fine tune

aaa_helpers.txt

@@ -1,16 +1,11 @@
+nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3" > nohup/review/pyr_abl_32_64_e2e_r3.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_pre" > nohup/review/pyr_abl_32_64_e2e_r3_pre.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_pyr_abl_32_64_e2e_r3_fine" > nohup/review/pyr_abl_32_64_e2e_r3_fine.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_pyr_abl_32_64_e2e_r3 > nohup/evaluate/pyr_abl_32_64_e2e_r3.out 2>&1 &
+nohup python calculate_error.py --name error_pyr_abl_32_64_e2e_r3 > nohup/error/pyr_abl_32_64_e2e_r3.out 2>&1 &
+
+
 one final convolutional layer for smoothing, on the final coordinates
-nohup python calculate_error.py --name error_al_all_150k > nohup/error/post_al_all_150k.out 2>&1 &
-nohup python auto_encoder_static.py --name="lhunor_static_iccv_1" > nohup/iccv/encoders/static_iccv_1.out 2>&1 &
-nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_skirt" > nohup/iccv/encoders/static_iccv_1_skirt.out 2>&1 &
-nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_cape_f" > nohup/iccv/encoders/static_iccv_1_cape_f.out 2>&1 &
-nohup python auto_encoder_static.py --name="lhunor_static_iccv_1_cape_m" > nohup/iccv/encoders/static_iccv_1_cape_m.out 2>&1 &
-nohup python auto_encoder_body.py --name="lhunor_body_iccv_1" > nohup/iccv/encoders/body_iccv_1.out 2>&1 &
-nohup python auto_encoder_body.py --name="lhunor_body_iccv_1_skirt" > nohup/iccv/encoders/body_iccv_1_skirt.out 2>&1 &
-nohup python auto_encoder_body.py --name="lhunor_body_iccv_1_skirt" > nohup/iccv/encoders/body_iccv_1_skirt.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1 " > nohup/iccv/encoders/curv_iccv_1.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_skirt" > nohup/iccv/encoders/curv_iccv_1_skirt.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_curv_iccv_1_cape_f" > nohup/iccv/encoders/curv_iccv_1_cape_f.out 2>&1 &
-nohup python cvae.py --name="lhunor_cvae_iccv_gnn_decoder_1" > nohup/iccv/cvae_iccv_gnn_decoder_1.out 2>&1 &
 
 skirts!!!!
 pyramid next week

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_ae_body_cape_f import config
+from configs.config_ae_body_post import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -31,11 +31,10 @@ 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 custom_utils.custom_utils import Accumulator
 
 
 def init_wandb():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_body.py')
     artifact.add_file('losses.py')
@@ -45,9 +44,7 @@ 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 = UV2Mesh(res=256, is_smpl_orig=config['is_cape'], is_skirt=config['is_skirt'])
@@ -127,26 +124,20 @@ def train():
     for batch in dataset_train:
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
         train_loss = train_step(batch)
-        train_accumulator.update(train_loss)
 
         data_valid = valid_iterator.get_next()
         data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
         valid_loss = valid_step(data_valid)
-        valid_accumulator.update(valid_loss)
 
-        if step % 1000 == 0 or (step < 1000 and step % 10 == 0):
-            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-                train_figs = plot_everything(batch, 'train')
-                valid_figs = plot_everything(data_valid, 'valid')
-                to_log = { **to_log, **train_figs, **valid_figs }
-            if step == 0:
-                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+        to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
+        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            train_figs = plot_everything(batch, 'train')
+            valid_figs = plot_everything(data_valid, 'valid')
+            to_log = { **to_log, **train_figs, **valid_figs }
+        if step == 0:
+            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-                
-            wandb.log(to_log, step=step)
-            train_accumulator.reset()
-            valid_accumulator.reset() 
+        wandb.log(to_log, step=step)  
             
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -159,6 +150,7 @@ def train():
 
 if __name__ == '__main__':
     init_wandb()
+    allow_memory_growth()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())
@@ -204,15 +196,13 @@ if __name__ == '__main__':
 
     model = AutoEncoder(config['cond_ae'])
     optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
-    train_accumulator = Accumulator()
-    valid_accumulator = Accumulator()
 
     # load_model(model.encoder, 'checkpoints/body_1_skirt_2_enc')
     # load_model(model.decoder, 'checkpoints/body_1_skirt_2_dec')
 
     ckpt_enc = tf.train.Checkpoint(model=model.encoder)
-    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
-    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
 
     train()

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_ae_curv_cape_f import config
+from configs.config_ae_curv_post import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -32,13 +32,12 @@ 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 AutoEncoderNew as AutoEncoder
-from custom_utils.custom_utils import Accumulator
 
 
 testing = False
 def init_wandb():
     if not testing:
-        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', 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')
@@ -48,9 +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'])
@@ -167,26 +164,21 @@ def train():
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
 
         train_loss = train_step(batch)
-        train_accumulator.update(train_loss)
 
         data_valid = valid_iterator.get_next()
         data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
         valid_loss = valid_step(data_valid)
-        valid_accumulator.update(valid_loss)
 
-        if step % 1000 == 0 or (step < 1000 and step % 10 == 0):
-            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-                train_figs = plot_everything(batch, 'train')
-                valid_figs = plot_everything(data_valid, 'valid')
-                to_log = { **to_log, **train_figs, **valid_figs }
-            if step == 0:
-                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+        to_log = { **train_loss, **valid_loss }
+        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            train_figs = plot_everything(batch, 'train')
+            valid_figs = plot_everything(data_valid, 'valid')
+            to_log = { **to_log, **train_figs, **valid_figs }
+        if step == 0:
+            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
  
-                
-            wandb.log(to_log, step=step)
-            train_accumulator.reset()
-            valid_accumulator.reset()
+        wandb.log(to_log, step=step)  
+        print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -239,7 +231,7 @@ if __name__ == '__main__':
                                          signature=config['signature_static'], 
                                          resolutions=[config['resolution']], 
                                          in_memory=True, 
-                                         is_cape=config['is_cape'])
+                                        is_cape=config['is_cape'])
 
     dataset_valid = factory.get_dataset(folder=config['valid_dir'],
                                         batch_size=config['batch_size'], 
@@ -253,17 +245,15 @@ if __name__ == '__main__':
                                          signature=config['signature_static'], 
                                          resolutions=[config['resolution']], 
                                          in_memory=True, 
-                                         is_cape=config['is_cape'])
+                                        is_cape=config['is_cape'])
 
     model = AutoEncoder(config['cond_ae'])
     optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
-    train_accumulator = Accumulator()
-    valid_accumulator = Accumulator()
 
     ckpt_enc = tf.train.Checkpoint(model=model.encoder)
-    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
-    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
 
     if testing:
         test()

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_ae_static_cape_m import config
+from configs.config_ae_static import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -34,11 +34,10 @@ 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 custom_utils.custom_utils import Accumulator
 
 
 def init_wandb():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_static.py')
     artifact.add_file('losses.py')
@@ -48,9 +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 = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -128,32 +125,27 @@ def train():
     for batch in dataset_train:
         batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
         train_loss = train_step(batch)
-        train_accumulator.update(train_loss)
 
         data_valid = valid_iterator.get_next()
         data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
         valid_loss = valid_step(data_valid)
-        valid_accumulator.update(valid_loss)
 
-        if step % 1000 == 0 or (step < 1000 and step % 10 == 0):
-            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-                train_figs = plot_everything(batch, 'train')
-                valid_figs = plot_everything(data_valid, 'valid')
-                to_log = { **to_log, **train_figs, **valid_figs }
-            if step == 0:
-                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+        to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+        if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
+            train_figs = plot_everything(batch, 'train')
+            valid_figs = plot_everything(data_valid, 'valid')
+            to_log = { **to_log, **train_figs, **valid_figs }
+        if step == 0:
+            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
             
-            wandb.log(to_log, step=step)
-            train_accumulator.reset()
-            valid_accumulator.reset()
+        wandb.log(to_log, step=step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
             manager_dec.save(checkpoint_number=step)
 
-            print(step)
+        print(step)
 
         step += 1
 
@@ -239,9 +231,6 @@ if __name__ == '__main__':
     model : AutoEncoder = AutoEncoder(config['cond_ae'])
     optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
 
-    train_accumulator = Accumulator()
-    valid_accumulator = Accumulator()
-
     if config['pretrained_model'] != '':
         load_model(model.encoder, config['pretrained_model'] + '_enc')
         load_model(model.decoder, config['pretrained_model'] + '_dec')

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 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,13 +59,13 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = ''
+    iteration = '200000'
 
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
 
 
-    output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
 
 
     faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')

configs/config_abl_all_post.py

@@ -19,7 +19,7 @@ config['only_curvatures'] =           False
 ablation_count = [config['use_skinning'], config['remove_global_orientation'], config['use_curvature'], config['use_extra_losses'], config['use_offsets']].count(False)
 assert ablation_count == 1 or ablation_count == 0
 
-config['gpu'] = '4'
+config['gpu'] = '1'
 config['name'] = 'al_all_post'
 config['notes'] = ''
 

configs/config_abl_pyr_32.py

@@ -1,8 +1,9 @@
 config = dict()
 
 config['gpu'] = '0'
-config['name'] = 'pyr_abl_32'
+config['name'] = 'pyr_abl_32_64_e2e_r3_fine_2'
 config['notes'] = ''
+config['tags'] = ['review_3']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -21,9 +22,12 @@ config['use_offsets'] =               False
 
 
 config['pyramid'] = dict()
-config['pyramid']['resolutions'] = [32]
+config['pyramid']['resolutions'] = [32, 64]
 config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_4'
+config['pyramid']['final_upscale_enhancer'] = 'checkpoints/64_512_2'
+
+config['pretrained_model'] = 'checkpoints/pyr_abl_32_64_e2e_r3_fine'
+config['pretrained_model_iteration'] = ''
 
 config['train_dir'] = '/home/workspace/local-data/train'
 config['valid_dir'] = '/home/workspace/local-data/valid'
@@ -40,7 +44,7 @@ config['smpl_res'] = 14475
 if config['is_cape']:
   config['smpl_res'] = 3638
 
-config['lr'] = 0.0001
+config['lr'] = 0.00001
 config['starting_balancing_coeff'] = 0.0001
 config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
 config['avg_garment_path'] = ''
@@ -64,7 +68,7 @@ config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
 config['pyramid']['noise_amount'] = 0.025
 
-config['pyramid']['loss_weights'] = [1,1,1,1,1]
+config['pyramid']['loss_weights'] = [2,1,1,1,1]
 
 for res in config['pyramid']['resolutions']:
   if res != 512:
@@ -149,7 +153,7 @@ for res in config['pyramid']['resolutions']:
     level['decoder_depths'] = [9, 9]
     level['decoder_dims'] = [256, 256]
     level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = ''#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer'] = 'checkpoints/32_512_4'#'checkpoints/up_3_d32_64_2'
     level['upscale_enhancer_freeze'] = True
     config['pyramid']['levels'].append(level)
   else:

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,8 @@
 config = dict()
 
 config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_2'
-config['notes'] = 'continued from pyr_abl_32_skirt-180k'
+config['name'] = 'pyr_abl_32_skirt_r1'
+config['notes'] = ''
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -24,7 +24,10 @@ config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
 config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
 
-config['train_dir'] = '/home/workspace/local-data/train_skirt'
+config['pretrained_model'] = ''
+config['pretrained_model_iteration'] = ''
+
+config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt'
 config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
 config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
 config['batch_size'] = 4
@@ -35,7 +38,7 @@ config['pyramid']['static_model'] = 'checkpoints/static_1_skirt'
 config['pyramid']['body_model'] = 'checkpoints/body_1_skirt_2_2'
 config['pyramid']['curvature_model'] = 'checkpoints/curv_1_skirt'
 
-config['dataset_in_memory'] = False
+config['dataset_in_memory'] = True
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -65,6 +68,7 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
 config['pyramid']['is_label'] = False
 config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
+config['pyramid']['noise_amount'] = 0.001
 
 config['pyramid']['loss_weights'] = [1,1,1,1,1]