fix

aaa_helpers.txt

@@ -1,20 +1,44 @@
-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 &
-
-
-
 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 } })
-            train_figs = plot_everything(batch, 'train')
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-            valid_figs = plot_everything(data_valid, 'valid')
+                train_figs = plot_everything(batch, 'train')
-            to_log = { **to_log, **train_figs, **valid_figs }
+                valid_figs = plot_everything(data_valid, 'valid')
-        if step == 0:
+                to_log = { **to_log, **train_figs, **valid_figs }
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+            if step == 0:
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-        wandb.log(to_log, step=step)  
+                
+            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_1_orig_curv_10_10p_r2_2 import config
+from configs.iccv.config_ae_curv_cape_m import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -31,13 +31,14 @@ 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
+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/', tags=config['tags'])
+        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')
@@ -98,73 +99,46 @@ def dice_dense(prediction, ground_truth, weight_map=None):
 
 
 @tf.function
-def train_step(batch):	
+def train_step(batch):
-    with tf.GradientTape() as tape:	
+    with tf.GradientTape() as tape:
-        pred = model([batch['uv_curvature'], batch['uv_mask']], training=True)	
+        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):
+        ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
-#     with tf.GradientTape() as tape:
+        ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))
-#         pred = model([batch['uv_curvature'], batch['uv_mask']], training=True)
 
-#         ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
+        mesh_pred = uv2mesh(pred) * batch['mesh_mask'][:,:,tf.newaxis]
-#         ms_ssim = tf.reduce_mean(tf.image.ssim(pred, batch['uv_curvature'], max_val=1))
+        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]
+        loss = ce_uv_loss + ce_mesh_loss
-#         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'])
     
-#     gradients = tape.gradient(loss, model.trainable_variables)
+    gradients = tape.gradient(loss, model.trainable_variables)
-#     optimizer.apply_gradients(zip(gradients, 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,
+    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 }
+             'train/dice': dice, 'train/ce_mesh_loss': ce_mesh_loss }
         
 
 
-# @tf.function
+@tf.function
-# def valid_step(batch):
+def valid_step(batch):
-#     pred = model([batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred = model([batch['uv_curvature'], batch['uv_mask']], training=False)
 
-#     ce_uv_loss = scce(tf.math.argmax(batch['uv_curvature'], axis=-1), pred)
+    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))
+    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_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']
+    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)
+    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))
+    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'])
+    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,
+    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 }
+             'valid/dice': dice, 'valid/ce_mesh_loss': ce_mesh_loss }
         
 
 def plot_everything(batch: dict, type: str):
@@ -193,21 +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 } })
-            train_figs = plot_everything(batch, 'train')
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-            valid_figs = plot_everything(data_valid, 'valid')
+                train_figs = plot_everything(batch, 'train')
-            to_log = { **to_log, **train_figs, **valid_figs }
+                valid_figs = plot_everything(data_valid, 'valid')
-        if step == 0:
+                to_log = { **to_log, **train_figs, **valid_figs }
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+            if step == 0:
- 
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
-        wandb.log(to_log, step=step)  
+
-        print(step)
+                
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -235,7 +214,7 @@ 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())
@@ -255,13 +234,12 @@ 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'],
+                                        is_cape=config['is_cape'])
-                                        curv_neighbourhood=config['curv_neighbourhood'])
     static_dataset_train = StaticDataset(folder=config['train_dir'],
                                          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'], 
@@ -270,21 +248,22 @@ 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'],
+                                        is_cape=config['is_cape'])
-                                        curv_neighbourhood=config['curv_neighbourhood'])
     static_dataset_valid = StaticDataset(folder=config['valid_dir'],
                                          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/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'])
@@ -125,27 +128,32 @@ 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 = dict({ **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 } })
-            train_figs = plot_everything(batch, 'train')
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
-            valid_figs = plot_everything(data_valid, 'valid')
+                train_figs = plot_everything(batch, 'train')
-            to_log = { **to_log, **train_figs, **valid_figs }
+                valid_figs = plot_everything(data_valid, 'valid')
-        if step == 0:
+                to_log = { **to_log, **train_figs, **valid_figs }
-            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+            if step == 0:
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-            
+                
-        wandb.log(to_log, step=step)
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
             manager_dec.save(checkpoint_number=step)
 
-        print(step)
+            print(step)
 
         step += 1
 
@@ -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()

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_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,7 +59,7 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = '70000'
+    iteration = ''
 
     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()

configs/archive/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'] = '1'
+config['gpu'] = '4'
 config['name'] = 'al_all_post'
 config['notes'] = ''
 

configs/archive/config_abl_pyr_32.py

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

configs/archive/config_abl_pyr_32_skirt.py

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

configs/archive/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),