calcualte error second level

aaa_helpers.txt

@@ -1,18 +1,11 @@
-nohup python cvae.py --name="lhunor_abl_all_10p_curv_10_r2" > nohup/review/abl_all_10p_curv_10_r2.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_1_orig_curv_10_10p_r2" > nohup/review/curv_1_orig_curv_10_10p_r2.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_1_orig_curv_25_10p_r2" > nohup/review/curv_1_orig_curv_25_10p_r2.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_1_orig_curv_100_10p_r2_2" > nohup/review/curv_1_orig_curv_100_10p_r2_2.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_all_10p_curv_10_r2" > nohup/review/abl_all_10p_curv_10_r2.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_all_10p_curv_25_r2" > nohup/review/abl_all_10p_curv_25_r2.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_all_10p_curv_100_r2" > nohup/review/abl_all_10p_curv_100_r2.out 2>&1 &
-nohup python evaluate_ae.py --name="lhunor_abl_all_10p_curv_100_r2" > nohup/evaluate/lhunor_abl_all_10p_curv_100_r2.out 2>&1 &
-nohup python evaluate_ae.py --name="lhunor_abl_all_10p_curv_10_r2" > nohup/evaluate/lhunor_abl_all_10p_curv_10_r2.out 2>&1 &
-nohup python evaluate_ae.py --name="lhunor_abl_all_10p_curv_25_r2" > nohup/evaluate/lhunor_abl_all_10p_curv_25_r2.out 2>&1 &
-nohup python calculate_error.py --name="lhunor_abl_all_10p_curv_100_r2" > nohup/error/abl_all_10p_curv_100_r2.out 2>&1 &
-nohup python calculate_error.py --name="lhunor_abl_all_10p_curv_10_r2" > nohup/error/abl_all_10p_curv_10_r2.out 2>&1 &
-nohup python calculate_error.py --name="lhunor_abl_all_10p_curv_25_r2" > nohup/error/abl_all_10p_curv_25_r2.out 2>&1 &
-
-
+nohup python cvae_pyramid.py --name="lhunor_abl_pyr_32_no_curv_r1" > nohup/review/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_ae_static_orig_10p_r1" > nohup/review/static_orig_10p_r1.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_ae_body_orig_10p_r1" > nohup/review/body_orig_10p_r1.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_abl_32_64_skirt_no_curv_r1" > nohup/review/abl_pyr_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_no_curv_r1 > nohup/evaluate/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_32_64_skirt_no_curv_r1 > nohup/evaluate/abl_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_abl_pyr_32_no_curv_r1 > nohup/error/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_pyr_abl_32_64_skirt_no_curv_r1 > nohup/error/pyr_abl_32_64_skirt_no_curv_r1.out 2>&1 &
 
 one final convolutional layer for smoothing, on the final coordinates
 

auto_encoder_body.py

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

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_curv_1_orig_curv_10_10p_r2_2 import config
+from configs.config_ae_curv_post import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -31,13 +31,13 @@ import plotly.express as ex
 from tf_utils import check_tf_version, allow_memory_growth
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict
-from models.cond_encoder import AutoEncoder
+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')
@@ -47,9 +47,7 @@ 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'
-            if os.path.exists(file_name):
-                artifact.add_file(file_name)
+            artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
         run.log_artifact(artifact)
 
 uv2mesh = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -98,73 +96,46 @@ def dice_dense(prediction, ground_truth, weight_map=None):
 
 
 @tf.function
-def train_step(batch):	
-    with tf.GradientTape() as tape:	
-        pred = model([batch['uv_curvature'], batch['uv_mask']], training=True)	
-        ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)	
-        ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))	
-        loss = ce_uv_loss	
-    pred_mesh = tf.math.argmax(uv2mesh(pred), axis=-1)	
-    mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1))	
-    mean_iou_mesh = get_mean_iou(tf.cast(batch['mesh_curvature'], tf.float32) * batch['mesh_mask'], tf.cast(pred_mesh, tf.float32) * batch['mesh_mask'])	
-    dice = dice_dense(pred, batch['uv_curvature'])	
-    	
-    gradients = tape.gradient(loss, model.trainable_variables)	
-    optimizer.apply_gradients(zip(gradients, model.trainable_variables))	
-    return { 'train/loss': loss, 'train/ce_uv_loss': ce_uv_loss, 'train/ssim': ms_ssim, 'train/mean_iou': mean_iou, 'train/mean_iou_mesh': mean_iou_mesh, 'train/dice': dice }	
-        	
-@tf.function	
-def valid_step(batch):	
-    pred = model([batch['uv_curvature'], batch['uv_mask']], training=False)	
-    ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)	
-    ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))	
-    loss = ce_uv_loss	
-    pred_mesh = tf.math.argmax(uv2mesh(pred), axis=-1)	
-    mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1))	
-    mean_iou_mesh = get_mean_iou(tf.cast(batch['mesh_curvature'], tf.float32) * batch['mesh_mask'], tf.cast(pred_mesh, tf.float32) * batch['mesh_mask'])	
-    dice = dice_dense(pred, batch['uv_curvature'])	
-    return { 'valid/loss': loss, 'valid/ce_uv_loss': ce_uv_loss, 'valid/ssim': ms_ssim, 'valid/mean_iou': mean_iou, 'valid/mean_iou_mesh': mean_iou_mesh, 'valid/dice': dice }
+def train_step(batch):
+    with tf.GradientTape() as tape:
+        pred = model([batch['uv_curvature'], batch['uv_mask']], training=True)
 
-# def train_step(batch):
-#     with tf.GradientTape() as tape:
-#         pred = model([batch['uv_curvature'], batch['uv_mask']], training=True)
+        ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
+        ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))
 
-#         ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
-#         ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))
+        mesh_pred = uv2mesh(pred) * batch['mesh_mask'][:,:,tf.newaxis]
+        mesh_orig = tf.cast(uv2mesh(tf.math.argmax(batch['uv_curvature'], axis=-1, output_type=tf.int32)), tf.float32) * batch['mesh_mask']
+        ce_mesh_loss = scce(mesh_orig, mesh_pred)
 
-#         mesh_pred = uv2mesh(pred) * batch['mesh_mask'][:,:,tf.newaxis]
-#         mesh_orig = tf.cast(uv2mesh(tf.math.argmax(batch['uv_curvature'], axis=-1, output_type=tf.int32)), tf.float32) * batch['mesh_mask']
-#         ce_mesh_loss = scce(mesh_orig, mesh_pred)
+        loss = ce_uv_loss + ce_mesh_loss
 
-#         loss = ce_uv_loss + ce_mesh_loss
-
-#     mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1))
-#     dice = dice_dense(pred, batch['uv_curvature'])
+    mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1))
+    dice = dice_dense(pred, batch['uv_curvature'])
     
-#     gradients = tape.gradient(loss, model.trainable_variables)
-#     optimizer.apply_gradients(zip(gradients, model.trainable_variables))
-#     return { 'train/loss': loss, 'train/ce_uv_loss': ce_uv_loss, 'train/ssim': ms_ssim, 'train/mean_iou': mean_iou,
-#              'train/dice': dice, 'train/ce_mesh_loss': ce_mesh_loss }
+    gradients = tape.gradient(loss, model.trainable_variables)
+    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
+    return { 'train/loss': loss, 'train/ce_uv_loss': ce_uv_loss, 'train/ssim': ms_ssim, 'train/mean_iou': mean_iou,
+             'train/dice': dice, 'train/ce_mesh_loss': ce_mesh_loss }
         
 
 
-# @tf.function
-# def valid_step(batch):
-#     pred = model([batch['uv_curvature'], batch['uv_mask']], training=False)
+@tf.function
+def valid_step(batch):
+    pred = model([batch['uv_curvature'], batch['uv_mask']], training=False)
 
-#     ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
-#     ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))
+    ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
+    ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))
 
-#     mesh_pred = uv2mesh(pred) * batch['mesh_mask'][:,:,tf.newaxis]
-#     mesh_orig = tf.cast(uv2mesh(tf.math.argmax(batch['uv_curvature'], axis=-1, output_type=tf.int32)), tf.float32) * batch['mesh_mask']
-#     ce_mesh_loss = scce(mesh_orig, mesh_pred)
-#     loss = ce_uv_loss + ce_mesh_loss
+    mesh_pred = uv2mesh(pred) * batch['mesh_mask'][:,:,tf.newaxis]
+    mesh_orig = tf.cast(uv2mesh(tf.math.argmax(batch['uv_curvature'], axis=-1, output_type=tf.int32)), tf.float32) * batch['mesh_mask']
+    ce_mesh_loss = scce(mesh_orig, mesh_pred)
+    loss = ce_uv_loss + ce_mesh_loss
 
-#     mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1))
-#     dice = dice_dense(pred, batch['uv_curvature'])
+    mean_iou = get_mean_iou(tf.math.argmax(batch['uv_curvature'], axis=-1), tf.math.argmax(pred, axis=-1))
+    dice = dice_dense(pred, batch['uv_curvature'])
 
-#     return { 'valid/loss': loss, 'valid/ce_uv_loss': ce_uv_loss, 'valid/ssim': ms_ssim, 'valid/mean_iou': mean_iou,
-#              'valid/dice': dice, 'valid/ce_mesh_loss': ce_mesh_loss }
+    return { 'valid/loss': loss, 'valid/ce_uv_loss': ce_uv_loss, 'valid/ssim': ms_ssim, 'valid/mean_iou': mean_iou,
+             'valid/dice': dice, 'valid/ce_mesh_loss': ce_mesh_loss }
         
 
 def plot_everything(batch: dict, type: str):
@@ -235,7 +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())
@@ -255,8 +226,7 @@ if __name__ == '__main__':
                                         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'],
-                                        curv_neighbourhood=config['curv_neighbourhood'])
+                                        is_cape=config['is_cape'])
     static_dataset_train = StaticDataset(folder=config['train_dir'],
                                          signature=config['signature_static'], 
                                          resolutions=[config['resolution']], 
@@ -270,8 +240,7 @@ if __name__ == '__main__':
                                         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'],
-                                        curv_neighbourhood=config['curv_neighbourhood'])
+                                        is_cape=config['is_cape'])
     static_dataset_valid = StaticDataset(folder=config['valid_dir'],
                                          signature=config['signature_static'], 
                                          resolutions=[config['resolution']], 

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_10p_curv_25_r2 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 = '70000'
+    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_all_10p_curv_100_r2.py

@@ -1,125 +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
-
-config['curv_neighbourhood'] = 100
-
-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'] = '1'
-config['name'] = 'abl_all_10p_curv_100_r2'
-config['notes'] = ''
-config['tags'] = ['review_2']
-
-config['avg_garment_path'] = 'custom_data/train_no_shape_skirt_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'] = True
-config['dataset_in_memory'] = False
-config['is_cape'] = False
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-# config['frames_file_test'] = 'frames_dress_30k.txt'
-
-config['static_model'] = 'checkpoints/static_1_skirt'
-config['body_model'] = 'checkpoints/body_1_skirt_2_2'
-config['curvature_model'] = 'checkpoints/post/curv_1_orig_curv_100_10p_r2_2'
-
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-
-config['pretrained_model'] = ''
-config['latent_dim'] = 128
-
-###############    
-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']['latent_dim'] = config['latent_dim']
-config['cvae']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.025
-
-config['cvae']['kernel_size'] = 7
-config['cvae']['encoder_depths'] = [3, 3, 9, 3]
-config['cvae']['encoder_dims'] = [32, 64, 128, 256]
-config['cvae']['decoder_input'] = (16, 8, 80)
-config['cvae']['decoder_depths'] = [3, 3, 9, 3]
-config['cvae']['decoder_dims'] = [256, 128, 64, 16]
-
-
-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_all_10p_curv_10_r2.py

@@ -1,125 +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
-
-config['curv_neighbourhood'] = 10
-
-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'] = '6'
-config['name'] = 'abl_all_10p_curv_10_r2_2'
-config['notes'] = ''
-config['tags'] = ['review_2']
-
-config['avg_garment_path'] = 'custom_data/train_no_shape_skirt_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'] = True
-config['dataset_in_memory'] = True
-config['is_cape'] = False
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-# config['frames_file_test'] = 'frames_dress_30k.txt'
-
-config['static_model'] = 'checkpoints/static_1_skirt'
-config['body_model'] = 'checkpoints/body_1_skirt_2_2'
-config['curvature_model'] = 'checkpoints/post/curv_1_orig_curv_10_10p_r2_2'
-
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-
-config['pretrained_model'] = ''
-config['latent_dim'] = 128
-
-###############    
-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']['latent_dim'] = config['latent_dim']
-config['cvae']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.025
-
-config['cvae']['kernel_size'] = 7
-config['cvae']['encoder_depths'] = [3, 3, 9, 3]
-config['cvae']['encoder_dims'] = [32, 64, 128, 256]
-config['cvae']['decoder_input'] = (16, 8, 80)
-config['cvae']['decoder_depths'] = [3, 3, 9, 3]
-config['cvae']['decoder_dims'] = [256, 128, 64, 16]
-
-
-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_all_10p_curv_25_r2.py

@@ -1,125 +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
-
-config['curv_neighbourhood'] = 25
-
-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'] = '0'
-config['name'] = 'abl_all_10p_curv_25_r2'
-config['notes'] = ''
-config['tags'] = ['review_2']
-
-config['avg_garment_path'] = 'custom_data/train_no_shape_skirt_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'] = True
-config['dataset_in_memory'] = True
-config['is_cape'] = False
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-# config['frames_file_test'] = 'frames_dress_30k.txt'
-
-config['static_model'] = 'checkpoints/static_1_skirt'
-config['body_model'] = 'checkpoints/body_1_skirt_2_2'
-config['curvature_model'] = 'checkpoints/post/curv_1_orig_curv_25_10p_r2'
-
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-
-config['pretrained_model'] = ''
-config['latent_dim'] = 128
-
-###############    
-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']['latent_dim'] = config['latent_dim']
-config['cvae']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.025
-
-config['cvae']['kernel_size'] = 7
-config['cvae']['encoder_depths'] = [3, 3, 9, 3]
-config['cvae']['encoder_dims'] = [32, 64, 128, 256]
-config['cvae']['decoder_input'] = (16, 8, 80)
-config['cvae']['decoder_depths'] = [3, 3, 9, 3]
-config['cvae']['decoder_dims'] = [256, 128, 64, 16]
-
-
-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_64_skirt_r1.py

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

configs/config_abl_pyr_32_skirt.py

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

configs/config_ae_body.py

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

configs/config_ae_curv.py

@@ -1,23 +1,13 @@
 from configs.config_base import config
 
-config['gpu'] = '4'
+config['gpu'] = '5'
 config['lr'] = 0.001
-config['name'] = 'curv_1_orig_r2' #'ae_curv_9'
+config['name'] = 'curv_1' #'ae_curv_9'
 config['notes'] = 'convnext + convnext, 16*8*32, ce loss. flattened latent dim of 128. trained on 100 garments. switched back to sparse CCE, normal one was giving NaN | \
 | \
   '
-config['tags'] = ['review_2']
-config['remove_global_orientation'] = True
 
 config['cond_ae']['is_label'] = True
-config['is_skirt'] = True
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-config['curv_neighbourhood'] = 10
 
 config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
                           'uv_curvature': (512, 256, 7),

configs/config_ae_curv_1_orig_curv_100_10p_r2.py

@@ -1,30 +0,0 @@
-from configs.config_base import config
-
-config['gpu'] = '1'
-config['lr'] = 0.001
-config['name'] = 'curv_1_orig_curv_100_10p_r2' #'ae_curv_9'
-config['notes'] = 'convnext + convnext, 16*8*32, ce loss. flattened latent dim of 128. trained on 100 garments. switched back to sparse CCE, normal one was giving NaN | \
-| \
-  '
-config['tags'] = ['review_2']
-config['remove_global_orientation'] = True
-config['dataset_in_memory'] = True
-
-config['cond_ae']['is_label'] = True
-config['is_skirt'] = True
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-config['curv_neighbourhood'] = 100
-
-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/config_ae_curv_1_orig_curv_100_10p_r2_2.py

@@ -1,30 +0,0 @@
-from configs.config_base import config
-
-config['gpu'] = '1'
-config['lr'] = 0.001
-config['name'] = 'curv_1_orig_curv_100_10p_r2_2' #'ae_curv_9'
-config['notes'] = 'convnext + convnext, 16*8*32, ce loss. flattened latent dim of 128. trained on 100 garments. switched back to sparse CCE, normal one was giving NaN | \
-| \
-  '
-config['tags'] = ['review_2']
-config['remove_global_orientation'] = True
-config['dataset_in_memory'] = True
-
-config['cond_ae']['is_label'] = True
-config['is_skirt'] = True
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-config['curv_neighbourhood'] = 100
-
-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/config_ae_curv_1_orig_curv_10_10p_r2.py

@@ -1,30 +0,0 @@
-from configs.config_base import config
-
-config['gpu'] = '4'
-config['lr'] = 0.001
-config['name'] = 'curv_1_orig_curv_10_10p_r2' #'ae_curv_9'
-config['notes'] = 'convnext + convnext, 16*8*32, ce loss. flattened latent dim of 128. trained on 100 garments. switched back to sparse CCE, normal one was giving NaN | \
-| \
-  '
-config['tags'] = ['review_2']
-config['remove_global_orientation'] = True
-config['dataset_in_memory'] = True
-
-config['cond_ae']['is_label'] = True
-config['is_skirt'] = True
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-config['curv_neighbourhood'] = 10
-
-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/config_ae_curv_1_orig_curv_10_10p_r2_2.py

@@ -1,30 +0,0 @@
-from configs.config_base import config
-
-config['gpu'] = '4'
-config['lr'] = 0.001
-config['name'] = 'curv_1_orig_curv_10_10p_r2_2' #'ae_curv_9'
-config['notes'] = 'convnext + convnext, 16*8*32, ce loss. flattened latent dim of 128. trained on 100 garments. switched back to sparse CCE, normal one was giving NaN | \
-| \
-  '
-config['tags'] = ['review_2']
-config['remove_global_orientation'] = True
-config['dataset_in_memory'] = True
-
-config['cond_ae']['is_label'] = True
-config['is_skirt'] = True
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-config['curv_neighbourhood'] = 10
-
-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/config_ae_curv_1_orig_curv_25_10p_r2.py

@@ -1,30 +0,0 @@
-from configs.config_base import config
-
-config['gpu'] = '6'
-config['lr'] = 0.001
-config['name'] = 'curv_1_orig_curv_25_10p_r2' #'ae_curv_9'
-config['notes'] = 'convnext + convnext, 16*8*32, ce loss. flattened latent dim of 128. trained on 100 garments. switched back to sparse CCE, normal one was giving NaN | \
-| \
-  '
-config['tags'] = ['review_2']
-config['remove_global_orientation'] = True
-config['dataset_in_memory'] = True
-
-config['cond_ae']['is_label'] = True
-config['is_skirt'] = True
-
-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['frames_file'] = 'frames_skirt_10p.txt'
-config['frames_file_valid'] = 'frames_skirt_10p.txt'
-config['curv_neighbourhood'] = 25
-
-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/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

convnext/models/convnext_tf.py

@@ -366,8 +366,8 @@ class ConvNeXtReverseLabels(tf.keras.Model):
             self.stages.append(stage)
             cur += depths[i]
 
-        self.last = Dense(nr_of_classes, activation='softmax')
-        # self.last = Dense(nr_of_classes - 1)
+        # self.last = Dense(nr_of_classes, activation='softmax')
+        self.last = Dense(nr_of_classes - 1)
 
     def call(self, x, training):
         for i in reversed(range(len(self.downsample_layers))):

custom_utils/custom_utils.py

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

cvae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_10p_curv_100_r2 import config
+from configs.config_abl_all_post 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, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
-from models.cvae_model import CVAE
+from models.cvae_model import CVAENew as CVAE
 
 
 def init_wandb():
@@ -73,7 +73,7 @@ def kl_loss(mean, logvar):
 
 # 3d loss on posed !!!!!!!!!!!!
 
-@tf.function
+# @tf.function
 def train_step(batch):
 
     with tf.GradientTape() as tape:
@@ -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())
@@ -494,8 +494,7 @@ if __name__ == '__main__':
                                         use_one_hot=config['use_one_hot'],
                                         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'],
-                                        curv_neighbourhood=config['curv_neighbourhood'])
+                                        is_cape=config['is_cape'])
     static_dataset_train = StaticDataset(folder=config['train_dir'],
                                          signature=config['signature_static'], 
                                          resolutions=[config['resolution']], 
@@ -510,8 +509,7 @@ if __name__ == '__main__':
                                         use_one_hot=config['use_one_hot'],
                                         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'],
-                                        curv_neighbourhood=config['curv_neighbourhood'])
+                                        is_cape=config['is_cape'])
     static_dataset_valid = StaticDataset(folder=config['valid_dir'],
                                          signature=config['signature_static'], 
                                          resolutions=[config['resolution']], 

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32_skirt import config
+from configs.config_abl_pyr_32_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -210,7 +210,7 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col
     return fig
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     levels_input, conds = group_inputs_for_levels(batch, config)
 
@@ -733,7 +733,7 @@ def speed_step(levels_input, conds):
 
 
 if __name__ == '__main__':
-    # init_wandb()
+    init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str, default='lhunor')
     args = vars(parser.parse_args())
@@ -803,12 +803,14 @@ 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'])

dataset.py

@@ -194,8 +194,7 @@ class DatasetFactory():
                     use_one_hot=False,
                     use_no_orient=True,
                     testing=False,
-                    frames_file=None,
-                    curv_neighbourhood=25):
+                    frames_file=None):
         assert set(resolutions).issubset(set([32, 64, 128, 256, 512]))
 
         dataset_idx = DatasetIdx(folder, shuffle, is_cape=is_cape, testing=testing, frames_file=frames_file)
@@ -261,7 +260,7 @@ class DatasetFactory():
 
 
             if 'mesh_curvature' in signature.keys():
-                mesh_curvature = np.load(os.path.join(folder, f'mesh_curvature_{curv_neighbourhood}_2' if curv_neighbourhood != 25 else 'mesh_curvature', id + separator + frame_nr + '.npz')); mesh_curvature = mesh_curvature['mesh_curvature']
+                mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature', id + separator + frame_nr + '.npz')); mesh_curvature = mesh_curvature['mesh_curvature']
                 item['mesh_curvature'] = mesh_curvature.astype(np.int32)
 
 
@@ -271,8 +270,7 @@ class DatasetFactory():
                     res_string = '_' + str(res)
 
                 if 'uv_curvature' + res_string in signature.keys():
-                    # print(os.path.join(folder, (f'uv_curvature_{curv_neighbourhood}_2' if curv_neighbourhood != 25 else 'uv_curvature')+ res_string, id + separator + frame_nr + '.npz'))
-                    uv_curvature = np.load(os.path.join(folder, (f'uv_curvature_{curv_neighbourhood}_2' if curv_neighbourhood != 25 else 'uv_curvature')+ res_string, id + separator + frame_nr + '.npz')); 
+                    uv_curvature = np.load(os.path.join(folder, 'uv_curvature' + res_string, id + separator + frame_nr + '.npz')); 
                     if res_string != '':
                         uv_curvature = uv_curvature['uv_curvature'] 
                     else:
@@ -383,16 +381,15 @@ if __name__ == '__main__':
                         #  'uv_shaped_body': (3, 512, 256,),
                           }
 
-    dataset = factory.get_dataset(folder='/home/workspace/data/dataset/local-cache/train_skirt',
+    dataset = factory.get_dataset(folder='/home/workspace/local-data/train_skirt',
                                   batch_size=1,
                                   signature=signature_dynamic,
                                   resolutions=[512],
                                   do_repeat=False,
                                   use_one_hot=False,
                                   is_cape=False,
-                                  frames_file='frames_skirt_10p.txt',
-                                  curv_neighbourhood=25)
-    static_dataset = StaticDataset(folder='/home/workspace/data/dataset/local-cache/train_skirt',
+                                  frames_file='frames_dress_30k.txt')
+    static_dataset = StaticDataset(folder='/home/workspace/local-data/train_skirt',
                                    signature=signature_static,
                                    resolutions=[512],
                                   is_cape=False)

evaluate_ae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_10p_curv_25_r2 import config
+from configs.config_abl_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -42,7 +42,7 @@ from losses import collision_loss as collision_penalty
 from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
-from models.cvae_model import CVAE
+from models.cvae_model import CVAENew as CVAE
 from custom_utils.supersmpl_io import writeOBJ
 # from unif_metric import chamfer_and_score
 
@@ -102,7 +102,7 @@ if __name__ == '__main__':
     ids = [id.split('_')[0] for id in ids]
     ids = set(ids)
 
-    iteration = '70000'
+    iteration = ''
 
     load_model(model, 'checkpoints/post/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')

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/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()