_ae_body.py

@@ -1,8 +1,9 @@
 from configs.config_base import config
 
-config['gpu'] = '2'
+config['gpu'] = '1'
 config['lr'] = 0.0001
-config['name'] = 'body_1_skirt_2_2'
+config['name'] = 'body_orig_10p_r1'
+config['tags'] = ['review_1']
 
 config['notes'] = 'convnext + convnext, add dense with tanh at the end of reverse convnext, | \
     flattened bottleneck with 128 latent_dim\ remove global orientation | \
@@ -15,7 +16,7 @@ config['notes'] = 'convnext + convnext, add dense with tanh at the end of revers
     continued from body_1_skirt_2 | \
     '
 
-config['dataset_in_memory'] = False
+config['dataset_in_memory'] = True
 config['batch_size'] = 32
 
 config['signature_dynamic'] = { 'id': (), 'frame_nr': (),

configs/config_ae_static.py

@@ -1,44 +1,14 @@
-config = dict()
+from configs.config_base import config
 
-
-config['batch_size'] = 4
-config['train_dir'] = '/home/workspace/local-data/train'
-config['valid_dir'] = '/home/workspace/local-data/valid'
-config['test_dir'] = '/home/workspace/data/dataset/test_ready'
-config['use_filled'] = False
-config['resolution'] = 512
-config['is_skirt'] = False
-config['dataset_in_memory'] = True
-config['is_cape'] = False
-config['remove_global_orientation'] = True
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-config['latent_dim'] = 128
-
-config['cond_ae'] = dict()
-config['cond_ae']['is_label'] = False
-config['cond_ae']['upscale_output'] = False
-config['cond_ae']['latent_dim'] = config['latent_dim']
-config['cond_ae']['kernel_size'] = 7
-config['cond_ae']['bottleneck_size'] = 8
-config['cond_ae']['encoder_depths'] = [3, 3, 3, 27, 3]
-config['cond_ae']['encoder_dims'] = [8, 16, 32, 32, config['cond_ae']['bottleneck_size']]
-config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
-config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
-config['cond_ae']['activation'] = 'linear'
-
-
-config['gpu'] = '5'
+config['gpu'] = '3'
 config['lr'] = 0.0005
-config['name'] = 'static_post_4'
-config['notes'] = 'convnext + convnext, | \
- \
-| \
+config['name'] = 'static_orig_10p_r1'
+config['tags'] = ['review_1']
+config['notes'] = 'convnext + convnext, add dense with tanh at the end of reverse convnext, | \
+    flattened latent dim to 128 | \
+    train on 100 garments | \
     deeper model | \
-linear activation| \
+    larger batch size | \
     ' 
 
 config['cond_ae']['upscale_output'] = False

configs/config_ae_static_post.py

@@ -0,0 +1,53 @@
+config = dict()
+
+
+config['batch_size'] = 4
+config['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/data/dataset/test_ready'
+config['use_filled'] = False
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = True
+config['is_cape'] = False
+config['remove_global_orientation'] = True
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+config['cond_ae'] = dict()
+config['cond_ae']['is_label'] = False
+config['cond_ae']['upscale_output'] = False
+config['cond_ae']['latent_dim'] = config['latent_dim']
+config['cond_ae']['kernel_size'] = 7
+config['cond_ae']['bottleneck_size'] = 8
+config['cond_ae']['encoder_depths'] = [3, 3, 3, 27, 3]
+config['cond_ae']['encoder_dims'] = [8, 16, 32, 32, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
+config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
+config['cond_ae']['activation'] = 'linear'
+
+
+config['gpu'] = '5'
+config['lr'] = 0.0005
+config['name'] = 'static_post_4'
+config['notes'] = 'convnext + convnext, | \
+ \
+| \
+    deeper model | \
+linear activation| \
+    ' 
+
+config['cond_ae']['upscale_output'] = False
+config['pretrained_model'] = ''
+
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (), }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                         'mesh_static': (config['smpl_res'], 3,),
+                         'mesh_mask': (config['smpl_res'],),
+                         'uv_mask': (512, 256,),
+                        }

configs/config_base.py

@@ -5,17 +5,19 @@ config['batch_size'] = 4
 # config['train_dir'] = '/home/workspace/local-data/cape_processed/train/female'
 # config['valid_dir'] = '/home/workspace/local-data/cape_processed/test/female'
 # config['test_dir'] = '/home/workspace/local-data/cape_processed/test/female'
-config['train_dir'] = '/home/workspace/local-data/train'
-config['valid_dir'] = '/home/workspace/local-data/valid'
-config['test_dir'] = '/home/workspace/data/dataset/test_ready'
+config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['test_dir'] = '/home/workspace/data/dataset/test_ready_skirt_2'
 # config['train_dir'] = '/home/workspace/local-data/train_skirt'
 # config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
 # config['test_dir'] = '/home/workspace/local-data/test_skirt_ready'
 config['use_filled'] = False
 config['resolution'] = 512
 config['is_skirt'] = False
-config['dataset_in_memory'] = False
+config['dataset_in_memory'] = True
 config['is_cape'] = False
+config['frames_file'] = 'frames_skirt_10p.txt'
+config['frames_file_valid'] = 'frames_skirt_10p.txt'
 
 config['smpl_res'] = 14475
 if config['is_cape']:

configs/post/config_abl_pyr_32.py

@@ -1,9 +1,9 @@
 config = dict()
 
-config['gpu'] = '2'
+config['gpu'] = '6'
 config['name'] = 'abl_pyr_32'
-config['notes'] = 'fixed noise handling'
-config['tags'] = ['pyr_post']
+config['notes'] = ''
+config['tags'] = ['review_1']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING

custom_utils/custom_utils.py

@@ -45,7 +45,7 @@ class UV2Mesh(tf.keras.Model):
         if uv.shape[1] == 3:
             uv = tf.transpose(uv, [0,2,3,1])
         if uv.shape[1] != 512:
-            uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.BILINEAR)
+            uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.LANCZOS5)
             
         batch_size = uv.shape[0]
 
@@ -311,7 +311,7 @@ def load_model(model, checkpoint, disable_assert=False, assert_consumed_on=False
 
 def get_summary_str(model):
     lines = []
-    model.summary(print_fn=lines.append, line_length=150,expand_nested=True,show_trainable=True)
+    model.summary(print_fn=lines.append, line_length=150, expand_nested=True, show_trainable=True)
     # Add initial spaces to avoid markdown formatting in TensorBoard
     return lines
 

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32 import config
+from configs.config_abl_pyr_32_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -217,100 +217,19 @@ def train_step(batch):
     with tf.GradientTape() as tape:
         out_levels = model([levels_input, conds], training=True)
 
-        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+        if config['use_skinning']:
+            mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+        else:
+            mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
         output = dict()
         reconstr_loss_total = 0
         kl_total = 0
 
-        for i, res in enumerate(config['pyramid']['resolutions']):
-            # i = -1
-            # res = config['pyramid']['resolutions'][-1]
-            if res != 512:
-                if i == len(config['pyramid']['resolutions']) - 1:
-                    res_modifier = ''
-                else:
-                    res_modifier = '_' + str(res)
-            else:
-                res_modifier = ''
-
-            pred, mean, logvar = out_levels[i]
-
-            mesh_pred = uv2mesh(pred)
-
-            if config['use_skinning']:
-                shape = batch['pose_shape'][:, 72:]
-                gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-                shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-                mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-                mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
-            else:
-                mesh_pred_posed = mesh_pred
-
-            # is the output already masked?
-
-            e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
-            c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
-            c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-            l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
-            # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-            # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-            l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
-            n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'])
-            kl = kl_loss(mean, logvar)
-
-            if config['use_extra_losses']:
-                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
-                if not config['is_cape']:
-                    reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
-            else:
-                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
-
-            # if config['use_norm_loss'] and step > 2000:
-            #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
-            
-            kl_total += kl
-
-            mean = tf.reduce_mean(mean)
-            logvar = tf.reduce_mean(logvar)
-
-            metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
-
-            output = { **output, **{ '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,
-
-        loss = reconstr_loss_total + balancing_coeff * kl_total
-
-    gradients = tape.gradient(loss, model.trainable_variables)
-    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
-    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
-
-
-@tf.function
-def valid_step(batch):
-    levels_input, conds = group_inputs_for_levels(batch, config)
-    out_levels = model([levels_input, conds], training=False)
-
-    mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
-
-    output = dict()
-    reconstr_loss_total = 0
-    kl_total = 0
-
-    for i, res in enumerate(config['pyramid']['resolutions']):
-        # i = -1
-        # res = config['pyramid']['resolutions'][-1]
-        if res != 512:
-            if i == len(config['pyramid']['resolutions']) - 1:
-                res_modifier = ''
-            else:
-                res_modifier = '_' + str(res)
-        else:
-            res_modifier = ''
-
+        #for i, res in enumerate(config['pyramid']['resolutions']):
+        i = -1
+        res = config['pyramid']['resolutions'][-1]
+        res_modifier = '_' + str(res) if res != 512 else ''
         pred, mean, logvar = out_levels[i]
 
         mesh_pred = uv2mesh(pred)
@@ -324,12 +243,13 @@ def valid_step(batch):
             mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
         else:
             mesh_pred_posed = mesh_pred
+
         # is the output already masked?
 
         e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
         c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
+        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
         # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
         # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
         l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
@@ -342,10 +262,10 @@ def valid_step(batch):
                 reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
         else:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
-        
+
         # if config['use_norm_loss'] and step > 2000:
         #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
-            
+        
         kl_total += kl
 
         mean = tf.reduce_mean(mean)
@@ -353,10 +273,83 @@ def valid_step(batch):
 
         metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
 
-        output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
-                                    'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
-                                    'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
-                                    'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
+        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,
+
+        loss = reconstr_loss_total + balancing_coeff * kl_total
+
+    gradients = tape.gradient(loss, model.trainable_variables)
+    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
+    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
+
+
+@tf.function
+def valid_step(batch):
+    levels_input, conds = group_inputs_for_levels(batch, config)
+    out_levels = model([levels_input, conds], training=False)
+
+
+    if config['use_skinning']:
+        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+    else:
+        mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+
+    output = dict()
+    reconstr_loss_total = 0
+    kl_total = 0
+
+    #for i, res in enumerate(config['pyramid']['resolutions']):
+    i = -1
+    res = config['pyramid']['resolutions'][-1]
+    res_modifier = '_' + str(res) if res != 512 else ''
+    pred, mean, logvar = out_levels[i]
+
+    mesh_pred = uv2mesh(pred)
+
+    if config['use_skinning']:
+        shape = batch['pose_shape'][:, 72:]
+        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
+
+        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
+        mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
+    else:
+        mesh_pred_posed = mesh_pred
+    # is the output already masked?
+
+    e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+    c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+    c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
+    l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+    # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+    # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
+    l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
+    n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'])
+    kl = kl_loss(mean, logvar)
+
+    if config['use_extra_losses']:
+        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+        if not config['is_cape']:
+            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+    else:
+        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
+    
+    # if config['use_norm_loss'] and step > 2000:
+    #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        
+    kl_total += kl
+
+    mean = tf.reduce_mean(mean)
+    logvar = tf.reduce_mean(logvar)
+
+    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+
+    output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
+                                 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
+                                'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
+                                'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim,
 
     loss = reconstr_loss_total + balancing_coeff * kl_total
 
@@ -807,19 +800,18 @@ if __name__ == '__main__':
         # assert len(config['pyramid']['resolutions']) == 1
         load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration'])
 
-    model.static_enc.trainable = False
-    model.body_enc.trainable = False
-    model.curv_enc.trainable = False
-
-    # model.trainable = False
-    # model.cond_encoder_2.trainable = True
-    # if len(config['pyramid']['resolutions']) == 1:
-    # else:
-    #     load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
-    #     model.static_enc.trainable = False
-    #     model.body_enc.trainable = False
-    #     model.curv_enc.trainable = False
-    #     model.cond_encoder.trainable = False
+    if len(config['pyramid']['resolutions']) == 1:
+        model.static_enc.trainable = False
+        model.body_enc.trainable = False
+        if config['use_curvature']:
+            model.curv_enc.trainable = False
+    else:
+        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
+        model.static_enc.trainable = False
+        model.body_enc.trainable = False
+        if config['use_curvature']:
+            model.curv_enc.trainable = False
+        model.cond_encoder.trainable = False
 
     # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
     # model.levels[0].upscale_enhancer.trainable = False
@@ -832,8 +824,8 @@ if __name__ == '__main__':
         load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
         model.upscale_enhancer.trainable = False
 
-    # for i in range(len(model.levels)-1):
-    #     model.levels[i].trainable = False
+    for i in range(len(model.levels)-1):
+        model.levels[i].trainable = False
 
     # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
     # load_model(model.levels[0], config['pyramid']['pretrained_pyramid'])

evaluate_ae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32 import config
+from configs.config_abl_pyr_32_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -97,7 +97,7 @@ if __name__ == '__main__':
     ids = [id.split('_')[0] for id in ids]
     ids = set(ids)
 
-    iteration = '200000'
+    iteration = '50000'
 
     load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')

models/pyramid_level.py

@@ -92,7 +92,7 @@ class PyramidLevel(tf.keras.Model):
         
         # x = x * uv_mask_high[:,:,:,tf.newaxis]
 
-        return x, z, mean, logvar
+        return x, mean, logvar
 
 
 

models/pyramid_model_optimized.py

@@ -24,15 +24,17 @@ class Pyramid(tf.keras.Model):
         self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['latent_dim'], config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['bottleneck_size'], config['cond_ae_body']['kernel_size'])
         if config['pyramid']['body_model'] != '':
             load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
-
-        self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-        if config['pyramid']['curvature_model'] != '':
-            load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
+        
+        if config['use_curvature']:
+            self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
+            if config['pyramid']['curvature_model'] != '':
+                load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
 
         if config['pyramid']['freeze_encoders']:
             self.static_enc.trainable = False
             self.body_enc.trainable = False
-            self.curv_enc.trainable = False
+            if config['use_curvature']:
+                self.curv_enc.trainable = False
 
         self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
                                                  tf.keras.layers.Dense(256, activation='relu'),
@@ -70,19 +72,15 @@ class Pyramid(tf.keras.Model):
         self.add_noise = config['pyramid']['add_noise']
         self.noise_amount = config['pyramid']['noise_amount']
         self.use_offsets = config['use_offsets']
+        self.use_curvature = config['use_curvature']
  
         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)
+            self.upscale_enhancer : tf.keras.Model = 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
 
-        self.cond_encoder_2 = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
-                                                 tf.keras.layers.Dense(256, activation='relu'),
-                                                 tf.keras.layers.Dense(128, activation='relu'),
-                                                 tf.keras.layers.Dense(config['pyramid']['latent_dim'], activation='tanh'),])
-
     def enhance(self, low, mask, training):
         x = self.upscale_enhancer([low, mask], training=training)
         return x
@@ -90,59 +88,51 @@ class Pyramid(tf.keras.Model):
     def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
         z_static = self.static_enc(uv_template, training)
         z_body = self.body_enc(uv_body_posed, training)
-        z_curv = self.curv_enc(uv_curv, training)
-
-        z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        if self.use_curvature:
+            z_curv = self.curv_enc(uv_curv, training=training)
+            z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        else:
+            z_cond = tf.concat([z_static, z_body], axis=-1)
         z_cond = self.cond_encoder(z_cond, training=training)
 
-        return z_cond, z_static, z_body, z_curv
-
-    def encode_conds_2(self, z, z_static, z_body, z_curv, training):
-        z_cond = tf.concat([z, z_static, z_body, z_curv], axis=-1)
-        z_cond = self.cond_encoder_2(z_cond, training=training)
-
         return z_cond
 
     def call(self, inputs, training):
         levels_input, conds = inputs
         uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
 
-        z_cond, z_static, z_body, z_curv = self.encode_conds(uv_static, uv_body, uv_curv, training)
+        z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training)
 
         if self.add_noise == True and training == True:
             z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
 
         out_levels = []
-        pred, z, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
+        pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
         if self.use_offsets:
             pred = pred + levels_input[0][2] # uv_body_posed_32
         if 1 != len(self.levels):
             pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training)  # levels_input[i][-2]=uv_mask_res
+            pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
             out_levels.append([pred, mean, logvar])
-            pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
             pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
         else:
             pred = self.enhance(pred, levels_input[0][-2], training=training)
-            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
+            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
             pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
             out_levels.append([pred, mean, logvar])
 
         for i in range(1, len(self.levels)):
-            input = levels_input[i]
-            input[0] = pred # use previous level output as input for next level
-            z_cond_2 = self.encode_conds_2(z, z_static, z_body, z_curv, training=training)
-
-            pred_level, z, mean, logvar = self.levels[i](input, z_cond_2, training=training)
+            pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
             pred = pred + pred_level
             if i != len(self.levels) - 1:
                 pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
                 out_levels.append([pred, mean, logvar])
-                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.BILINEAR)
+                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
                 pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
             else:
                 if self.upscale_enhancer is not None:
                     pred = self.enhance(pred, levels_input[-1][-2], training=training)
-                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
+                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
                 pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
                 out_levels.append([pred, mean, logvar])
 
@@ -309,7 +299,8 @@ class PyramidNew(tf.keras.Model):
         self.add_noise = config['pyramid']['add_noise']
         self.noise_amount = config['pyramid']['noise_amount']
         self.use_offsets = config['use_offsets']
- 
+        self.use_curvature = config['use_curvature']
+
         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))
@@ -324,9 +315,11 @@ class PyramidNew(tf.keras.Model):
     def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
         z_static = self.static_enc(uv_template, training)
         z_body = self.body_enc(uv_body_posed, training)
-        z_curv = self.curv_enc(uv_curv, training)
-
-        z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        if self.use_curvature:
+            z_curv = self.curv_enc(uv_curv, training=training)
+            z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        else:
+            z_cond = tf.concat([z_static, z_body], axis=-1)
 
         return z_cond
 

preprocessing.py

@@ -232,17 +232,17 @@ def generate_frames_file(folder, ratio=0.1):
     selected = []
 
     for id in tqdm.tqdm(sub_ids):
-        if garment_type_table[id] != 'Dress':
-            continue
-        if len(selected) > 30000:
-            break
+        # if garment_type_table[id] != 'Dress':
+        #     continue
+        # if len(selected) > 30000:
+        #     break
 
         # frames = glob.glob(os.path.join(folder, 'pose_shape', id + '_*'))
         frames = [frame for frame in all_frames if frame.startswith(id + '_')]
         frames = [frame.split('/')[-1].split('.')[0] for frame in frames]
         selected.extend(frames)
 
-    with open(os.path.join(folder, 'frames_dress_30k.txt'), 'w') as f:
+    with open(os.path.join(folder, 'frames_skirt_10p.txt'), 'w') as f:
         for i, frame in enumerate(selected):
             f.write(frame + '\n')
 
@@ -293,9 +293,9 @@ def generate_frames_file_filtered_cape():
 
 if __name__ == '__main__':
 
-    src_folder = '/home/workspace/local-data/train_skirt' #cloth3d_skirt
+    src_folder = '/home/workspace/local-data/valid_skirt' #cloth3d_skirt
     # src_folder = r'D:\Work\Dataset\validation_2'
-    dest_folder = '/home/workspace/data/dataset/validation' 
+    dest_folder = '/home/workspace/data/dataset/local-cache/train_skirt' 
 
 
     # create_no_orient_body(src_folder)
@@ -306,5 +306,5 @@ if __name__ == '__main__':
     # verify_poses(src_folder)
     # create_garment_type_table()
     # generate_faces()
-    generate_frames_file(src_folder, ratio=1)
+    generate_frames_file(src_folder, ratio=0.1)
     # generate_frames_file_filtered_cape()