fix

aaa_helpers.txt

@@ -1,5 +1,44 @@
 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_cape_m" > nohup/iccv/encoders/body_iccv_1_cape_m.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 auto_encoder_curv.py --name="lhunor_curv_iccv_1_cape_m" > nohup/iccv/encoders/curv_iccv_1_cape_m.out 2>&1 &
+nohup python cvae.py --name="lhunor_cvae_iccv_gnn_1" > nohup/iccv/cvae_iccv_gnn_1.out 2>&1 &
+
+nohup python cvae.py --name="lhunor_abl_all" > nohup/iccv/ablation/abl_all.out 2>&1 &
+nohup python cvae.py --name="lhunor_abl_all_gnn" > nohup/iccv/ablation/abl_all_gnn.out 2>&1 &
+nohup python cvae.py --name="lhunor_abl_all_gnn_3" > nohup/iccv/ablation/abl_all_gnn_3.out 2>&1 &
+
+nohup python upscale_test.py --name="iccv_32_2" > nohup/iccv/upscale/iccv_32_2.out 2>&1 &
+nohup python upscale_test.py --name="iccv_64_2" > nohup/iccv/upscale/iccv_64_2.out 2>&1 &
+nohup python upscale_test.py --name="iccv_128_2" > nohup/iccv/upscale/iccv_128_2.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2" > nohup/iccv/upscale/iccv_256_2.out 2>&1 &
+
+nohup python upscale_test.py --name="iccv_32_2_skirt" > nohup/iccv/upscale/iccv_32_2_skirt.out 2>&1 &
+nohup python upscale_test.py --name="iccv_64_2_skirt" > nohup/iccv/upscale/iccv_64_2_skirt.out 2>&1 &
+nohup python upscale_test.py --name="iccv_128_2_skirt" > nohup/iccv/upscale/iccv_128_2_skirt.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2_skirt" > nohup/iccv/upscale/iccv_256_2_skirt.out 2>&1 &
+
+nohup python upscale_test.py --name="iccv_32_2_cape_f" > nohup/iccv/upscale/iccv_32_2_cape_f_real.out 2>&1 &
+nohup python upscale_test.py --name="iccv_64_2_cape_f" > nohup/iccv/upscale/iccv_64_2_cape_f.out 2>&1 &
+nohup python upscale_test.py --name="iccv_128_2_cape_f" > nohup/iccv/upscale/iccv_128_2_cape_f.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2_cape_f" > nohup/iccv/upscale/iccv_256_2_cape_f.out 2>&1 &
+
+nohup python upscale_test.py --name="iccv_32_2_cape_m" > nohup/iccv/upscale/iccv_32_2_cape_m.out 2>&1 &
+nohup python upscale_test.py --name="iccv_64_2_cape_m" > nohup/iccv/upscale/iccv_64_2_cape_m.out 2>&1 &
+nohup python upscale_test.py --name="iccv_128_2_cape_m" > nohup/iccv/upscale/iccv_128_2_cape_m.out 2>&1 &
+nohup python upscale_test.py --name="iccv_256_2_cape_m" > nohup/iccv/upscale/iccv_256_2_cape_m.out 2>&1 &
+
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32" > nohup/iccv/pyr/iccv_pyr_32.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skirt" > nohup/iccv/pyr/iccv_pyr_32_skirt.out 2>&1 &
 
 skirts!!!!
 pyramid next week

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_body_post import config
+from configs.iccv.config_ae_body_cape_m import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -31,10 +31,11 @@ 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='/home/workspace/local-data/temp')
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_body.py')
     artifact.add_file('losses.py')
@@ -44,7 +45,9 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_smpl_orig=config['is_cape'], is_skirt=config['is_skirt'])
@@ -124,20 +127,26 @@ 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)
 
-        to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
+        if step % 1000 == 0 or (step < 1000 and step % 10 == 0):
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 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)) } }
 
+                
             wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset() 
             
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -150,7 +159,6 @@ 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())
@@ -196,13 +204,15 @@ 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/post/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
-    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
 
     train()

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_curv_post import config
+from configs.iccv.config_ae_curv_cape_m import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -32,12 +32,13 @@ 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='/home/workspace/local-data/temp/')
+        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
         artifact = wandb.Artifact('code', type='code')
         artifact.add_file('auto_encoder_curv.py')
         artifact.add_file('losses.py')
@@ -47,7 +48,9 @@ def init_wandb():
         artifact.add_file('convnext/models/convnext_tf.py')
         config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
         for config_file_name in config_file_names:
-            artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+            file_name = '/'.join(config_file_name.split('.')) + '.py'
+            if os.path.exists(file_name):
+                artifact.add_file(file_name)
         run.log_artifact(artifact)
 
 uv2mesh = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -164,21 +167,26 @@ 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)
 
-        to_log = { **train_loss, **valid_loss }
+        if step % 1000 == 0 or (step < 1000 and step % 10 == 0):
-        if step % 5000 == 0 or (step < 5000 and step % 500 == 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)) } }
 
+                
             wandb.log(to_log, step=step)
-        print(step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -249,11 +257,13 @@ if __name__ == '__main__':
 
     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/post/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
-    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
 
     if testing:
         test()

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_static import config
+from configs.iccv.config_ae_static_cape_m import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -34,10 +34,11 @@ 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='/home/workspace/local-data/temp')
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_static.py')
     artifact.add_file('losses.py')
@@ -47,7 +48,9 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -125,13 +128,16 @@ 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 % 500 == 0):
+            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 }
@@ -140,6 +146,8 @@ def train():
 
                 
             wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -231,14 +239,17 @@ 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')
 
     ckpt_enc = tf.train.Checkpoint(model=model.encoder)
-    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/post/' + config['name'] + '_enc', max_to_keep=20)
+    manager_enc = tf.train.CheckpointManager(ckpt_enc, 'checkpoints/iccv/' + config['name'] + '_enc', max_to_keep=20)
     ckpt_dec = tf.train.Checkpoint(model=model.decoder)
-    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/post/' + config['name'] + '_dec', max_to_keep=20)
+    manager_dec = tf.train.CheckpointManager(ckpt_dec, 'checkpoints/iccv/' + config['name'] + '_dec', max_to_keep=20)
 
     # test()
     train()