evaluate training

aaa_helpers.txt

@@ -1,56 +1,11 @@
+nohup python auto_encoder_static.py --name="lhunor_ae_static_r7_3" > nohup/review/ae_static_r7_3.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_ae_body_r7_3" > nohup/review/ae_body_r7_3.out 2>&1 &
+nohup python auto_encoder_curv.py --name="lhunor_ae_curv_r7_3" > nohup/review/ae_curv_r7_3.out 2>&1 &
+nohup python cvae.py --name="lhunor_abl_all_resnet_r7" > nohup/review/abl_all_resnet_r7.out 2>&1 &
+nohup python calculate_error.py --name abl_all_resnet_r7_70k > nohup/error/abl_all_resnet_r7_70k.out 2>&1 &
+nohup python evaluate_ae.py --name abl_all_resnet_r7_70k > nohup/evaluate/abl_all_resnet_r7_70k.out 2>&1 &
+
 one final convolutional layer for smoothing, on the final coordinates
-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_2.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_2" > nohup/iccv/ablation/abl_all_gnn.out 2>&1 &
-
-nohup python cvae.py --name="lhunor_abl_all_skirt" > nohup/iccv/ablation/abl_all_skirt.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_curv" > nohup/iccv/ablation/abl_curv.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_skin" > nohup/iccv/ablation/abl_skin.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_reg" > nohup/iccv/ablation/abl_reg.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_off" > nohup/iccv/ablation/abl_off.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_skin_curv" > nohup/iccv/ablation/abl_skin_curv.out 2>&1 &
-
-nohup python cvae.py --name="lhunor_abl_skin_gnn" > nohup/iccv/ablation/abl_skin_gnn.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_2.out 2>&1 &
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_skin" > nohup/iccv/pyr/iccv_pyr_32_skin.out 2>&1 &
-
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_64_cape_f" > nohup/iccv/pyr/iccv_pyr_64_cape_f.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_m import config
+from configs.review.config_ae_body 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', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_body.py')
     artifact.add_file('losses.py')
@@ -43,11 +42,9 @@ def init_wandb():
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
     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 +124,23 @@ 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() 
+        if step % 1000 == 0:    
+            wandb.log(to_log, step=step, commit=True)
+        else:
+            wandb.log(to_log, step=step, commit=False)
             
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -159,6 +153,7 @@ 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 +199,13 @@ 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_m import config
+from configs.review.config_ae_curv 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', tags=config['tags'])
         artifact = wandb.Artifact('code', type='code')
         artifact.add_file('auto_encoder_curv.py')
         artifact.add_file('losses.py')
@@ -46,11 +45,9 @@ def init_wandb():
         artifact.add_file('models/cond_encoder.py')
         artifact.add_file('dataset.py')
         artifact.add_file('convnext/models/convnext_tf.py')
-        config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+        config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
         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 +164,24 @@ 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)) } }
-
-                
-            wandb.log(to_log, step=step)
-            train_accumulator.reset()
-            valid_accumulator.reset()
+        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)) } }
+ 
+        if step % 1000 == 0:    
+            wandb.log(to_log, step=step, commit=True)
+        else:
+            wandb.log(to_log, step=step, commit=False)  
+        # print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -214,7 +209,7 @@ 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())
@@ -239,7 +234,7 @@ 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 +248,15 @@ 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.review.config_ae_static import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -34,23 +34,21 @@ 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', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_static.py')
     artifact.add_file('losses.py')
     artifact.add_file('models/base.py')
+    artifact.add_file('models/resnet.py')
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
     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 +126,30 @@ 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()
+        # if step % 1000 == 0:    
+        #     wandb.log(to_log, step=step, commit=True)
+        # else:
+            # wandb.log(to_log, step=step, commit=False)
+        wandb.log(to_log, step=step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
             manager_dec.save(checkpoint_number=step)
 
-            print(step)
+        print(step)
 
         step += 1
 
@@ -239,17 +235,14 @@ 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/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)
 
     # test()
     train()

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_post import config
+from configs.review.config_abl_all import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf

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_ae_static.py

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