calcualte error second level

aaa_helpers.txt

@@ -1,3 +1,12 @@
+nohup python cvae_pyramid.py --name="lhunor_abl_pyr_32_no_curv_r1" > nohup/review/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_ae_static_orig_10p_r1" > nohup/review/static_orig_10p_r1.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_ae_body_orig_10p_r1" > nohup/review/body_orig_10p_r1.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_abl_32_64_skirt_no_curv_r1" > nohup/review/abl_pyr_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_no_curv_r1 > nohup/evaluate/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_32_64_skirt_no_curv_r1 > nohup/evaluate/abl_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_abl_pyr_32_no_curv_r1 > nohup/error/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_pyr_abl_32_64_skirt_no_curv_r1 > nohup/error/pyr_abl_32_64_skirt_no_curv_r1.out 2>&1 &
+
 one final convolutional layer for smoothing, on the final coordinates
 
 skirts!!!!

auto_encoder_body.py

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

auto_encoder_static.py

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

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_post import config
+from configs.config_abl_pyr_32_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,13 +59,13 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = ''
+    iteration = '50000'
 
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
 
 
-    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 '')
@@ -107,7 +107,7 @@ if __name__ == '__main__':
     for key in per_garment_errors.keys():
         print(key + ': ' + str(np.mean(per_garment_errors[key])))
 
-    with open('/home/workspace/data/results/errors/post/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
+    with open('/home/workspace/data/results/errors/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
         file_writer = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
 
         for key in sorted(errors.keys()):

configs/config_abl_pyr_32.py

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

configs/config_abl_pyr_32_64_skirt_r1.py

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

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,9 @@
 config = dict()
 
-config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_2'
-config['notes'] = 'continued from pyr_abl_32_skirt-180k'
+config['gpu'] = '4'
+config['name'] = 'pyr_abl_32_skirt_no_curv_r1'
+config['notes'] = 'no curv, 10p data'
+config['tags'] = ['review_1']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -18,24 +19,30 @@ 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['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
 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'] = False
+config['dataset_in_memory'] = True
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -65,6 +72,7 @@ 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_body.py

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

configs/config_ae_static.py

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

configs/config_ae_static_post.py

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

configs/config_base.py

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

configs/post/config_abl_pyr_32.py

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

custom_utils/custom_utils.py

@@ -311,7 +311,7 @@ def load_model(model, checkpoint, disable_assert=False, assert_consumed_on=False
 
 def get_summary_str(model):
     lines = []
-    model.summary(print_fn=lines.append, line_length=150,expand_nested=True,show_trainable=True)
+    model.summary(print_fn=lines.append, line_length=150, expand_nested=True, show_trainable=True)
     # Add initial spaces to avoid markdown formatting in TensorBoard
     return lines
 

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.post.config_abl_pyr_64_128_5 import config
+from configs.config_abl_pyr_32_64_skirt_r1 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'])
@@ -261,8 +263,8 @@ 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:
-            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        # if config['use_norm_loss'] and step > 2000:
+        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
         kl_total += kl
 
@@ -334,8 +336,8 @@ 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:
-        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+    # if config['use_norm_loss'] and step > 2000:
+    #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
     kl_total += kl
 
@@ -790,7 +792,7 @@ 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')
 
@@ -801,24 +803,26 @@ if __name__ == '__main__':
     if len(config['pyramid']['resolutions']) == 1:
         model.static_enc.trainable = False
         model.body_enc.trainable = False
-        model.curv_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
-        model.curv_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)):
+    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:
-    #     load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-    #     model.upscale_enhancer.trainable = False
+    if config['pyramid']['resolutions'][-1] != 512:
+        load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
+        model.upscale_enhancer.trainable = False
 
     for i in range(len(model.levels)-1):
         model.levels[i].trainable = False

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_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf

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'])

models/pyramid_model_optimized.py

@@ -24,15 +24,17 @@ class Pyramid(tf.keras.Model):
         self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['latent_dim'], config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['bottleneck_size'], config['cond_ae_body']['kernel_size'])
         if config['pyramid']['body_model'] != '':
             load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
-
-        self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-        if config['pyramid']['curvature_model'] != '':
-            load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
+        
+        if config['use_curvature']:
+            self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
+            if config['pyramid']['curvature_model'] != '':
+                load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
 
         if config['pyramid']['freeze_encoders']:
             self.static_enc.trainable = False
             self.body_enc.trainable = False
-            self.curv_enc.trainable = False
+            if config['use_curvature']:
+                self.curv_enc.trainable = False
 
         self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
                                                  tf.keras.layers.Dense(256, activation='relu'),
@@ -70,11 +72,12 @@ class Pyramid(tf.keras.Model):
         self.add_noise = config['pyramid']['add_noise']
         self.noise_amount = config['pyramid']['noise_amount']
         self.use_offsets = config['use_offsets']
+        self.use_curvature = config['use_curvature']
  
         self.upscale_enhancer = None
         if config['pyramid']['final_upscale_enhancer'] != '':
             k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-            self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
+            self.upscale_enhancer : tf.keras.Model = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
             load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
             self.upscale_enhancer.trainable = False
 
@@ -85,9 +88,11 @@ class Pyramid(tf.keras.Model):
     def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
         z_static = self.static_enc(uv_template, training)
         z_body = self.body_enc(uv_body_posed, training)
-        z_curv = self.curv_enc(uv_curv, training)
-
-        z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        if self.use_curvature:
+            z_curv = self.curv_enc(uv_curv, training=training)
+            z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        else:
+            z_cond = tf.concat([z_static, z_body], axis=-1)
         z_cond = self.cond_encoder(z_cond, training=training)
 
         return z_cond
@@ -294,7 +299,8 @@ class PyramidNew(tf.keras.Model):
         self.add_noise = config['pyramid']['add_noise']
         self.noise_amount = config['pyramid']['noise_amount']
         self.use_offsets = config['use_offsets']
- 
+        self.use_curvature = config['use_curvature']
+
         self.upscale_enhancer = None
         if config['pyramid']['final_upscale_enhancer'] != '':
             k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
@@ -309,9 +315,11 @@ class PyramidNew(tf.keras.Model):
     def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
         z_static = self.static_enc(uv_template, training)
         z_body = self.body_enc(uv_body_posed, training)
-        z_curv = self.curv_enc(uv_curv, training)
-
-        z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        if self.use_curvature:
+            z_curv = self.curv_enc(uv_curv, training=training)
+            z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        else:
+            z_cond = tf.concat([z_static, z_body], axis=-1)
 
         return z_cond
 

preprocessing.py

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