evaluate training

aaa_helpers.txt

@@ -1,11 +1,9 @@
-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_r7_3" > nohup/review/ae_static_r7_3.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_r7_3" > nohup/review/ae_body_r7_3.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 auto_encoder_curv.py --name="lhunor_ae_curv_r7_3" > nohup/review/ae_curv_r7_3.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 cvae.py --name="lhunor_abl_all_resnet_r7" > nohup/review/abl_all_resnet_r7.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 calculate_error.py --name abl_all_resnet_r7_70k > nohup/error/abl_all_resnet_r7_70k.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 evaluate_ae.py --name abl_all_resnet_r7_70k > nohup/evaluate/abl_all_resnet_r7_70k.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 import config
+from configs.review.config_ae_body import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -30,11 +30,11 @@ 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 AutoEncoder
+from models.cond_encoder import AutoEncoderNew as AutoEncoder
 
 
 def init_wandb():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_body.py')
     artifact.add_file('losses.py')
@@ -42,7 +42,7 @@ def init_wandb():
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
     for config_file_name in config_file_names:
         artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
@@ -137,7 +137,10 @@ def train():
         if step == 0:
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-        wandb.log(to_log, step=step)  
+        if step % 1000 == 0:    
+            wandb.log(to_log, step=step, commit=True)
+        else:
+            wandb.log(to_log, step=step, commit=False)
             
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -171,6 +174,7 @@ 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'],
@@ -184,6 +188,7 @@ 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_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_curv_post import config
+from configs.review.config_ae_curv import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -37,7 +37,7 @@ from models.cond_encoder import AutoEncoderNew as AutoEncoder
 testing = False
 def init_wandb():
     if not testing:
-        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp/')
+        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
         artifact = wandb.Artifact('code', type='code')
         artifact.add_file('auto_encoder_curv.py')
         artifact.add_file('losses.py')
@@ -45,7 +45,7 @@ def init_wandb():
         artifact.add_file('models/cond_encoder.py')
         artifact.add_file('dataset.py')
         artifact.add_file('convnext/models/convnext_tf.py')
-        config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+        config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
         for config_file_name in config_file_names:
             artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
         run.log_artifact(artifact)
@@ -177,8 +177,11 @@ def train():
         if step == 0:
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
  
-        wandb.log(to_log, step=step)  
+        if step % 1000 == 0:    
-        print(step)
+            wandb.log(to_log, step=step, commit=True)
+        else:
+            wandb.log(to_log, step=step, commit=False)  
+        # print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -206,7 +209,7 @@ def test():
 
 if __name__ == '__main__':
     init_wandb()
-    allow_memory_growth()
+    # allow_memory_growth()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_static import config
+from configs.review.config_ae_static import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -33,19 +33,20 @@ 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 AutoEncoder
+from models.cond_encoder import AutoEncoderNew as AutoEncoder
 
 
 def init_wandb():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_static.py')
     artifact.add_file('losses.py')
     artifact.add_file('models/base.py')
+    artifact.add_file('models/resnet.py')
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
     for config_file_name in config_file_names:
         artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
@@ -138,7 +139,10 @@ def train():
         if step == 0:
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-            
+        # if step % 1000 == 0:    
+        #     wandb.log(to_log, step=step, commit=True)
+        # else:
+            # wandb.log(to_log, step=step, commit=False)
         wandb.log(to_log, step=step)
 
         if step % 10000 == 0:
@@ -205,6 +209,7 @@ 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'],
@@ -218,6 +223,7 @@ 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_64_skirt_r1 import config
+from configs.review.config_abl_all import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,13 +59,13 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = '50000'
+    iteration = ''
 
     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()
 
 
-    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
 
 
     faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')
@@ -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/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
+    with open('/home/workspace/data/results/errors/post/' + 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

@@ -1,7 +1,7 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32_r1'
+config['name'] = 'pyr_abl_32'
 config['notes'] = ''
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE

configs/config_abl_pyr_32_64_skirt_r1.py

@@ -1,189 +0,0 @@
-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

@@ -1,9 +1,8 @@
 config = dict()
 
-config['gpu'] = '4'
+config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_no_curv_r1'
+config['name'] = 'pyr_abl_32_skirt_2'
-config['notes'] = 'no curv, 10p data'
+config['notes'] = 'continued from pyr_abl_32_skirt-180k'
-config['tags'] = ['review_1']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -19,30 +18,24 @@ 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]
 config['pyramid']['pretrained_pyramid'] = ''
 config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
 
-config['pretrained_model'] = ''
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
-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['dataset_in_memory'] = False
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -72,7 +65,6 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
 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]
 

configs/config_ae_body.py

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

configs/config_ae_static.py

@@ -1,14 +1,44 @@
-from configs.config_base import config
+config = dict()
 
-config['gpu'] = '3'
+
+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'] = '0'
 config['lr'] = 0.0005
-config['name'] = 'static_orig_10p_r1'
+config['name'] = 'static_post_4'
-config['tags'] = ['review_1']
+config['notes'] = 'convnext + convnext, | \
-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 | \
-    larger batch size | \
+linear activation| \
     ' 
 
 config['cond_ae']['upscale_output'] = False

configs/config_base.py

@@ -5,19 +5,17 @@ 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/data/dataset/local-cache/train_skirt'
+config['train_dir'] = '/home/workspace/local-data/train'
-config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
+config['valid_dir'] = '/home/workspace/local-data/valid'
-config['test_dir'] = '/home/workspace/data/dataset/test_ready_skirt_2'
+config['test_dir'] = '/home/workspace/data/dataset/test_ready'
 # 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'] = True
+config['dataset_in_memory'] = False
 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'] = '6'
+config['gpu'] = '2'
 config['name'] = 'abl_pyr_32'
-config['notes'] = ''
+config['notes'] = 'fixed noise handling'
-config['tags'] = ['review_1']
+config['tags'] = ['pyr_post']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING

configs/review/config_abl_all.py

@@ -0,0 +1,126 @@
+config = dict()
+
+# 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 AVG GARMENT USED
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_curvature'] =             True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               True
+
+config['use_norm_loss'] =             True
+config['only_curvatures'] =           False
+
+ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
+assert ablation_count == 1 or ablation_count == 0
+
+config['gpu'] = '4'
+config['name'] = 'abl_all_resnet_r7'
+config['notes'] = ''
+
+config['avg_garment_path'] = 'custom_data/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and 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['train_dir'] = '/home/workspace/local-data/train'
+config['valid_dir'] = '/home/workspace/local-data/valid'
+config['test_dir'] = '/home/workspace/data/dataset/test_ready'
+
+# config['frames_file'] = 'frames_dress_30k.txt'
+# config['frames_file_valid'] = 'frames_dress_30k.txt'
+# config['frames_file_test'] = 'frames_dress_30k.txt'
+
+config['static_model'] = 'checkpoints/post/static_r7_3'
+config['body_model'] = 'checkpoints/post/body_r7_3'
+config['curvature_model'] = 'checkpoints/post/curv_r7_3'
+
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+
+config['pretrained_model'] = ''
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.001
+
+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,),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+if config['use_skinning']:
+  config['signature_dynamic']['uv_unposed'] = (512, 256, 3)
+  config['signature_dynamic']['mesh_unposed'] = (config['smpl_res'], 3,)
+else:
+  config['signature_dynamic']['uv_posed'] = (512, 256, 3)
+
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+
+config['cvae'] = dict()
+config['cvae']['is_label'] = False
+config['cvae']['add_noise'] = True
+config['cvae']['noise_amount'] = 0.001
+
+config['cvae']['kernel_size'] = 7
+config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
+config['cvae']['encoder_dims'] = [32, 64, 128, 256, 64]
+config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
+config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
+
+
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8
+config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 9, 3]
+config['cond_ae_static']['encoder_dims'] = [16, 32, 64, 64, config['cond_ae_static']['bottleneck_size']]
+config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
+config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
+config['cond_ae_static']['activation'] = 'tanh'
+
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40
+config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
+config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
+config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
+config['cond_ae_curv']['activation'] = 'tanh'
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
+config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
+config['cond_ae_body']['activation'] = 'tanh'

configs/review/config_ae_body.py

@@ -0,0 +1,51 @@
+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'] = False
+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'] = 16
+config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
+config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
+config['cond_ae']['activation'] = 'tanh'
+
+
+config['gpu'] = '4'
+config['lr'] = 0.0001
+config['name'] = 'body_r7_3'
+config['notes'] = 'resnet18' 
+config['tags'] = ['review_7']
+
+config['cond_ae']['upscale_output'] = False
+config['pretrained_model'] = ''
+
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (3, 512, 256,),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                        }
+config['signature_static'] = { 
+                         'mesh_mask': (config['smpl_res'],),
+                        }

configs/review/config_ae_curv.py

@@ -0,0 +1,50 @@
+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'] = False
+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'] = True
+config['cond_ae']['upscale_output'] = False
+config['cond_ae']['latent_dim'] = config['latent_dim']
+config['cond_ae']['kernel_size'] = 7
+config['cond_ae']['bottleneck_size'] = 40
+config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_depths'] = config['cond_ae']['encoder_depths']
+config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
+config['cond_ae']['activation'] = 'tanh'
+
+
+config['gpu'] = '3'
+config['lr'] = 0.001
+config['name'] = 'curv_r7_3'
+config['notes'] = 'resnet18' 
+config['tags'] = ['review_7']
+
+config['cond_ae']['upscale_output'] = False
+config['pretrained_model'] = ''
+
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'uv_curvature': (512, 256, 7),
+                          'mesh_curvature':  (config['smpl_res'])
+                        }
+config['signature_static'] = { 'mesh_mask': (config['smpl_res'],),
+                         'uv_mask': (512, 256,),
+                        }

configs/review/config_ae_static.py

@@ -31,15 +31,13 @@ config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
 config['cond_ae']['activation'] = 'linear'
 
 
-config['gpu'] = '5'
+config['gpu'] = '6'
 config['lr'] = 0.0005
-config['name'] = 'static_post_4'
+config['name'] = 'static_r7_3'
-config['notes'] = 'convnext + convnext, | \
+config['notes'] = 'resnet18 based, one more block'
- \
+config['tags'] = ['review_7']
-| \
+
-    deeper model | \
+    
-linear activation| \
-    ' 
 
 config['cond_ae']['upscale_output'] = False
 config['pretrained_model'] = ''

custom_utils/custom_utils.py

@@ -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.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_post import config
+from configs.review.config_abl_all import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -58,7 +58,9 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
@@ -73,7 +75,7 @@ def kl_loss(mean, logvar):
 
 # 3d loss on posed !!!!!!!!!!!!
 
-# @tf.function
+@tf.function
 def train_step(batch):
 
     with tf.GradientTape() as tape:
@@ -425,8 +427,6 @@ def sample(folder):
 
 
 
-
-
 def test():
     str_split = config['name'].split('_')
     test_idx = str_split.index('test')
@@ -476,7 +476,7 @@ def test():
 
 
 if __name__ == '__main__':
-    # init_wandb()
+    init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32_64_skirt_r1 import config
+from configs.post.config_abl_pyr_64_128_5 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -41,7 +41,7 @@ from losses import collision_loss as collision_penalty
 from custom_utils.custom_utils import batch_to_dict, load_model
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
-from models.pyramid_model_optimized import Pyramid
+from models.pyramid_model_optimized import PyramidNew as Pyramid
 from postprocessing import fix_collision
 
 
@@ -59,11 +59,9 @@ def init_wandb():
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.post.')]
     for config_file_name in config_file_names:
-        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
-        if os.path.exists(file_name):
-            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -263,8 +261,8 @@ def train_step(batch):
         else:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
 
-        # if config['use_norm_loss'] and step > 2000:
+        if config['use_norm_loss'] and step > 2000:
-        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
         kl_total += kl
 
@@ -336,8 +334,8 @@ def valid_step(batch):
     else:
         reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
     
-    # if config['use_norm_loss'] and step > 2000:
+    if config['use_norm_loss'] and step > 2000:
-    #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
     kl_total += kl
 
@@ -792,7 +790,7 @@ if __name__ == '__main__':
     # generate_results()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -803,26 +801,24 @@ if __name__ == '__main__':
     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
 
 
-    for i in range(len(model.levels)-1):
+    for i in range(len(model.levels)):
         load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer'])
         model.levels[i].upscale_enhancer.trainable = False
-    if config['pyramid']['resolutions'][-1] != 512:
+    # if config['pyramid']['resolutions'][-1] != 512:
-        load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
+    #     load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-        model.upscale_enhancer.trainable = False
+    #     model.upscale_enhancer.trainable = False
 
     for i in range(len(model.levels)-1):
         model.levels[i].trainable = False

evaluate_ae.py

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

evaluate_ae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32_64_skirt_r1 import config
+from configs.config_abl_2_pyr_32_64_128_256_512 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf

models/base.py

@@ -1,5 +1,7 @@
 import tensorflow as tf
 from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block, ConvNeXtReverseLabels
+from models.resnet import resnet_18, make_basic_block_layer
+
 
 class Bottleneck(tf.keras.Model):
     
@@ -111,20 +113,34 @@ class Decoder(tf.keras.Model):
 
 class VariationalEncoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7):
+    def __init__(self, features):
         super(VariationalEncoderNew, self).__init__()
 
-        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
+        self.encoder = resnet_18(features)
 
-        self.mean_branch = tf.keras.Sequential(
+        self.mean_branch = tf.keras.Sequential([
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+            tf.keras.layers.Conv2D(filters=features,
-                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
+                                            kernel_size=(3, 3),
-            )
+                                            strides=1,
+                                            padding="same"),
+            tf.keras.layers.BatchNormalization(),
+            tf.keras.layers.Conv2D(filters=features,
+                                            kernel_size=(3, 3),
+                                            strides=1,
+                                            padding="same")
+        ])
 
-        self.var_branch = tf.keras.Sequential(
+        self.var_branch = tf.keras.Sequential([
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+            tf.keras.layers.Conv2D(filters=features,
-                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
+                                            kernel_size=(3, 3),
-            )
+                                            strides=1,
+                                            padding="same"),
+            tf.keras.layers.BatchNormalization(),
+            tf.keras.layers.Conv2D(filters=features,
+                                            kernel_size=(3, 3),
+                                            strides=1,
+                                            padding="same")
+        ])
 
         self.flatten_mean = tf.keras.layers.Flatten()
         self.flatten_var = tf.keras.layers.Flatten()
@@ -147,10 +163,10 @@ class VariationalEncoderNew(tf.keras.Model):
 
 class AEEncoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, activation='tanh'):
+    def __init__(self, features, activation='tanh'):
         super(AEEncoderNew, self).__init__()
 
-        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
+        self.encoder = resnet_18(features)
         self.act = tf.keras.layers.Activation(activation)
 
 
@@ -171,15 +187,15 @@ class AEEncoderNew(tf.keras.Model):
 
 class DecoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, is_label=False):
+    def __init__(self, features, is_label=False, is_cvae=False):
         super(DecoderNew, self).__init__()
 
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
+            self.decoder = resnet_18(features, reversed=True, is_cvae=is_cvae)
         else:
-            self.decoder = ConvNeXtReverseLabels(depths=depths, dims=dims, nr_of_classes=7)
+            self.decoder = resnet_18(features, reversed=True, labels=6, is_cvae=is_cvae)
             
 
     def call(self, inputs, training):

models/cond_encoder.py

@@ -25,8 +25,8 @@ class AutoEncoderNew(tf.keras.Model):
     def __init__(self, config):
         super(AutoEncoderNew, self).__init__()
 
-        self.encoder : AEEncoderNew = AEEncoderNew(config['encoder_depths'], config['encoder_dims'], config['kernel_size'], config['activation'])
+        self.encoder : AEEncoderNew = AEEncoderNew(config['bottleneck_size'], config['activation'])
-        self.decoder : DecoderNew = DecoderNew(config['decoder_depths'], config['decoder_dims'], kernel_size=config['kernel_size'], is_label=config['is_label'])
+        self.decoder : DecoderNew = DecoderNew(config['bottleneck_size'], is_label=config['is_label'])
 
 
     def call(self, inputs, training):

models/cvae_model.py

@@ -43,7 +43,7 @@ class CVAE(tf.keras.Model):
         self.cond_encoder = 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.Lambda(lambda x: x / 1000),
+                                                 tf.keras.layers.Lambda(lambda x: x / 1000),
                                                  tf.keras.layers.Dense(config['latent_dim'], activation='tanh')])
 
         self.encoder = VariationalEncoder(config['cvae']['latent_dim'], config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
@@ -159,16 +159,16 @@ class CVAENew(tf.keras.Model):
         self.size = config['resolution']
 
         if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
-            self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['encoder_depths'], config['cond_ae_static']['encoder_dims'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'])
+            self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['bottleneck_size'], config['cond_ae_static']['activation'])
             if config['static_model'] != '':
                 load_model(self.static_enc, config['static_model'] + '_enc')
 
-            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_size'])
+            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['bottleneck_size'])
             if config['body_model'] != '':
                 load_model(self.body_enc, config['body_model'] + '_enc')
 
         if config['use_curvature']:
-            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'])
+            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['bottleneck_size'], config['cond_ae_curv']['activation'])
             if config['curvature_model'] != '':
                 load_model(self.curv_enc, config['curvature_model'] + '_enc')
 
@@ -179,10 +179,10 @@ class CVAENew(tf.keras.Model):
             if config['use_curvature']:
                 self.curv_enc.trainable = False
 
-        self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
+        self.encoder = VariationalEncoderNew(config['cvae']['encoder_dims'][-1])
-        self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
+        self.decoder = DecoderNew(config['cvae']['decoder_dims'][-1], is_cvae=True)
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
+        self.reshape = tf.keras.layers.Reshape((8, 4, config['cvae']['decoder_dims'][-1]))
 
         if config['avg_garment_path'] != '':
             self.avg_garment = np.load(config['avg_garment_path'])

models/pyramid_model_optimized.py

@@ -25,7 +25,6 @@ class Pyramid(tf.keras.Model):
         if config['pyramid']['body_model'] != '':
             load_model(self.body_enc, config['pyramid']['body_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')
@@ -33,7 +32,6 @@ class Pyramid(tf.keras.Model):
         if config['pyramid']['freeze_encoders']:
             self.static_enc.trainable = False
             self.body_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'),
@@ -72,12 +70,11 @@ 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 : tf.keras.Model = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
+            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
 
@@ -88,11 +85,9 @@ 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)
-        if self.use_curvature:
+        z_curv = self.curv_enc(uv_curv, training)
-            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
@@ -299,7 +294,6 @@ 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'] != '':
@@ -315,11 +309,9 @@ 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)
-        if self.use_curvature:
+        z_curv = self.curv_enc(uv_curv, training)
-            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
 

models/resnet.py

@@ -0,0 +1,254 @@
+# taken from https://github.com/calmisential/TensorFlow2.0_ResNet/blob/master/models/resnet.py
+
+import tensorflow as tf
+
+
+class BasicBlock(tf.keras.layers.Layer):
+
+    def __init__(self, filter_num, stride=1, upsample=False):
+        super(BasicBlock, self).__init__()
+        if not upsample:
+            self.conv1 = tf.keras.layers.Conv2D(filters=filter_num,
+                                                kernel_size=(3, 3),
+                                                strides=stride,
+                                                padding="same")
+        else:
+            self.conv1 = tf.keras.layers.Conv2DTranspose(filters=filter_num,
+                                                kernel_size=(3, 3),
+                                                strides=stride,
+                                                padding="same")
+        self.bn1 = tf.keras.layers.BatchNormalization()
+        self.conv2 = tf.keras.layers.Conv2D(filters=filter_num,
+                                            kernel_size=(3, 3),
+                                            strides=1,
+                                            padding="same")
+        self.bn2 = tf.keras.layers.BatchNormalization()
+        if stride != 1:
+            if not upsample:
+                self.updownsample = tf.keras.Sequential()
+                self.updownsample.add(tf.keras.layers.Conv2D(filters=filter_num,
+                                                        kernel_size=(1, 1),
+                                                        strides=stride))
+                self.updownsample.add(tf.keras.layers.BatchNormalization())
+            else:
+                self.updownsample = tf.keras.Sequential()
+                self.updownsample.add(tf.keras.layers.Conv2DTranspose(filters=filter_num,
+                                                        kernel_size=(1, 1),
+                                                        strides=stride))
+                self.updownsample.add(tf.keras.layers.BatchNormalization())
+        else:
+            self.updownsample = lambda x: x
+
+    def call(self, inputs, training=None, **kwargs):
+        residual = self.updownsample(inputs)
+
+        x = self.conv1(inputs)
+        x = self.bn1(x, training=training)
+        x = tf.nn.relu(x)
+        x = self.conv2(x)
+        x = self.bn2(x, training=training)
+
+        output = tf.nn.relu(tf.keras.layers.add([residual, x]))
+
+        return output
+
+
+class BottleNeck(tf.keras.layers.Layer):
+    def __init__(self, filter_num, stride=1):
+        super(BottleNeck, self).__init__()
+        self.conv1 = tf.keras.layers.Conv2D(filters=filter_num,
+                                            kernel_size=(1, 1),
+                                            strides=1,
+                                            padding='same')
+        self.bn1 = tf.keras.layers.BatchNormalization()
+        self.conv2 = tf.keras.layers.Conv2D(filters=filter_num,
+                                            kernel_size=(3, 3),
+                                            strides=stride,
+                                            padding='same')
+        self.bn2 = tf.keras.layers.BatchNormalization()
+        self.conv3 = tf.keras.layers.Conv2D(filters=filter_num * 4,
+                                            kernel_size=(1, 1),
+                                            strides=1,
+                                            padding='same')
+        self.bn3 = tf.keras.layers.BatchNormalization()
+
+        self.downsample = tf.keras.Sequential()
+        self.downsample.add(tf.keras.layers.Conv2D(filters=filter_num * 4,
+                                                   kernel_size=(1, 1),
+                                                   strides=stride))
+        self.downsample.add(tf.keras.layers.BatchNormalization())
+
+    def call(self, inputs, training=None, **kwargs):
+        residual = self.downsample(inputs)
+
+        x = self.conv1(inputs)
+        x = self.bn1(x, training=training)
+        x = tf.nn.relu(x)
+        x = self.conv2(x)
+        x = self.bn2(x, training=training)
+        x = tf.nn.relu(x)
+        x = self.conv3(x)
+        x = self.bn3(x, training=training)
+
+        output = tf.nn.relu(tf.keras.layers.add([residual, x]))
+
+        return output
+
+
+def make_basic_block_layer(filter_num, blocks, stride=1, upsample=False):
+    res_block = tf.keras.Sequential()
+    res_block.add(BasicBlock(filter_num, stride=stride, upsample=upsample))
+
+    for _ in range(1, blocks):
+        res_block.add(BasicBlock(filter_num, stride=1))
+
+    return res_block
+
+
+def make_bottleneck_layer(filter_num, blocks, stride=1):
+    res_block = tf.keras.Sequential()
+    res_block.add(BottleNeck(filter_num, stride=stride))
+
+    for _ in range(1, blocks):
+        res_block.add(BottleNeck(filter_num, stride=1))
+
+    return res_block
+
+
+class ResNetTypeI(tf.keras.Model):
+    def __init__(self, layer_params, features, reversed=False, labels=None, is_cvae=False):
+        super(ResNetTypeI, self).__init__()
+        self.reversed = reversed
+        self.labels = labels
+
+        if not reversed:
+            self.conv1 = tf.keras.layers.Conv2D(filters=64,
+                                                kernel_size=(7, 7),
+                                                strides=2,
+                                                padding="same")
+            self.bn1 = tf.keras.layers.BatchNormalization()
+            self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
+                                                strides=2,
+                                                padding="same")
+        else:
+            self.conv1 = tf.keras.layers.Conv2DTranspose(filters=3 if labels is None else labels,
+                                                kernel_size=(7, 7),
+                                                strides=2,
+                                                padding="same")
+            self.bn1 = tf.keras.layers.BatchNormalization()
+            # self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
+            #                                     strides=2,
+            #                                     padding="same")
+            self.pool1 = tf.keras.layers.UpSampling2D()
+
+        self.layer1 = make_basic_block_layer(filter_num=64,
+                                             blocks=layer_params[0],
+                                             stride=1 if not reversed else 2,
+                                             upsample=reversed)
+        self.layer2 = make_basic_block_layer(filter_num=64,
+                                             blocks=layer_params[1],
+                                             stride=2,
+                                             upsample=reversed)
+        self.layer3 = make_basic_block_layer(filter_num=64,
+                                             blocks=layer_params[2],
+                                             stride=2,
+                                             upsample=reversed)
+        self.layer4 = make_basic_block_layer(filter_num=128,
+                                             blocks=layer_params[3],
+                                             stride=2,
+                                             upsample=reversed)
+        self.layer5 = make_basic_block_layer(filter_num=features if not is_cvae else features*2,
+                                             blocks=layer_params[4],
+                                             stride=2 if not reversed else 1,
+                                             upsample=reversed)
+
+    def call(self, inputs, training=None, mask=None):
+        if not self.reversed:
+            x = self.conv1(inputs)
+            x = self.bn1(x, training=training)
+            x = tf.nn.relu(x)
+            x = self.pool1(x)
+            x = self.layer1(x, training=training)
+            x = self.layer2(x, training=training)
+            x = self.layer3(x, training=training)
+            x = self.layer4(x, training=training)
+            x = self.layer5(x, training=training)
+        else:
+            x = self.layer5(inputs, training=training)
+            x = self.layer4(x, training=training)
+            x = self.layer3(x, training=training)
+            x = self.layer2(x, training=training)
+            x = self.layer1(x, training=training)
+
+            x = self.pool1(x)
+            x = self.bn1(x, training=training)
+            # x = tf.nn.relu(x)
+            x = self.conv1(x)
+            if self.labels is None:
+                x = tf.nn.tanh(x)
+            # else:
+            #     x = tf.nn.softmax(x)
+
+        return x
+
+
+class ResNetTypeII(tf.keras.Model):
+    def __init__(self, layer_params):
+        super(ResNetTypeII, self).__init__()
+        self.conv1 = tf.keras.layers.Conv2D(filters=64,
+                                            kernel_size=(7, 7),
+                                            strides=2,
+                                            padding="same")
+        self.bn1 = tf.keras.layers.BatchNormalization()
+        self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
+                                               strides=2,
+                                               padding="same")
+
+        self.layer1 = make_bottleneck_layer(filter_num=64,
+                                            blocks=layer_params[0])
+        self.layer2 = make_bottleneck_layer(filter_num=128,
+                                            blocks=layer_params[1],
+                                            stride=2)
+        self.layer3 = make_bottleneck_layer(filter_num=256,
+                                            blocks=layer_params[2],
+                                            stride=2)
+        self.layer4 = make_bottleneck_layer(filter_num=512,
+                                            blocks=layer_params[3],
+                                            stride=2)
+
+        self.avgpool = tf.keras.layers.GlobalAveragePooling2D()
+        self.fc = tf.keras.layers.Dense(units=NUM_CLASSES, activation=tf.keras.activations.softmax)
+
+    def call(self, inputs, training=None, mask=None):
+        x = self.conv1(inputs)
+        x = self.bn1(x, training=training)
+        x = tf.nn.relu(x)
+        x = self.pool1(x)
+        x = self.layer1(x, training=training)
+        x = self.layer2(x, training=training)
+        x = self.layer3(x, training=training)
+        x = self.layer4(x, training=training)
+        x = self.avgpool(x)
+        output = self.fc(x)
+
+        return output
+
+
+def resnet_18(features, reversed=False, labels=None, is_cvae=False):
+    return ResNetTypeI(layer_params=[2, 2, 2, 2, 2], features=features, reversed=reversed, labels=labels, is_cvae=is_cvae)
+
+
+def resnet_34():
+    return ResNetTypeI(layer_params=[3, 4, 6, 3])
+
+
+def resnet_50():
+    return ResNetTypeII(layer_params=[3, 4, 6, 3])
+
+
+def resnet_101():
+    return ResNetTypeII(layer_params=[3, 4, 23, 3])
+
+
+def resnet_152():
+    return ResNetTypeII(layer_params=[3, 8, 36, 3])

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':
+        if garment_type_table[id] != 'Dress':
-        #     continue
+            continue
-        # if len(selected) > 30000:
+        if len(selected) > 30000:
-        #     break
+            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_skirt_10p.txt'), 'w') as f:
+    with open(os.path.join(folder, 'frames_dress_30k.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/valid_skirt' #cloth3d_skirt
+    src_folder = '/home/workspace/local-data/train_skirt' #cloth3d_skirt
     # src_folder = r'D:\Work\Dataset\validation_2'
-    dest_folder = '/home/workspace/data/dataset/local-cache/train_skirt' 
+    dest_folder = '/home/workspace/data/dataset/validation' 
 
 
     # 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=0.1)
+    generate_frames_file(src_folder, ratio=1)
     # generate_frames_file_filtered_cape()