fine tune

aaa_helpers.txt

@@ -1,9 +1,9 @@
-nohup python auto_encoder_static.py --name="lhunor_ae_static_r7_3" > nohup/review/ae_static_r7_3.out 2>&1 &
+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 auto_encoder_body.py --name="lhunor_ae_body_r7_3" > nohup/review/ae_body_r7_3.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 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_pyr_abl_32_64_e2e_r3_fine" > nohup/review/pyr_abl_32_64_e2e_r3_fine.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_pyr_abl_32_64_e2e_r3 > nohup/evaluate/pyr_abl_32_64_e2e_r3.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 calculate_error.py --name error_pyr_abl_32_64_e2e_r3 > nohup/error/pyr_abl_32_64_e2e_r3.out 2>&1 &
-nohup python evaluate_ae.py --name abl_all_resnet_r7_70k > nohup/evaluate/abl_all_resnet_r7_70k.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.review.config_ae_body import config
+from configs.config_ae_body_post import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -34,7 +34,7 @@ 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', tags=config['tags'])
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
     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.review.')]
+    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')
     run.log_artifact(artifact)
@@ -137,10 +137,7 @@ 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)  
-            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)

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_ae_curv import config
+from configs.config_ae_curv_post 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', tags=config['tags'])
+        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp/')
         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.review.')]
+        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')
         run.log_artifact(artifact)
@@ -177,11 +177,8 @@ 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)  
-            wandb.log(to_log, step=step, commit=True)
+        print(step)
-        else:
-            wandb.log(to_log, step=step, commit=False)  
-        # print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -209,7 +206,7 @@ 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.review.config_ae_static import config
+from configs.config_ae_static import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -37,16 +37,15 @@ 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', tags=config['tags'])
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
     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.review.')]
+    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')
     run.log_artifact(artifact)
@@ -139,10 +138,7 @@ 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:

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_abl_all import config
+from configs.config_abl_pyr_32 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 = ''
+    iteration = '200000'
 
     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/post/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
 
 
     faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')

configs/config_abl_pyr_32.py

@@ -1,8 +1,9 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32'
+config['name'] = 'pyr_abl_32_64_e2e_r3_fine_2'
 config['notes'] = ''
+config['tags'] = ['review_3']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -21,9 +22,12 @@ config['use_offsets'] =               False
 
 
 config['pyramid'] = dict()
-config['pyramid']['resolutions'] = [32]
+config['pyramid']['resolutions'] = [32, 64]
 config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_4'
+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['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
@@ -40,7 +44,7 @@ config['smpl_res'] = 14475
 if config['is_cape']:
   config['smpl_res'] = 3638
 
-config['lr'] = 0.0001
+config['lr'] = 0.00001
 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'] = ''
@@ -64,7 +68,7 @@ config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
 config['pyramid']['noise_amount'] = 0.025
 
-config['pyramid']['loss_weights'] = [1,1,1,1,1]
+config['pyramid']['loss_weights'] = [2,1,1,1,1]
 
 for res in config['pyramid']['resolutions']:
   if res != 512:
@@ -149,7 +153,7 @@ for res in config['pyramid']['resolutions']:
     level['decoder_depths'] = [9, 9]
     level['decoder_dims'] = [256, 256]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = ''#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer'] = 'checkpoints/32_512_4'#'checkpoints/up_3_d32_64_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   else:

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,8 @@
 config = dict()
 
 config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_2'
+config['name'] = 'pyr_abl_32_skirt_r1'
-config['notes'] = 'continued from pyr_abl_32_skirt-180k'
+config['notes'] = ''
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -24,7 +24,10 @@ config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
 config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
 
-config['train_dir'] = '/home/workspace/local-data/train_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
@@ -35,7 +38,7 @@ 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'] = False
+config['dataset_in_memory'] = True
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -65,6 +68,7 @@ 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_static.py

@@ -31,7 +31,7 @@ config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
 config['cond_ae']['activation'] = 'linear'
 
 
-config['gpu'] = '0'
+config['gpu'] = '5'
 config['lr'] = 0.0005
 config['name'] = 'static_post_4'
 config['notes'] = 'convnext + convnext, | \

configs/review/config_abl_all.py

@@ -1,126 +0,0 @@
-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

@@ -1,51 +0,0 @@
-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

@@ -1,50 +0,0 @@
-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

@@ -1,51 +0,0 @@
-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'] = '6'
-config['lr'] = 0.0005
-config['name'] = 'static_r7_3'
-config['notes'] = 'resnet18 based, one more block'
-config['tags'] = ['review_7']
-
-    
-
-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,),
-                        }

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.LANCZOS5)
+            uv = tf.image.resize(uv, (512, 256), tf.image.ResizeMethod.BILINEAR)
             
         batch_size = uv.shape[0]
 

cvae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_abl_all import config
+from configs.config_abl_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -58,9 +58,7 @@ 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:
-        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_adaptive=False, is_smpl_orig=config['is_cape'])
@@ -75,7 +73,7 @@ def kl_loss(mean, logvar):
 
 # 3d loss on posed !!!!!!!!!!!!
 
-@tf.function
+# @tf.function
 def train_step(batch):
 
     with tf.GradientTape() as tape:
@@ -427,6 +425,8 @@ 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.post.config_abl_pyr_64_128_5 import config
+from configs.config_abl_pyr_32 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 PyramidNew as Pyramid
+from models.pyramid_model_optimized import Pyramid
 from postprocessing import fix_collision
 
 
@@ -59,9 +59,11 @@ 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.post.')]
+    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_smpl_orig=config['is_cape'])
@@ -215,66 +217,70 @@ def train_step(batch):
     with tf.GradientTape() as tape:
         out_levels = model([levels_input, conds], training=True)
 
-        if config['use_skinning']:
+        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
-            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']):
+        for i, res in enumerate(config['pyramid']['resolutions']):
-        i = -1
+            # i = -1
-        res = config['pyramid']['resolutions'][-1]
+            # res = config['pyramid']['resolutions'][-1]
-        res_modifier = '_' + str(res) if res != 512 else ''
+            if res != 512:
-        pred, mean, logvar = out_levels[i]
+                if i == len(config['pyramid']['resolutions']) - 1:
+                    res_modifier = ''
+                else:
+                    res_modifier = '_' + str(res)
+            else:
+                res_modifier = ''
 
-        mesh_pred = uv2mesh(pred)
+            pred, mean, logvar = out_levels[i]
 
-        if config['use_skinning']:
+            mesh_pred = uv2mesh(pred)
-            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]
+            if config['use_skinning']:
-            mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
+                shape = batch['pose_shape'][:, 72:]
-        else:
+                gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-            mesh_pred_posed = mesh_pred
+                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])])
 
-        # is the output already masked?
+                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
 
-        e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+            # is the output already masked?
-        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']:
+            e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+            c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
-            if not config['is_cape']:
+            c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+            l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
-        else:
+            # 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)))
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
+            # 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_norm_loss'] and step > 2000:
+            if config['use_extra_losses']:
-            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
-        
+                if not config['is_cape']:
-        kl_total += kl
+                    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)
 
-        mean = tf.reduce_mean(mean)
+            # if config['use_norm_loss'] and step > 2000:
-        logvar = tf.reduce_mean(logvar)
+            #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+            
+            kl_total += kl
 
-        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'])
+            mean = tf.reduce_mean(mean)
+            logvar = tf.reduce_mean(logvar)
 
-        output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
+            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'])
-                                 '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,
+            output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
-                                 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim,
+                                    '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
 
@@ -288,66 +294,69 @@ 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']
-    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']):
+    for i, res in enumerate(config['pyramid']['resolutions']):
-    i = -1
+        # i = -1
-    res = config['pyramid']['resolutions'][-1]
+        # res = config['pyramid']['resolutions'][-1]
-    res_modifier = '_' + str(res) if res != 512 else ''
+        if res != 512:
-    pred, mean, logvar = out_levels[i]
+            if i == len(config['pyramid']['resolutions']) - 1:
+                res_modifier = ''
+            else:
+                res_modifier = '_' + str(res)
+        else:
+            res_modifier = ''
 
-    mesh_pred = uv2mesh(pred)
+        pred, mean, logvar = out_levels[i]
 
-    if config['use_skinning']:
+        mesh_pred = uv2mesh(pred)
-        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]
+        if config['use_skinning']:
-        mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
+            shape = batch['pose_shape'][:, 72:]
-    else:
+            gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-        mesh_pred_posed = mesh_pred
+            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])])
-    # is the output already masked?
 
-    e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-    c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+            mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
-    c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
+        else:
-    l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+            mesh_pred_posed = mesh_pred
-    # 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)))
+        # is the output already masked?
-    # 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']:
+        e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
-        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+        c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
-        if not config['is_cape']:
+        c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed' + res_modifier] - pred) ** 2), axis=-1), axis=[1, 2]))
-    else:
+        # 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)))
-        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
+        # 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))
-    if config['use_norm_loss'] and step > 2000:
+        n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'])
-        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        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)
         
-    kl_total += kl
+        # 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)
+        mean = tf.reduce_mean(mean)
-    logvar = tf.reduce_mean(logvar)
+        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'])
+        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, 
+        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/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/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,
+                                    '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
 
@@ -790,7 +799,7 @@ if __name__ == '__main__':
     # generate_results()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -798,30 +807,33 @@ if __name__ == '__main__':
         # assert len(config['pyramid']['resolutions']) == 1
         load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration'])
 
-    if len(config['pyramid']['resolutions']) == 1:
+    model.static_enc.trainable = False
-        model.static_enc.trainable = False
+    model.body_enc.trainable = False
-        model.body_enc.trainable = False
+    model.curv_enc.trainable = False
-        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
-        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
 
     # 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)):
+    for i in range(len(model.levels)-1):
         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):
+    # for i in range(len(model.levels)-1):
-        model.levels[i].trainable = False
+    #     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.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_abl_all import config
+from configs.config_abl_all_post 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_2_pyr_32_64_128_256_512 import config
+from configs.config_abl_pyr_32 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 = '50000'
+    iteration = '200000'
 
     load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')

models/base.py

@@ -1,7 +1,5 @@
 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):
     
@@ -113,34 +111,20 @@ class Decoder(tf.keras.Model):
 
 class VariationalEncoderNew(tf.keras.Model):
     
-    def __init__(self, features):
+    def __init__(self, depths, dims, kernel_size=7):
         super(VariationalEncoderNew, self).__init__()
 
-        self.encoder = resnet_18(features)
+        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
 
-        self.mean_branch = tf.keras.Sequential([
+        self.mean_branch = tf.keras.Sequential(
-            tf.keras.layers.Conv2D(filters=features,
+                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
-                                            kernel_size=(3, 3),
+                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
-                                            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(
-            tf.keras.layers.Conv2D(filters=features,
+                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
-                                            kernel_size=(3, 3),
+                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
-                                            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()
@@ -163,10 +147,10 @@ class VariationalEncoderNew(tf.keras.Model):
 
 class AEEncoderNew(tf.keras.Model):
     
-    def __init__(self, features, activation='tanh'):
+    def __init__(self, depths, dims, kernel_size=7, activation='tanh'):
         super(AEEncoderNew, self).__init__()
 
-        self.encoder = resnet_18(features)
+        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
         self.act = tf.keras.layers.Activation(activation)
 
 
@@ -187,15 +171,15 @@ class AEEncoderNew(tf.keras.Model):
 
 class DecoderNew(tf.keras.Model):
     
-    def __init__(self, features, is_label=False, is_cvae=False):
+    def __init__(self, depths, dims, kernel_size=7, is_label=False):
         super(DecoderNew, self).__init__()
 
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = resnet_18(features, reversed=True, is_cvae=is_cvae)
+            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
         else:
-            self.decoder = resnet_18(features, reversed=True, labels=6, is_cvae=is_cvae)
+            self.decoder = ConvNeXtReverseLabels(depths=depths, dims=dims, nr_of_classes=7)
             
 
     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['bottleneck_size'], config['activation'])
+        self.encoder : AEEncoderNew = AEEncoderNew(config['encoder_depths'], config['encoder_dims'], config['kernel_size'], config['activation'])
-        self.decoder : DecoderNew = DecoderNew(config['bottleneck_size'], is_label=config['is_label'])
+        self.decoder : DecoderNew = DecoderNew(config['decoder_depths'], config['decoder_dims'], kernel_size=config['kernel_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']['bottleneck_size'], config['cond_ae_static']['activation'])
+            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'])
             if config['static_model'] != '':
                 load_model(self.static_enc, config['static_model'] + '_enc')
 
-            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['bottleneck_size'])
+            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_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']['bottleneck_size'], config['cond_ae_curv']['activation'])
+            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'])
             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_dims'][-1])
+        self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
-        self.decoder = DecoderNew(config['cvae']['decoder_dims'][-1], is_cvae=True)
+        self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, config['cvae']['decoder_dims'][-1]))
+        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
 
         if config['avg_garment_path'] != '':
             self.avg_garment = np.load(config['avg_garment_path'])

models/pyramid_level.py

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

models/pyramid_model_optimized.py

@@ -78,6 +78,11 @@ class Pyramid(tf.keras.Model):
             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
@@ -90,44 +95,54 @@ class Pyramid(tf.keras.Model):
         z_cond = tf.concat([z_static, z_body, z_curv], 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 = self.encode_conds(uv_static, uv_body, uv_curv, training)
+        z_cond, z_static, z_body, z_curv = 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, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training)
+        pred, z, 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.LANCZOS5)
+            pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
             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)):
-            pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
+            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 = 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.LANCZOS5)
+                pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.BILINEAR)
                 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.LANCZOS5)
+                    pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
                 pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
                 out_levels.append([pred, mean, logvar])
 

models/resnet.py

@@ -1,254 +0,0 @@
-# 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])