convert test set to raw uv as well

aaa_helpers.txt

@@ -1,13 +1,9 @@
-nohup python cvae.py --name="lhunor_weights_test_6" > nohup/iccv/weights_test_6.out 2>&1 &
-nohup python evaluate_ae.py --name iccv_weights_test_6 > nohup/iccv/evaluate_iccv_weights_test_6.out 2>&1 &
-nohup python calculate_error.py --name iccv_weights_test_6 > nohup/iccv/error_iccv_weights_test_6.out 2>&1 &
-nohup python auto_encoder_static.py --name="lhunor_ae_static_iccv_resnet_2" > nohup/iccv/encoders/ae_static_iccv_resnet_2.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_iccv_resnet_2" > nohup/iccv/encoders/ae_curv_iccv_resnet_2.out 2>&1 &
-nohup python auto_encoder_body.py --name="lhunor_ae_body_iccv_resnet_2" > nohup/iccv/encoders/ae_body_iccv_resnet_2.out 2>&1 &
+python merge_data.py -fi '/home/workspace/data/dataset/train' -fo '/home/workspace/local-data/train' -s 0 -e 1500
+nohup python auto_encoder_curv.py --name="lhunor_curv_raw_r2" > nohup/review/curv_raw_r2.out 2>&1 &
+nohup python cvae.py --name="lhunor_abl_all_raw_r2" > nohup/review/abl_all_raw_r2.out 2>&1 &
+nohup python evaluate_ae.py --name abl_all_raw_r2_70k > nohup/evaluate/abl_all_raw_r2_70k.out 2>&1 &
+nohup python calculate_error.py --name error_abl_all_raw_r2 > nohup/error/abl_all_raw_r2_70k.out 2>&1 &
 
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_res_skirt" > nohup/iccv/pyr/iccv_pyr_32_res_skirt.out 2>&1 &
-nohup python evaluate_ae_pyramid.py --name evaluate_iccv_pyr_32_res > nohup/iccv/evaluate/iccv_pyr_32_res.out 2>&1 &
-nohup python evaluate_ae_pyramid.py --name evaluate_iccv_pyr_32_res_skirt > nohup/iccv/evaluate/iccv_pyr_32_res_skirt.out 2>&1 &
 
 one final convolutional layer for smoothing, on the final coordinates
 
@@ -80,7 +76,6 @@ nohup python cvae.py --name="lhunor_abl_skin_var_4" > nohup/ablation/abl_skin_va
 nohup python cvae_curv.py --name="lhunor_cvae_curv" > nohup/ablation/cvae_curv.out 2>&1 &
 nohup python cvae_curv.py --name="lhunor_cvae_curv_2" > nohup/ablation/cvae_curv_2.out 2>&1 &
 
-nohup python cvae_pyramid.py --name="lhunor_iccv_pyr_32_res" > nohup/iccv/pyr/iccv_pyr_32_res.out 2>&1 &
 
 abl_2_pyr_32_64_128
 abl_2_pyr_64_cape_f_03223_SS
@@ -143,7 +138,7 @@ nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_skirt > nohup/
 nohup python evaluate_ae.py --name abl_norm_skirt_70k > nohup/evaluate/abl_norm_skirt_70k.out 2>&1 &
 nohup python calculate_error.py --name error_abl_2_pyr_32_64_128_skirt > nohup/error_ae_abl_skin_skirt_70k.out 2>&1 &
 
-nohup python evaluate_ae_pyramid.py --name pyr_32_res_skirt > nohup/evaluate/pyr_32_res_skirt.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name abl_2_pyr_32_64_100k > nohup/evaluate/abl_2_pyr_32_64_100k.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name abl_2_pyr_32_64_128_80k > nohup/evaluate/abl_2_pyr_32_64_128_80k.out 2>&1 &
 nohup python evaluate_ae_pyramid.py --name abl_2_pyr_32_64_128_256_512_skirt_50k > nohup/evaluate/abl_2_pyr_32_64_128_256_512_skirt_50k.out 2>&1 &
 

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_ae_body 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'])
@@ -63,10 +60,9 @@ def train_step(batch):
 
         e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones((pred.shape[0], 3638 if config['is_cape'] else 14475))))
         l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed' + resolution_modifier] - pred))), axis=1))
-        # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-        ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3))
+        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
 
-        loss = l1_loss
+        loss = 1e3 * (1 - ms_ssim)
 
     metric = tf.reduce_mean(tf.math.sqrt(tf.reduce_sum((mesh_orig - mesh_pred) ** 2, axis=-1)))
     gradients = tape.gradient(loss, model.trainable_variables)
@@ -84,10 +80,9 @@ def valid_step(batch):
 
     e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones((pred.shape[0], 3638 if config['is_cape'] else 14475))))
     l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed' + resolution_modifier] - pred))), axis=1))
-    # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=3))
+    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_body_posed' + resolution_modifier] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
 
-    loss = l1_loss
+    loss = 1e3 * (1 - ms_ssim)
 
     metric = tf.reduce_mean(tf.math.sqrt(tf.reduce_sum((mesh_orig - mesh_pred) ** 2, axis=-1)))
     return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim, }
@@ -129,17 +124,13 @@ 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)
 
-        if step % 50 == 0:
         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 % 100 == 0):
-            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+        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 }
@@ -147,8 +138,6 @@ def train():
             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)
@@ -215,7 +204,5 @@ if __name__ == '__main__':
     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/post/' + config['name'] + '_dec', max_to_keep=20)
-    train_accumulator = Accumulator()
-    valid_accumulator = Accumulator()
 
     train()

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_ae_curv 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/', tags=config['tags'])
         artifact = wandb.Artifact('code', type='code')
         artifact.add_file('auto_encoder_curv.py')
         artifact.add_file('losses.py')
@@ -103,22 +102,18 @@ 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 = tf.reduce_mean(tf.abs(batch['uv_curvature'] - pred))
+        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(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)
+        ce_mesh_loss = tf.reduce_mean(tf.abs(batch['mesh_curvature'] - mesh_pred[:,:,0]))
 
         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'])
-    
     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 }
+    return { 'train/loss': loss, 'train/uv_l1': ce_uv_loss, 'train/ssim': ms_ssim, 
+             'train/mesh_l1': ce_mesh_loss }
         
 
 
@@ -126,35 +121,30 @@ def train_step(batch):
 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 = tf.reduce_mean(tf.abs(batch['uv_curvature'] - pred))
+    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(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)
+    ce_mesh_loss = tf.reduce_mean(tf.abs(batch['mesh_curvature'] - mesh_pred[:,:,0]))
     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'])
-
-    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/uv_l1': ce_uv_loss, 'valid/ssim': ms_ssim, 'valid/mesh_l1': ce_mesh_loss }
         
 
 def plot_everything(batch: dict, type: str):
     pred = model([batch['uv_curvature'], batch['uv_mask']], training=False)
     
-    orig_img = tf.math.argmax(batch['uv_curvature'], axis=-1, output_type=tf.dtypes.int32)
-    pred_img = tf.math.argmax(pred, axis=-1, output_type=tf.dtypes.int32)
+    orig_img = batch['uv_curvature']
+    pred_img = pred
     img = tf.concat((orig_img, pred_img), axis=2).numpy()
 
-    colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, 6+1)])
-    color_img = np.zeros((img.shape[0], img.shape[1], img.shape[2], 3), np.uint8)
-    for i in range(7):
-        color_img[img == i, :] = colors[i]
-    color_img = [wandb.Image(color_img[i]) for i in range(4)]
+    # colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, 6+1)])
+    # color_img = np.zeros((img.shape[0], img.shape[1], img.shape[2], 3), np.uint8)
+    # for i in range(7):
+    #     color_img[img == i, :] = colors[i]
+    # color_img = [wandb.Image(color_img[i]) for i in range(4)]
 
-    imgs = { type + '/images': [wandb.Image(img[i,:,:,np.newaxis] / 6.0) for i in range(img.shape[0])], type + '/color_images': color_img }
+    imgs = { type + '/images': [wandb.Image((img[i,:,:,np.newaxis]-img[i,:,:,np.newaxis].min()) / (img[i,:,:,np.newaxis].max()-img[i,:,:,np.newaxis].min())) for i in range(img.shape[0])],  } # type + '/color_images': color_img
 
     return imgs
 
@@ -167,17 +157,13 @@ 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)
 
-        if step % 50 == 0:
         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 % 100 == 0):
-            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+        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 }
@@ -185,8 +171,7 @@ def train():
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
  
         wandb.log(to_log, step=step)  
-            train_accumulator.reset()
-            valid_accumulator.reset()
+        print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -262,8 +247,6 @@ if __name__ == '__main__':
     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/post/' + config['name'] + '_dec', max_to_keep=20)
-    train_accumulator = Accumulator()
-    valid_accumulator = Accumulator()
 
     if testing:
         test()

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_ae_static import config
+from configs.config_ae_static import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -34,24 +34,20 @@ 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')
     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.')]
     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'])
@@ -68,14 +64,11 @@ def train_step(batch):
 
         e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1))
-        # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-        ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_static'] + 1, max_val=3))
-        # loss = 1e3 * (1 - ms_ssim)
-        loss = l1_loss
+        ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+        loss = 1e3 * (1 - ms_ssim)
 
     metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     gradients = tape.gradient(loss, model.trainable_variables)
-    gradients = [(tf.clip_by_norm(grad, clip_norm=2.0)) for grad in gradients]
     optimizer.apply_gradients(zip(gradients, model.trainable_variables))
     return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim, }
         
@@ -90,10 +83,8 @@ def valid_step(batch):
 
     e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
     l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_static'] - pred)), axis=1))
-    # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_static'] + 1, max_val=3))
-    # loss = 1e3 * (1 - ms_ssim) 
-    loss = l1_loss
+    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 1, batch['uv_static'] + 1, max_val=2, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
+    loss = 1e3 * (1 - ms_ssim)
 
     metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim, }
@@ -134,26 +125,21 @@ 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)
 
-        if step % 50 == 0:
         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 % 100 == 0):
         to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+        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 % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -198,9 +184,9 @@ def test():
     print()
 
 
-
 if __name__ == '__main__':
     init_wandb()
+    # allow_memory_growth()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())
@@ -244,8 +230,6 @@ 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')

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_res import config
+from configs.config_abl_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,21 +59,21 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = '195000'
+    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()
 
 
-    output_folder = '/home/workspace/data/results/iccv/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
 
 
-    # faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')
-    # ids = os.listdir(faces_folder)
-    # ids = [id.split('.')[0] for id in ids]
-    # faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
+    faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')
+    ids = os.listdir(faces_folder)
+    ids = [id.split('.')[0] for id in ids]
+    faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
 
-    masks_folder = '/home/workspace/local-data/test' + ('_skirt' if config['is_skirt'] else '') + '_ready' + ('_2' if config['is_skirt'] else '') + '/mesh_mask'
+    masks_folder = '/home/workspace/data/dataset/test' + ('_skirt' if config['is_skirt'] else '') + '_ready' + ('_2' if config['is_skirt'] else '') + '/mesh_mask'
     ids = os.listdir(masks_folder)
     ids = [id.split('.')[0] for id in ids]
     masks = {id : np.load(masks_folder + '/' + id + '.npy') for id in ids }
@@ -86,7 +86,7 @@ if __name__ == '__main__':
     else:
         gt_name = 'mesh_posed'
 
-    orig_folder = '/home/workspace/local-data/test' + ('_skirt' if config['is_skirt'] else '') + '_ready' + ('_2' if config['is_skirt'] else '') + '/' + gt_name
+    orig_folder = '/home/workspace/data/dataset/test' + ('_skirt' if config['is_skirt'] else '') + '_ready' + ('_2' if config['is_skirt'] else '') + '/' + gt_name
 
     errors = dict()
     if config['is_skirt']:
@@ -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/iccv/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
+    with open('/home/workspace/data/results/errors/post/' + 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()):

compare_models_saved.py

@@ -1,188 +0,0 @@
-import os
-import sys
-from configs.config_abl_all_post import config as config_a
-
-os.environ["CUDA_VISIBLE_DEVICES"] = '5'
-import tensorflow as tf
-
-gpus = tf.config.experimental.list_physical_devices('GPU')
-if gpus:
-    try:
-        # Currently, memory growth needs to be the same across GPUs
-        for gpu in gpus:
-            tf.config.experimental.set_memory_growth(gpu, True)
-        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
-        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
-    except RuntimeError as e:
-        # Memory growth must be set before GPUs have been initialized
-        print(e)
-
-import glob
-import time
-import argparse
-import wandb
-import tqdm
-import random
-import numpy as np
-import plotly.graph_objects as go
-import plotly.express as ex
-from PIL import Image
-from postprocessing import fix_collision
-
-if config_a['is_skirt']:
-    from losses import edge_loss_skirt as edge_loss
-else:
-    from losses import edge_loss
-
-
-
-from losses import collision_ratio, kl_loss #, concept_loss
-# from losses import collision_penalty as collision_penalty
-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 custom_utils.supersmpl_io import writeOBJ
-from plotly.subplots import make_subplots
-
-
-# uv2mesh = UV2Mesh(res=256, is_skirt=config_a['is_skirt'], is_adaptive=False)
-
-
-
-def plot(mesh_gt, pred_a, pred_b, body, mask):
-    fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
-    
-    _, faces_garment = _maskFaces(np.zeros((14475, 3), np.float32), F, mask)
-    faces = np.concatenate((F, faces_garment + 14475), axis=0)
-    mesh_gt = np.concatenate((body, mesh_gt[mask, :]), axis=0)
-    pred_a = np.concatenate((body, pred_a), axis=0)
-    pred_b = np.concatenate((body, pred_b), axis=0)
-    colors = np.concatenate((np.ones_like(body, dtype=np.int32)*100, np.ones_like(mesh_gt, dtype=np.int32)*230), axis=0)
-    # colors = np.ones_like(mesh_gt, dtype=np.int32)*230
-
-    fig.add_trace(go.Mesh3d(
-            x=mesh_gt[:,0],
-            y=mesh_gt[:,2],
-            z=mesh_gt[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Ground Truth",
-            vertexcolor=colors,
-        ),
-        row=1, col=1)
-
-    fig.add_trace(go.Mesh3d(
-            x=pred_a[:,0],
-            y=pred_a[:,2],
-            z=pred_a[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Pred A",
-            vertexcolor=colors,
-        ),
-        row=1, col=2)
-
-    fig.add_trace(go.Mesh3d(
-            x=pred_b[:,0],
-            y=pred_b[:,2],
-            z=pred_b[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Pred B",
-            vertexcolor=colors,
-        ),
-        row=1, col=3)
-
-
-
-    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), 
-                    scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), 
-                    scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), 
-                    )
-    helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
-                yaxis = dict(nticks=4, range=[-1,1],),
-                zaxis = dict(nticks=4, range=[-1,1],),)
-    fig.update_layout(scene = helper,
-                        scene2 = helper,
-                        scene3 = helper,
-                        )
-
-    return fig
-
-
-
-if __name__ == '__main__':
-    run = wandb.init(project='plots', name=config_a['name'], notes=config_a['notes'], dir='/wandb')
-
-    parser = argparse.ArgumentParser(description='')
-    parser.add_argument('--name', type=str)
-    args = vars(parser.parse_args())
-
-    skirt_modifier = '_skirt' if config_a['is_skirt'] else ''
-
-    folder = config_a['test_dir']
-    # smpl = SMPL(use_one_hot=False)
-
-    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
-
-    iteration = ''
-
-    # load_model(model, 'checkpoints/' + 'abl_all_120k')
-
-
-    factory = DatasetFactory()
-    dataset_a = factory.get_dataset(folder=config_a['test_dir'], 
-                                       batch_size=config_a['batch_size'], 
-                                       signature=config_a['signature_dynamic'], 
-                                       resolutions=[config_a['resolution']], 
-                                       in_memory=False, 
-                                       do_repeat=False,
-                                       use_one_hot=config_a['use_one_hot'],
-                                       use_no_orient=config_a['remove_global_orientation'],
-                                       shuffle=False,
-                                       testing=True,
-                                    #    frames_file='frames_abl.txt',
-                                       )
-    static_dataset_a = StaticDataset(folder=config_a['test_dir'], 
-                                        signature=config_a['signature_static'], 
-                                        resolutions=[config_a['resolution']], 
-                                        in_memory=True)
-
-    iterator_a = iter(dataset_a)
-    
-
-    faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config_a['is_skirt'] else '')
-    ids = os.listdir(faces_folder)
-    ids = [id.split('.')[0] for id in ids]
-    faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
-
-    results_folder = '/home/workspace/data/results/post'
-
-    count = 0
-    while True:
-        batch = iterator_a.get_next()
-
-        batch = static_dataset_a.expand_batch(batch_to_dict(batch, config_a['signature_dynamic']))
-
-        mask = batch['mesh_mask'].numpy().astype(bool)
-        gt = batch['mesh_posed'].numpy()
-        body = batch['mesh_body_posed'].numpy()
-
-        for i in range(mask.shape[0]):
-            id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8")
-            pred_a = np.load(results_folder + '/al_all_post-/' + id + '_' + frame_nr + '.npy')
-            pred_b = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
-            # pred_c = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
-
-            fig = plot(gt[i], pred_a, pred_b, body[i], mask[i])
-
-            wandb.log({f'{id}_{frame_nr}': fig}, step = count)
-            count += 1
-
-            print(count)
-

configs/config_abl_all_post.py

@@ -7,7 +7,7 @@ config = dict()
 # DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
 # DON'T FORGET TO CHECK AVG GARMENT USED
 
-config['use_skinning'] =              False # and deshaping
+config['use_skinning'] =              True # and deshaping
 config['remove_global_orientation'] = True
 config['use_curvature'] =             True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
@@ -19,9 +19,10 @@ 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['name'] = 'iccv_weights_test_6'
-config['notes'] = 'smaller weight loss coeff, 1e-6, convolutional weight learning, continued from _5'
+config['gpu'] = '3'
+config['name'] = 'abl_all_raw_r2'
+config['notes'] = ''
+config['tags'] = ['review_2']
 
 config['avg_garment_path'] = 'custom_data/train_no_shape_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']:
@@ -45,7 +46,7 @@ config['test_dir'] = '/home/workspace/data/dataset/test_ready'
 
 config['static_model'] = 'checkpoints/post/static_post_2'
 config['body_model'] = 'checkpoints/post/body_post_2'
-config['curvature_model'] = 'checkpoints/post/curv_post_1'
+config['curvature_model'] = 'checkpoints/post/curv_raw_r2'
 
 
 config['smpl_res'] = 14475
@@ -53,7 +54,7 @@ if config['is_cape']:
   config['smpl_res'] = 3638
 
 
-config['pretrained_model'] = 'checkpoints/post/iccv_weights_test_5'
+config['pretrained_model'] = ''
 
 ###############    
 config['lr'] = 0.0001#                 0.0001
@@ -86,15 +87,14 @@ config['use_one_hot'] = False
 config['cvae'] = dict()
 config['cvae']['is_label'] = False
 config['cvae']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.00001
+config['cvae']['noise_amount'] = 0.001
 
 config['cvae']['kernel_size'] = 7
 config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
 config['cvae']['encoder_dims'] = [32, 64, 128, 256, 64]
 config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
 config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
-config['cvae']['decoder_weights_depths'] = [3, 3, 3, 5, 3]
-config['cvae']['decoder_weights_dims'] = [24, 32, 64, 128, 256]
+
 
 config['cond_ae_static'] = dict()
 config['cond_ae_static']['is_label'] = False

configs/config_ae_curv_post.py

@@ -31,22 +31,18 @@ config['cond_ae']['decoder_dims'] = config['cond_ae']['encoder_dims']
 config['cond_ae']['activation'] = 'tanh'
 
 
-config['gpu'] = '3'
+config['gpu'] = '1'
 config['lr'] = 0.001
-config['name'] = 'curv_post_1'
-config['notes'] = 'convnext + convnext, | \
- \
-| \
-    deeper model | \
-| \
-    ' 
+config['name'] = 'curv_raw_r2'
+config['notes'] = '' 
+config['tags'] = ['review_2']
 
 config['cond_ae']['upscale_output'] = False
 config['pretrained_model'] = ''
 
 
 config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
-                          'uv_curvature': (512, 256, 7),
+                          'uv_curvature': (512, 256, 1),
                           'mesh_curvature':  (config['smpl_res'])
                         }
 config['signature_static'] = { 'mesh_mask': (config['smpl_res'],),

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'] = '0'
+config['gpu'] = '5'
 config['lr'] = 0.0005
 config['name'] = 'static_post_4'
 config['notes'] = 'convnext + convnext, | \

configs/iccv/config_abl_all.py

@@ -1,119 +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'] =              False # 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
-
-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['name'] = 'all_iccv_1'
-config['notes'] = ''
-
-config['avg_garment_path'] = 'custom_data/train_no_shape_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'] = False
-config['dataset_in_memory'] = False
-config['is_cape'] = False
-
-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['frames_file'] = 'frames_dress_30k.txt'
-# config['frames_file_valid'] = 'frames_dress_30k.txt'
-# config['frames_file_test'] = 'frames_dress_30k.txt'
-
-config['static_model'] = 'checkpoints/post/static_r7_3'
-config['body_model'] = 'checkpoints/post/body_r7_3'
-config['curvature_model'] = 'checkpoints/post/curv_r7_3'
-
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-
-config['pretrained_model'] = ''
-
-###############    
-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']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.001
-
-config['cvae']['kernel_size'] = 7
-config['cvae']['features'] = 64*4 # 8*4
-config['cvae']['layer_params'] = [3, 4, 5, 4, 3]
-# config['cond_ae']['layer_params'] = [3, 4, 23, 3, 3]
-
-
-config['cond_ae_static'] = dict()
-config['cond_ae_static']['is_label'] = False
-config['cond_ae_static']['kernel_size'] = 7
-config['cond_ae_static']['bottleneck_size'] = 8*4
-config['cond_ae_static']['layer_params'] = [3, 4, 5, 4, 3]
-# config['cond_ae_static']['layer_params'] = [3, 4, 23, 3, 3]
-config['cond_ae_static']['activation'] = 'tanh'
-
-config['cond_ae_curv'] = dict()
-config['cond_ae_curv']['is_label'] = True
-config['cond_ae_curv']['kernel_size'] = 7
-config['cond_ae_curv']['bottleneck_size'] = 40*4
-config['cond_ae_curv']['layer_params'] = [3, 4, 5, 4, 3]
-# config['cond_ae_curv']['layer_params'] = [3, 4, 23, 3, 3]]
-config['cond_ae_curv']['activation'] = 'tanh'
-
-config['cond_ae_body'] = dict()
-config['cond_ae_body']['is_label'] = False
-config['cond_ae_body']['kernel_size'] = 7
-config['cond_ae_body']['bottleneck_size'] = 16*4
-config['cond_ae_body']['layer_params'] = [3, 4, 5, 4, 3]
-# config['cond_ae_body']['layer_params'] = [3, 4, 23, 3, 3]]
-config['cond_ae_body']['activation'] = 'tanh'

configs/iccv/config_abl_pyr_32_res.py

@@ -1,178 +0,0 @@
-config = dict()
-
-config['gpu'] = '0'
-config['name'] = 'iccv_pyr_32_res'
-config['notes'] = ''
-config['tags'] = ['pyr', 'iccv', 'resnet']
-
-# 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_norm_loss'] =             True
-config['use_curvature'] =             True
-
-config['pretrained_model'] = ''
-config['pretrained_model_iteration'] = ''
-
-config['pyramid'] = dict()
-config['pyramid']['resolutions'] = [32]
-config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['final_upscale_enhancer'] = ''
-
-config['train_dir'] = '/home/workspace/local-data_127/train'
-config['valid_dir'] = '/home/workspace/local-data_127/valid'
-config['test_dir'] = '/home/workspace/local-data/test_ready'
-config['batch_size'] = 4
-config['is_skirt'] = False
-config['is_cape'] = False
-
-config['dataset_in_memory'] = False
-config['resolution'] = None
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-config['lr'] = 0.0001
-config['starting_balancing_coeff'] = 0.001
-config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
-config['avg_garment_path'] = ''
-config['bottleneck_scale'] = 2
-
-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']['add_noise'] = False
-config['pyramid']['noise_amount'] = 0.0
-
-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']['static_model'] = 'checkpoints/post/static_resnet_3'
-config['pyramid']['body_model'] = 'checkpoints/post/body_resnet_3'
-config['pyramid']['curvature_model'] = 'checkpoints/post/curv_resnet_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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 7
-    level['encoder_depths'] = [3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
-    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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 5
-    level['encoder_depths'] = [9, 9, 9, 9]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
-    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/iccv/iccv_'#'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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 5
-    level['encoder_depths'] = [16, 9, 9, 9]
-    level['encoder_dims'] = [64, 128, 128, 64]
-    level['decoder_input'] = (4, 2, 128)
-    level['decoder_depths'] = [16, 9, 9, 9]
-    level['decoder_dims'] = [256, 128, 128, level['latent_dim']]
-    level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 3
-    level['encoder_depths'] = [9, 9]
-    level['encoder_dims'] = [64, level['latent_dim']]
-    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_dims'] = level['encoder_dims']
-    level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#checkpoints/up_3_d64_128_2'
-    level['upscale_enhancer_freeze'] = True
-    config['pyramid']['levels'].append(level)
-  elif res == 32:
-    level = dict()
-    level['resolution'] = 32
-    level['latent_dim'] = 64 * config['bottleneck_scale']
-    level['bottleneck_size'] = 64 * 2
-    level['layer_params'] = [7]
-    level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2'#'checkpoints/up_3_d32_64_2'
-    level['upscale_enhancer_freeze'] = True
-    config['pyramid']['levels'].append(level)
-  else:
-    raise NotImplementedError
-
-config['cond_ae_static'] = dict()
-config['cond_ae_static']['is_label'] = False
-config['cond_ae_static']['kernel_size'] = 7
-config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
-config['cond_ae_static']['activation'] = 'tanh'
-# config['cond_ae']['layer_params'] = [3, 4, 23, 4, 3]
-config['cond_ae_static']['layer_params'] = [3, 7, 15, 7, 3]
-
-config['cond_ae_curv'] = dict()
-config['cond_ae_curv']['is_label'] = True
-config['cond_ae_curv']['kernel_size'] = 7
-config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
-config['cond_ae_curv']['activation'] = 'tanh'
-config['cond_ae_curv']['layer_params'] = [3, 7, 15, 7, 3]
-
-config['cond_ae_body'] = dict()
-config['cond_ae_body']['is_label'] = False
-config['cond_ae_body']['kernel_size'] = 7
-config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
-config['cond_ae_body']['activation'] = 'tanh'
-config['cond_ae_body']['layer_params'] = [3, 7, 15, 7, 3]

configs/iccv/config_abl_pyr_32_res_skirt.py

@@ -1,178 +0,0 @@
-config = dict()
-
-config['gpu'] = '0'
-config['name'] = 'iccv_pyr_32_res_skirt'
-config['notes'] = ''
-config['tags'] = ['pyr', 'iccv', 'resnet']
-
-# 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_norm_loss'] =             True
-config['use_curvature'] =             True
-
-config['pretrained_model'] = ''
-config['pretrained_model_iteration'] = ''
-
-config['pyramid'] = dict()
-config['pyramid']['resolutions'] = [32]
-config['pyramid']['pretrained_pyramid'] = ''
-config['pyramid']['final_upscale_enhancer'] = ''
-
-config['train_dir'] = '/home/workspace/local-data_128/train_skirt'
-config['valid_dir'] = '/home/workspace/local-data_127/valid_skirt'
-config['test_dir'] = '/home/workspace/local-data/test_skirt_ready_2'
-config['batch_size'] = 4
-config['is_skirt'] = True
-config['is_cape'] = False
-
-config['dataset_in_memory'] = False
-config['resolution'] = None
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-config['lr'] = 0.0001
-config['starting_balancing_coeff'] = 0.001
-config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
-config['avg_garment_path'] = ''
-config['bottleneck_scale'] = 2
-
-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']['add_noise'] = False
-config['pyramid']['noise_amount'] = 0.0
-
-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']['static_model'] = 'checkpoints/post/static_resnet_3'
-config['pyramid']['body_model'] = 'checkpoints/post/body_resnet_3'
-config['pyramid']['curvature_model'] = 'checkpoints/post/curv_resnet_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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 7
-    level['encoder_depths'] = [3, 3, 9, 3]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
-    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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 5
-    level['encoder_depths'] = [9, 9, 9, 9]
-    level['encoder_dims'] = [32, 64, 128, level['latent_dim']]
-    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/iccv/iccv_'#'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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 5
-    level['encoder_depths'] = [16, 9, 9, 9]
-    level['encoder_dims'] = [64, 128, 128, 64]
-    level['decoder_input'] = (4, 2, 128)
-    level['decoder_depths'] = [16, 9, 9, 9]
-    level['decoder_dims'] = [256, 128, 128, level['latent_dim']]
-    level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#'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'] = 64 * config['bottleneck_scale']
-    level['kernel_size'] = 3
-    level['encoder_depths'] = [9, 9]
-    level['encoder_dims'] = [64, level['latent_dim']]
-    level['decoder_depths'] = level['encoder_depths']
-    level['decoder_dims'] = level['encoder_dims']
-    level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_'#checkpoints/up_3_d64_128_2'
-    level['upscale_enhancer_freeze'] = True
-    config['pyramid']['levels'].append(level)
-  elif res == 32:
-    level = dict()
-    level['resolution'] = 32
-    level['latent_dim'] = 64 * config['bottleneck_scale']
-    level['bottleneck_size'] = 64 * 2
-    level['layer_params'] = [7]
-    level['avg_garment_path'] = ''
-    level['upscale_enhancer'] = 'checkpoints/iccv/iccv_32_2_skirt'#'checkpoints/up_3_d32_64_2'
-    level['upscale_enhancer_freeze'] = True
-    config['pyramid']['levels'].append(level)
-  else:
-    raise NotImplementedError
-
-config['cond_ae_static'] = dict()
-config['cond_ae_static']['is_label'] = False
-config['cond_ae_static']['kernel_size'] = 7
-config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
-config['cond_ae_static']['activation'] = 'tanh'
-# config['cond_ae']['layer_params'] = [3, 4, 23, 4, 3]
-config['cond_ae_static']['layer_params'] = [3, 7, 15, 7, 3]
-
-config['cond_ae_curv'] = dict()
-config['cond_ae_curv']['is_label'] = True
-config['cond_ae_curv']['kernel_size'] = 7
-config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
-config['cond_ae_curv']['activation'] = 'tanh'
-config['cond_ae_curv']['layer_params'] = [3, 7, 15, 7, 3]
-
-config['cond_ae_body'] = dict()
-config['cond_ae_body']['is_label'] = False
-config['cond_ae_body']['kernel_size'] = 7
-config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
-config['cond_ae_body']['activation'] = 'tanh'
-config['cond_ae_body']['layer_params'] = [3, 7, 15, 7, 3]

configs/iccv/config_ae_body.py

@@ -1,48 +0,0 @@
-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'] = False
-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'] = 16 * 2
-config['cond_ae']['layer_params'] = [3, 7, 15, 7, 3]
-config['cond_ae']['activation'] = 'tanh'
-
-
-config['gpu'] = '3'
-config['lr'] = 0.0001
-config['name'] = 'body_resnet_3'
-config['notes'] = '' 
-config['tags'] = ['iccv', 'resnet']
-
-config['cond_ae']['upscale_output'] = False
-config['pretrained_model'] = ''
-
-
-config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
-                          'pose_shape': (72 + 11,),
-                          'uv_body_posed': (3, 512, 256,),
-                          'mesh_body_posed': (config['smpl_res'], 3,),
-                        }
-config['signature_static'] = { 
-                         'mesh_mask': (config['smpl_res'],),
-                        }

configs/iccv/config_ae_curv.py

@@ -1,48 +0,0 @@
-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'] = False
-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'] = True
-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'] = 40 * 2
-config['cond_ae']['layer_params'] = [3, 7, 15, 7, 3]
-config['cond_ae']['activation'] = 'tanh'
-
-
-
-config['gpu'] = '2'
-config['lr'] = 0.001
-config['name'] = 'curv_resnet_3'
-config['notes'] = '' 
-config['tags'] = ['iccv', 'resnet']
-
-config['cond_ae']['upscale_output'] = False
-config['pretrained_model'] = ''
-
-
-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/iccv/config_ae_static.py

@@ -1,49 +0,0 @@
-config = dict()
-
-
-config['batch_size'] = 4 ##################################### CHANGE CHANGE CHANGE CHANGE CHANGE CHANGE CHANGE
-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*2 # 8*4
-# config['cond_ae']['layer_params'] = [3, 4, 23, 4, 3]
-config['cond_ae']['layer_params'] = [3, 7, 15, 7, 3]
-config['cond_ae']['activation'] = 'tanh'
-
-
-config['gpu'] = '1'
-config['lr'] = 3e-4
-config['name'] = 'static_resnet_3'
-config['notes'] = ''
-config['tags'] = ['iccv', 'resnet', 'static']
-
-    
-
-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/review/config_abl_all.py

@@ -1,126 +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
-
-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['name'] = 'abl_all_resnet_r7'
-config['notes'] = ''
-
-config['avg_garment_path'] = 'custom_data/train_no_shape_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'] = False
-config['dataset_in_memory'] = False
-config['is_cape'] = False
-
-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['frames_file'] = 'frames_dress_30k.txt'
-# config['frames_file_valid'] = 'frames_dress_30k.txt'
-# config['frames_file_test'] = 'frames_dress_30k.txt'
-
-config['static_model'] = 'checkpoints/post/static_r7_3'
-config['body_model'] = 'checkpoints/post/body_r7_3'
-config['curvature_model'] = 'checkpoints/post/curv_r7_3'
-
-
-config['smpl_res'] = 14475
-if config['is_cape']:
-  config['smpl_res'] = 3638
-
-
-config['pretrained_model'] = ''
-
-###############    
-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']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.001
-
-config['cvae']['kernel_size'] = 7
-config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
-config['cvae']['encoder_dims'] = [32, 64, 128, 256, 64]
-config['cvae']['decoder_depths'] = config['cvae']['encoder_depths']
-config['cvae']['decoder_dims'] = config['cvae']['encoder_dims']
-
-
-config['cond_ae_static'] = dict()
-config['cond_ae_static']['is_label'] = False
-config['cond_ae_static']['kernel_size'] = 7
-config['cond_ae_static']['bottleneck_size'] = 8
-config['cond_ae_static']['encoder_depths'] = [3, 3, 3, 9, 3]
-config['cond_ae_static']['encoder_dims'] = [16, 32, 64, 64, config['cond_ae_static']['bottleneck_size']]
-config['cond_ae_static']['decoder_depths'] = config['cond_ae_static']['encoder_depths']
-config['cond_ae_static']['decoder_dims'] = config['cond_ae_static']['encoder_dims']
-config['cond_ae_static']['activation'] = 'tanh'
-
-config['cond_ae_curv'] = dict()
-config['cond_ae_curv']['is_label'] = True
-config['cond_ae_curv']['kernel_size'] = 7
-config['cond_ae_curv']['bottleneck_size'] = 40
-config['cond_ae_curv']['encoder_depths'] = [3, 3, 9, 9, 3]
-config['cond_ae_curv']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_curv']['bottleneck_size']]
-config['cond_ae_curv']['decoder_depths'] = config['cond_ae_curv']['encoder_depths']
-config['cond_ae_curv']['decoder_dims'] = config['cond_ae_curv']['encoder_dims']
-config['cond_ae_curv']['activation'] = 'tanh'
-
-config['cond_ae_body'] = dict()
-config['cond_ae_body']['is_label'] = False
-config['cond_ae_body']['kernel_size'] = 7
-config['cond_ae_body']['bottleneck_size'] = 16
-config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3]
-config['cond_ae_body']['encoder_dims'] = [16, 32, 64, 128, config['cond_ae_body']['bottleneck_size']]
-config['cond_ae_body']['decoder_depths'] = config['cond_ae_body']['encoder_depths']
-config['cond_ae_body']['decoder_dims'] = config['cond_ae_body']['encoder_dims']
-config['cond_ae_body']['activation'] = 'tanh'

configs/review/config_ae_body.py

@@ -1,51 +0,0 @@
-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'] = False
-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'] = 16
-config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
-config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, 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'] = 'tanh'
-
-
-config['gpu'] = '4'
-config['lr'] = 0.0001
-config['name'] = 'body_r7_3'
-config['notes'] = 'resnet18' 
-config['tags'] = ['review_7']
-
-config['cond_ae']['upscale_output'] = False
-config['pretrained_model'] = ''
-
-
-config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
-                          'pose_shape': (72 + 11,),
-                          'uv_body_posed': (3, 512, 256,),
-                          'mesh_body_posed': (config['smpl_res'], 3,),
-                        }
-config['signature_static'] = { 
-                         'mesh_mask': (config['smpl_res'],),
-                        }

configs/review/config_ae_curv.py

@@ -1,50 +0,0 @@
-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'] = False
-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'] = True
-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'] = 40
-config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
-config['cond_ae']['encoder_dims'] = [16, 32, 64, 128, 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'] = 'tanh'
-
-
-config['gpu'] = '3'
-config['lr'] = 0.001
-config['name'] = 'curv_r7_3'
-config['notes'] = 'resnet18' 
-config['tags'] = ['review_7']
-
-config['cond_ae']['upscale_output'] = False
-config['pretrained_model'] = ''
-
-
-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/review/config_ae_static.py

@@ -1,51 +0,0 @@
-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'] = '6'
-config['lr'] = 0.0005
-config['name'] = 'static_r7_3'
-config['notes'] = 'resnet18 based, one more block'
-config['tags'] = ['review_7']
-
-    
-
-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,),
-                        }

convert_to_uv.py

@@ -266,7 +266,9 @@ def convert_to_uv_batch(res, m2uv, uv_map, verts, neighbours=15, mask=None, meth
 
 def convert_to_uv_batch_label(res, m2uv, uv_map, values, neighbours=15, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=None):
     batch = values.shape[0]
-    values = (values + 1) * mask
+    x = np.zeros((batch,14475))
+    x[:,mask] = values
+    values = x
     values_uv = np.zeros((batch, res * 2, res))
     missing = np.zeros((res * 2, res))
     uv_values = np.zeros((batch, uv_map.shape[0]))
@@ -314,7 +316,8 @@ def convert_to_uv_batch_label(res, m2uv, uv_map, values, neighbours=15, mask=Non
     final = []
     for i in range(batch):
         print('processing frame: ' + str(i))
-        interpolator =  spi.NearestNDInterpolator(x=uv_map_discreet_unique_unique, y=unique_uv_values[i,:])
+        # interpolator =  spi.NearestNDInterpolator(x=uv_map_discreet_unique_unique, y=unique_uv_values[i,:])
+        interpolator =  spi.RBFInterpolator(y=uv_map_discreet_unique_unique, d=unique_uv_values[i,:], neighbors=neighbours, kernel='linear')
         final.append(interpolator(rbf_dest_current))
     final = np.asarray(final)
 
@@ -450,7 +453,7 @@ if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/data/dataset/train')
     parser.add_argument("-s", "--start", help = "start of range", default=0)
-    parser.add_argument("-e", "--end", help = "end of range", default=10)
+    parser.add_argument("-e", "--end", help = "end of range", default=1)
     parser.add_argument("-n", "--name", help = "end of range", default='lhunor')
     parser.add_argument("-sk", "--skirt", help = "end of range", default=0)
     args = parser.parse_args()
@@ -526,17 +529,17 @@ if __name__ == '__main__':
         offsets_static = sio.loadmat(os.path.join(folder, id, garment + '_offsets_static.mat'))['label'][:,:3]
         body_static = sio.loadmat(os.path.join(garment_dir, 'info_body.mat'))['B']
         mask = np.squeeze(sio.loadmat(os.path.join(garment_dir, garment + '_mask.mat'))['mask'].astype(bool))
-        body = readPC2(os.path.join(folder, id, 'Body_posed.pc16'),  True)['V']
+        # body = readPC2(os.path.join(folder, id, 'Body_posed.pc16'),  True)['V']
         # gt = readPC2(os.path.join(folder, id, garment + '_registered.pc16'),  True)['V']
-        # curvature = np.load(os.path.join(folder, id, 'curvature_label_' + curvature_label_type + '.npy'))
+        curvature = np.load(os.path.join(folder, id, 'curvature_25_raw.npy'))
         # mesh_unposed = [np.load(os.path.join(folder, id, 'mesh_unposed',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # mesh_unposed = np.stack([mesh_unposed[i]['mesh_unposed'] for i in range(gt.shape[0])])
         # mesh_unposed_no_shape = [np.load(os.path.join(folder, id, 'mesh_unposed_no_shape',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # mesh_unposed_no_shape = np.stack([mesh_unposed_no_shape[i]['mesh_unposed_no_shape'] for i in range(gt.shape[0])])
         # body_no_orient = [np.load(os.path.join(folder, id, 'mesh_posed_body_no_orient',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # body_no_orient = np.stack([body_no_orient[i]['mesh_posed_body_no_orient'] for i in range(gt.shape[0])])
-        mesh_unposed_no_shape_one_hot = [np.load(os.path.join(folder, id, 'mesh_unposed_no_shape_one_hot',  id + '_' + str(i) + '.npz')) for i in range(body.shape[0])]
-        mesh_unposed_no_shape_one_hot = np.stack([mesh_unposed_no_shape_one_hot[i]['mesh_unposed_no_shape'] for i in range(body.shape[0])])
+        # mesh_unposed_no_shape_one_hot = [np.load(os.path.join(folder, id, 'mesh_unposed_no_shape_one_hot',  id + '_' + str(i) + '.npz')) for i in range(body.shape[0])]
+        # mesh_unposed_no_shape_one_hot = np.stack([mesh_unposed_no_shape_one_hot[i]['mesh_unposed_no_shape'] for i in range(body.shape[0])])
 
 
         verts_static = (body_static + offsets_static) # * mask[:, np.newaxis]
@@ -608,10 +611,10 @@ if __name__ == '__main__':
         # uv_body = convert_to_uv_batch(uv_res, m2uv, uv_map, body[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_posed_body_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, body_no_orient[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_gt = convert_to_uv_batch(uv_res, m2uv, uv_map, gt[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
-        # uv_curvature = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='nearest', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        uv_curvature_raw = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed_no_shape = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
-        uv_unposed_no_shape_one_hot = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape_one_hot[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        # uv_unposed_no_shape_one_hot = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape_one_hot[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_shaped_body = convert_to_uv(uv_res, m2uv, uv_map, shaped_body, neighbours=3, mask=None, method='rbf', garment_uv_mask=None).astype(np.float32)
         print(time.perf_counter() - start)
 
@@ -632,9 +635,9 @@ if __name__ == '__main__':
         # for i in range(uv_gt.shape[0]):
         #     np.savez_compressed(os.path.join(folder, id, 'gt_uv', garment + '_' + str(i) + '.npz'), uv_gt=uv_gt[i, :, :, :])
 
-        # os.makedirs(os.path.join(folder, id, 'curvature_uv'), exist_ok=True)
-        # for i in range(uv_curvature.shape[0]):
-        #     np.savez_compressed(os.path.join(folder, id, 'curvature_uv', garment + '_' + str(i) + '.npz'), curvature_uv=uv_curvature[i, :, :])
+        os.makedirs(os.path.join(folder, id, 'curvature_uv_raw'), exist_ok=True)
+        for i in range(uv_curvature_raw.shape[0]):
+            np.savez_compressed(os.path.join(folder, id, 'curvature_uv_raw', garment + '_' + str(i) + '.npz'), curvature_uv_raw=uv_curvature_raw[i, :, :])
 
         # os.makedirs(os.path.join(folder, id, 'uv_unposed'), exist_ok=True)
         # for i in range(uv_unposed.shape[0]):
@@ -644,9 +647,9 @@ if __name__ == '__main__':
         # for i in range(uv_unposed_no_shape.shape[0]):
         #     np.savez_compressed(os.path.join(folder, id, 'uv_unposed_no_shape', garment + '_' + str(i) + '.npz'), uv_unposed_no_shape=uv_unposed_no_shape[i, :, :, :])
 
-        os.makedirs(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot'), exist_ok=True)
-        for i in range(uv_unposed_no_shape_one_hot.shape[0]):
-            np.savez_compressed(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot', garment + '_' + str(i) + '.npz'), uv_unposed_no_shape=uv_unposed_no_shape_one_hot[i, :, :, :])
+        # os.makedirs(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot'), exist_ok=True)
+        # for i in range(uv_unposed_no_shape_one_hot.shape[0]):
+        #     np.savez_compressed(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot', garment + '_' + str(i) + '.npz'), uv_unposed_no_shape=uv_unposed_no_shape_one_hot[i, :, :, :])
 
         # os.makedirs(os.path.join(folder, id, 'uv_shaped_body'), exist_ok=True)
         # np.savez_compressed(os.path.join(folder, id, 'uv_shaped_body.npz'), uv_shaped_body=uv_shaped_body)

convert_to_uv_local.py

@@ -416,7 +416,7 @@ def test(verts, faces, values):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/data/dataset/train')
+    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/local-data/train')
     parser.add_argument("-s", "--start", help = "start of range", default=0)
     parser.add_argument("-e", "--end", help = "end of range", default=10)
     parser.add_argument("-n", "--name", help = "end of range", default='lhunor')
@@ -499,15 +499,15 @@ if __name__ == '__main__':
         mask = np.load(os.path.join(local_folder, 'mesh_mask', id + '.npy')).astype(bool)
         # body = readPC2(os.path.join(folder, id, 'Body_posed.pc16'),  True)['V']
         # gt = readPC2(os.path.join(folder, id, garment + '_registered.pc16'),  True)['V']
-        # curvature = np.load(os.path.join(folder, id, 'curvature_label_' + curvature_label_type + '.npy'))
+        curvature = np.load(os.path.join(folder, id, 'curvature_raw.npy'))
         # mesh_unposed = [np.load(os.path.join(folder, id, 'mesh_unposed',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # mesh_unposed = np.stack([mesh_unposed[i]['mesh_unposed'] for i in range(gt.shape[0])])
         # mesh_unposed_no_shape = [np.load(os.path.join(folder, id, 'mesh_unposed_no_shape',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # mesh_unposed_no_shape = np.stack([mesh_unposed_no_shape[i]['mesh_unposed_no_shape'] for i in range(gt.shape[0])])
         # body_no_orient = [np.load(os.path.join(folder, id, 'mesh_posed_body_no_orient',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # body_no_orient = np.stack([body_no_orient[i]['mesh_posed_body_no_orient'] for i in range(gt.shape[0])])
-        mesh_unposed_no_shape_one_hot = [np.load(os.path.join(local_folder, 'mesh_unposed_no_shape_one_hot',  id + '_' + str(i) + '.npz')) for i in range(frames)]
-        mesh_unposed_no_shape_one_hot = np.stack([mesh_unposed_no_shape_one_hot[i]['mesh_unposed_no_shape'] for i in range(frames)])
+        # mesh_unposed_no_shape_one_hot = [np.load(os.path.join(local_folder, 'mesh_unposed_no_shape_one_hot',  id + '_' + str(i) + '.npz')) for i in range(frames)]
+        # mesh_unposed_no_shape_one_hot = np.stack([mesh_unposed_no_shape_one_hot[i]['mesh_unposed_no_shape'] for i in range(frames)])
 
 
         # verts_dynamic = gt
@@ -561,10 +561,10 @@ if __name__ == '__main__':
         # uv_body = convert_to_uv_batch(uv_res, m2uv, uv_map, body[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_posed_body_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, body_no_orient[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_gt = convert_to_uv_batch(uv_res, m2uv, uv_map, gt[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
-        # uv_curvature = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='nearest', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        uv_curvature_raw = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed_no_shape = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
-        uv_unposed_no_shape_one_hot = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape_one_hot[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        # uv_unposed_no_shape_one_hot = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape_one_hot[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_shaped_body = convert_to_uv(uv_res, m2uv, uv_map, shaped_body, neighbours=3, mask=None, method='rbf', garment_uv_mask=None).astype(np.float32)
         print(time.perf_counter() - start)
 
@@ -585,9 +585,9 @@ if __name__ == '__main__':
         # for i in range(uv_gt.shape[0]):
         #     np.savez_compressed(os.path.join(folder, id, 'gt_uv', garment + '_' + str(i) + '.npz'), uv_gt=uv_gt[i, :, :, :])
 
-        # os.makedirs(os.path.join(folder, id, 'curvature_uv'), exist_ok=True)
-        # for i in range(uv_curvature.shape[0]):
-        #     np.savez_compressed(os.path.join(folder, id, 'curvature_uv', garment + '_' + str(i) + '.npz'), curvature_uv=uv_curvature[i, :, :])
+        os.makedirs(os.path.join(folder, id, 'curvature_uv_raw'), exist_ok=True)
+        for i in range(uv_curvature_raw.shape[0]):
+            np.savez_compressed(os.path.join(folder, id, 'curvature_uv_raw', garment + '_' + str(i) + '.npz'), curvature_uv_raw=uv_curvature_raw[i, :, :])
 
         # os.makedirs(os.path.join(folder, id, 'uv_unposed'), exist_ok=True)
         # for i in range(uv_unposed.shape[0]):
@@ -597,9 +597,9 @@ if __name__ == '__main__':
         # for i in range(uv_unposed_no_shape.shape[0]):
         #     np.savez_compressed(os.path.join(folder, id, 'uv_unposed_no_shape', garment + '_' + str(i) + '.npz'), uv_unposed_no_shape=uv_unposed_no_shape[i, :, :, :])
 
-        os.makedirs(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot'), exist_ok=True)
-        for i in range(uv_unposed_no_shape_one_hot.shape[0]):
-            np.savez_compressed(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot', garment + '_' + str(i) + '.npz'), uv_unposed_no_shape=uv_unposed_no_shape_one_hot[i, :, :, :])
+        # os.makedirs(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot'), exist_ok=True)
+        # for i in range(uv_unposed_no_shape_one_hot.shape[0]):
+        #     np.savez_compressed(os.path.join(folder, id, 'uv_unposed_no_shape_one_hot', garment + '_' + str(i) + '.npz'), uv_unposed_no_shape=uv_unposed_no_shape_one_hot[i, :, :, :])
 
         # os.makedirs(os.path.join(folder, id, 'uv_shaped_body'), exist_ok=True)
         # np.savez_compressed(os.path.join(folder, id, 'uv_shaped_body.npz'), uv_shaped_body=uv_shaped_body)

convert_to_uv_local_single.py

@@ -202,7 +202,9 @@ def convert_to_uv_batch(res, m2uv, uv_map, verts, neighbours=15, mask=None, meth
 
 def convert_to_uv_batch_label(res, m2uv, uv_map, values, neighbours=15, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=None):
     batch = values.shape[0]
-    values = (values + 1) * mask
+    x = np.zeros((batch,14475))
+    x[:,mask] = values
+    values = x
     values_uv = np.zeros((batch, res * 2, res))
     missing = np.zeros((res * 2, res))
     uv_values = np.zeros((batch, uv_map.shape[0]))
@@ -250,7 +252,8 @@ def convert_to_uv_batch_label(res, m2uv, uv_map, values, neighbours=15, mask=Non
     final = []
     for i in range(batch):
         print('processing frame: ' + str(i))
-        interpolator =  spi.NearestNDInterpolator(x=uv_map_discreet_unique_unique, y=unique_uv_values[i,:])
+        interpolator =  spi.RBFInterpolator(y=uv_map_discreet_unique_unique, d=unique_uv_values[i,:], neighbors=neighbours, kernel='linear')
+        # interpolator =  spi.NearestNDInterpolator(x=uv_map_discreet_unique_unique, y=unique_uv_values[i,:])
         final.append(interpolator(rbf_dest_current))
     final = np.asarray(final)
 
@@ -384,16 +387,17 @@ def test(verts, faces, values):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/local-data/valid')
+    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/local-data/train')
     parser.add_argument("-s", "--start", help = "start of range", default=0)
     parser.add_argument("-e", "--end", help = "end of range", default=1500)
     parser.add_argument("-n", "--name", help = "end of range", default='lhunor')
-    parser.add_argument("-sk", "--skirt", help = "end of range", default=1)
+    parser.add_argument("-sk", "--skirt", help = "end of range", default=0)
     args = parser.parse_args()
 
     # smpl = SMPL('FeatureLines/superSMPL')
 
     local_folder = args.folder 
+    remote_folder = '/home/workspace/data/dataset/test'
     os.makedirs(os.path.join(local_folder, 'uv_posed_no_orient'), exist_ok=True)
     # os.makedirs(os.path.join(local_folder, 'uv_unposed_no_shape_one_hot_2'), exist_ok=True)
 
@@ -461,7 +465,7 @@ if __name__ == '__main__':
         mask = np.load(os.path.join(local_folder, 'mesh_mask', id + '.npy')).astype(bool)
         # body = readPC2(os.path.join(folder, id, 'Body_posed.pc16'),  True)['V']
         # gt = readPC2(os.path.join(folder, id, garment + '_registered.pc16'),  True)['V']
-        # curvature = np.load(os.path.join(folder, id, 'curvature_label_' + curvature_label_type + '.npy'))
+        curvature = np.load(os.path.join(remote_folder, id, 'curvature_25_raw.npy'))
         # mesh_unposed = [np.load(os.path.join(folder, id, 'mesh_unposed',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
         # mesh_unposed = np.stack([mesh_unposed[i]['mesh_unposed'] for i in range(gt.shape[0])])
         # mesh_unposed_no_shape = [np.load(os.path.join(folder, id, 'mesh_unposed_no_shape',  id + '_' + str(i) + '.npz')) for i in range(gt.shape[0])]
@@ -470,8 +474,8 @@ if __name__ == '__main__':
         # body_no_orient = np.stack([body_no_orient[i]['mesh_posed_body_no_orient'] for i in range(gt.shape[0])])
         # mesh_unposed_no_shape_one_hot = [np.load(os.path.join(local_folder, 'mesh_unposed_no_shape_one_hot',  id + '_' + str(i) + '.npz')) for i in range(frames)]
         # mesh_unposed_no_shape_one_hot = [mesh_unposed_no_shape_one_hot[i]['mesh_unposed_no_shape'] for i in range(frames)]
-        mesh_posed_no_orient = [np.load(os.path.join(local_folder, 'mesh_posed_no_orient',  id + '_' + str(i) + '.npz')) for i in range(frames)]
-        mesh_posed_no_orient = [mesh_posed_no_orient[i]['mesh_posed_no_orient'] for i in range(frames)]
+        # mesh_posed_no_orient = [np.load(os.path.join(local_folder, 'mesh_posed_no_orient',  id + '_' + str(i) + '.npz')) for i in range(frames)]
+        # mesh_posed_no_orient = [mesh_posed_no_orient[i]['mesh_posed_no_orient'] for i in range(frames)]
 
 
         # verts_dynamic = gt
@@ -491,11 +495,11 @@ if __name__ == '__main__':
         # uv_body = convert_to_uv_batch(uv_res, m2uv, uv_map, body[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_posed_body_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, body_no_orient[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_gt = convert_to_uv_batch(uv_res, m2uv, uv_map, gt[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
-        # uv_curvature = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='nearest', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        uv_curvature_raw = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed_no_shape = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
         # uv_unposed_no_shape_one_hot = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape_one_hot, neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border, id=id)
-        uv_posed_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_posed_no_orient, neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border, id=id)
+        # uv_posed_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_posed_no_orient, neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border, id=id)
         # uv_shaped_body = convert_to_uv(uv_res, m2uv, uv_map, shaped_body, neighbours=3, mask=None, method='rbf', garment_uv_mask=None).astype(np.float32)
         print(time.perf_counter() - start)
 
@@ -516,9 +520,9 @@ if __name__ == '__main__':
         # for i in range(uv_gt.shape[0]):
         #     np.savez_compressed(os.path.join(folder, id, 'gt_uv', garment + '_' + str(i) + '.npz'), uv_gt=uv_gt[i, :, :, :])
 
-        # os.makedirs(os.path.join(folder, id, 'curvature_uv'), exist_ok=True)
-        # for i in range(uv_curvature.shape[0]):
-        #     np.savez_compressed(os.path.join(folder, id, 'curvature_uv', garment + '_' + str(i) + '.npz'), curvature_uv=uv_curvature[i, :, :])
+        os.makedirs(os.path.join(local_folder, 'curvature_uv_raw'), exist_ok=True)
+        for i in range(uv_curvature_raw.shape[0]):
+            np.savez_compressed(os.path.join(local_folder, 'curvature_uv_raw', id + '_' + str(i) + '.npz'), curvature_uv_raw=uv_curvature_raw[i, :, :])
 
         # os.makedirs(os.path.join(folder, id, 'uv_unposed'), exist_ok=True)
         # for i in range(uv_unposed.shape[0]):

convnext/models/convnext_tf.py

@@ -2,7 +2,7 @@ from unittest import skip
 import numpy as np
 import tensorflow as tf
 from tensorflow.keras.layers import (Conv2D, Conv2DTranspose, Dense, DepthwiseConv2D,
-                                     GlobalAveragePooling2D, Layer, Activation, Lambda,
+                                     GlobalAveragePooling2D, Layer,
                                      LayerNormalization, Flatten, Reshape, UpSampling2D)
 
 def drop_path(inputs, drop_prob, is_training):
@@ -222,7 +222,7 @@ class ConvNeXtReverse(tf.keras.Model):
 
     def __init__(self, 
                  depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], kernel_size=7,
-                 drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1., learn_weights=False,
+                 drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1.,
                  ):
         super().__init__()
         self.upsample_layers = []  # stem and 3 intermediate downsampling conv layers
@@ -255,18 +255,12 @@ class ConvNeXtReverse(tf.keras.Model):
             self.stages.append(stage)
             cur += depths[i]
 
-        if not learn_weights:
         self.last = Dense(3, activation='tanh')
-        else:
-            self.last = Activation('softmax')
-            # self.last = Dense(24, activation='softmax')
-
 
     def call(self, x, training):
         for i in reversed(range(len(self.upsample_layers))):
             x = self.upsample_layers[i](x, training=training)
             x = self.stages[i](x, training=training)
-
         x = self.last(x, training=training)
         return x
 
@@ -344,7 +338,7 @@ class ConvNeXtReverseLabels(tf.keras.Model):
     """
 
     def __init__(self, 
-                 depths=[3, 3, 9, 3], dims=[96, 192, 384, 768],
+                 depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], kernel_size=7,
                  drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1.,
                  nr_of_classes=7):
         super().__init__()
@@ -366,14 +360,14 @@ class ConvNeXtReverseLabels(tf.keras.Model):
         cur = 0
         for i in range(len(depths)):
             stage = tf.keras.Sequential(
-                [Block(dim=dims[i], drop_path=dp_rates[cur + j],
+                [Block(dim=dims[i], drop_path=dp_rates[cur + j], kernel_size=kernel_size,
                        layer_scale_init_value=layer_scale_init_value, prefix=f'block{i}') for j in range(depths[i])]
             )
             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(1, activation='sigmoid')
 
     def call(self, x, training):
         for i in reversed(range(len(self.downsample_layers))):

curvature_labels.py

@@ -275,6 +275,7 @@ def read_raw_curvatures(folder):
             continue
 
         curv = np.load(garment_dir + '/curvature_25_raw.npy')
+        print(curv.max())
         curvatures_all.append(curv)
     
     return curvatures_all
@@ -282,24 +283,24 @@ def read_raw_curvatures(folder):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument("-f", "--folder", help = "process the given folder", default=r'/home/workspace/data/dataset/test')
+    parser.add_argument("-f", "--folder", help = "process the given folder", default=r'/home/workspace/data/dataset/train')
     parser.add_argument("-s", "--start", help = "start of range", default=0)
     parser.add_argument("-e", "--end", help = "end of range", default=1500)
     parser.add_argument("-n", "--name", help = "end of range", default="lhunor")
     args = parser.parse_args()
 
-    F = np.load("FeatureLines/superSMPL/smpl_faces.npy")
+    # F = np.load("FeatureLines/superSMPL/smpl_faces.npy")
     # k_neighbours(k=25)
 
     folder = args.folder
     nr_of_labels = 6
     neighbourhood = 25
     temp_file = 'temp/' + ''.join(random.choice(string.ascii_lowercase) for i in range(10)) + '.ply'
-    dist = np.load('MeshUtils/dijsktra.npy')
+    # dist = np.load('MeshUtils/dijsktra.npy')
     # dist = np.load('MeshUtils/dijkstra_skirt.npy')
 
-    generate_curvatures(folder, neighbourhood)
-    # curvatures = read_raw_curvatures(folder)
+    # generate_curvatures(folder, neighbourhood)
+    curvatures = read_raw_curvatures(folder)
     # bins = get_bins(curvatures, nr_of_labels)
     # np.save('train_bins_skirt.npy', bins)
     # bins = np.load('train_bins.npy')

custom_utils/custom_utils.py

@@ -2,7 +2,6 @@ import json
 import numpy as np
 import tensorflow as tf
 import scipy as sp
-import cmapy as cm
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
 
@@ -217,35 +216,6 @@ def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, colli
     return fig
 
 
-def plot_weights(weights, body, faces):
-    fig = go.Figure()
-    colors = np.array([cm.color('jet', 1 - w) for w in weights.numpy()])
-
-    # if flip_xy:
-    #     mesh_gt = flip_axis(mesh_gt)
-    #     mesh_pred_unposed = flip_axis(mesh_pred_unposed)
-    #     collision = flip_axis(collision, ind=14475)
-
-    fig.add_trace(go.Mesh3d(
-                x=body[:,0],
-                y=body[:,2],
-                z=body[:,1],
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors
-            ))
-    
-
-    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),)
-    helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
-                yaxis = dict(nticks=4, range=[-1,1],),
-                zaxis = dict(nticks=4, range=[-1,1],),)
-    fig.update_layout(scene = helper,)
-
-    return fig
-
-
 def plot_3d_collision(gt, collision_1, collision_2, collision_faces, collision_color, flip_xy=False):
     fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
 
@@ -433,27 +403,3 @@ def group_inputs_for_levels(batch, config):
         levels_input.append([uv_orig, batch['uv_static' + res_modifier], batch['uv_body_posed' + res_modifier], batch['uv_curvature' + res_modifier], batch['uv_mask' + res_modifier], batch['uv_mask']])
     conds = [batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature']]
     return levels_input, conds
-
-
-
-
-
-class Accumulator():
-    def __init__(self):
-        self.dict = dict()
-
-    def update(self, dict):
-        for key in dict.keys():
-            if key in self.dict.keys():
-                self.dict[key].append(dict[key])
-            else:
-                self.dict[key] = [dict[key]]
-
-    def get(self):
-        result = dict()
-        for key in self.dict.keys():
-            result[key] = np.mean(self.dict[key])
-        return result
-
-    def reset(self):
-        self.dict = dict()

custom_utils/smpl.py

@@ -406,8 +406,7 @@ class SMPL:
         return T_out, J_out
 
 
-    def run_garment_with_weights(self, pose, betas, v_cloth, weights, J=None):
-        R = self.run_rodrigues(pose)
+    def run_garment_with_weights(self, R, betas, v_cloth, weights, J=None):
         
         if J is None:
             J = self.get_joints_template(betas)
@@ -431,12 +430,13 @@ class SMPL:
             J = tf.gather(J, tf.constant([0, 1, 2], tf.int32), axis=1)
             
             T = tf.tensordot(weights, results, axes=((1), (0)))
-            rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.shape[0], 1), dtype=tf.float32)), axis=1)
+            rest_shape_h = tf.concat((v_cloth, tf.ones((v_cloth.get_shape().as_list()[0], 1), dtype=tf.float32)), axis=1)
             v = tf.matmul(T, tf.reshape(rest_shape_h, (-1, 4, 1)))
             v = tf.reshape(v, (-1, 4))[:, :3]
 
             return v, tf.squeeze(J)
 
+        # gender = tf.cast(tf.greater_equal(betas[:, 10] , 0), tf.int32)
         T_out, J_out = tf.map_fn(single_run, (R, J, v_cloth, weights), (tf.float32, tf.float32))
         
         J0 = tf.reshape(J_out[:,0,:], (-1, 1, 3))

cvae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_abl_all import config
+from configs.config_abl_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -38,14 +38,14 @@ else:
 from losses import collision_ratio, kl_loss, normal_loss #, concept_loss
 # from losses import collision_penalty as collision_penalty
 from losses import collision_loss as collision_penalty
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, UV2MeshLabel, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision, plot_weights
+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 CVAENew as CVAE
 
 
 def init_wandb():
-    run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb')
+    run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('cvae.py')
     artifact.add_file('models/cvae_model.py')
@@ -64,7 +64,6 @@ def init_wandb():
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
-uv2mesh_label = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
 
 
 def kl_loss(mean, logvar):
@@ -74,12 +73,6 @@ def kl_loss(mean, logvar):
     return kl_loss
 
 
-def blend_weights_reg(pred_w, gender=None):
-    orig = smpl.weights
-    l1 = tf.reduce_mean(tf.abs(pred_w - orig[None, 0, :, :]))
-    return l1
-
-
 # 3d loss on posed !!!!!!!!!!!!
 
 @tf.function
@@ -91,10 +84,9 @@ def train_step(batch):
         else:
             mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-        pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
+        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
 
         mesh_pred = uv2mesh(pred)
-        mesh_weigths = uv2mesh_label(weights)
 
         if config['use_skinning']:
             shape = batch['pose_shape'][:, 72:]
@@ -104,31 +96,25 @@ def train_step(batch):
             mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
             mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
         else:
-            shape = batch['pose_shape'][:, 72:]
-            gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-            shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-            mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
+            mesh_pred_posed = mesh_pred
 
         # is the output already masked?
 
         e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
         c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-        # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
         l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
         n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
         # conc_loss = concept_loss(pred, batch['uv_unposed'])
         kl = kl_loss(mean, logvar)
-        weights_l = blend_weights_reg(mesh_weigths)
 
-        reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
+        reconstr_loss = l2_loss
         if config['use_extra_losses']:
             if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True:
-                reconstr_loss = reconstr_loss + (e_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff']
             else:
-                reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
         if config['use_norm_loss'] and step > 2000:
             reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
@@ -138,14 +124,14 @@ def train_step(batch):
         logvar = tf.reduce_mean(logvar)
 
     # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     gradients = tape.gradient(loss, model.trainable_variables)
     optimizer.apply_gradients(zip(gradients, model.trainable_variables))
     return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
              'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio,
              'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
-             'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss, 'train/weights_loss': weights_l,
-             # 'train/ms_ssim': ms_ssim, 'train/l2_loss': l2_loss, 
+             'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
+             # 'train/ms_ssim': ms_ssim, 
             }
 
 
@@ -156,10 +142,9 @@ def valid_step(batch):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
-    mesh_weigths = uv2mesh_label(weights)
 
     if config['use_skinning']:
         shape = batch['pose_shape'][:, 72:]
@@ -169,28 +154,22 @@ def valid_step(batch):
         mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
     else:
-        shape = batch['pose_shape'][:, 72:]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
+        mesh_pred_posed = mesh_pred
 
     # is the output already masked?
 
     e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
     c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
     c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-    # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+    l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
     l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
     n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
     # conc_loss = concept_loss(pred, batch['uv_unposed'])
     kl = kl_loss(mean, logvar)
-    weights_l = blend_weights_reg(mesh_weigths)
 
-    reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
+    reconstr_loss = l2_loss
     if config['use_extra_losses']:
-        reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+        reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
     if config['use_norm_loss']:
         reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
@@ -200,12 +179,12 @@ def valid_step(batch):
     logvar = tf.reduce_mean(logvar)
 
     # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     # c_ratio = tf.reduce_mean(collision_ratio(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
 
     return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric, 
              'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/collision_ratio': c_ratio,
-             'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar, 'valid/weights_loss': weights_l,
+             'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
               'valid/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim, 
               }
 
@@ -217,7 +196,7 @@ def test_step(batch):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
     
-    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
 
@@ -231,7 +210,7 @@ def test_step(batch):
         mesh_orig_shaped = mesh_orig + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_orig_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_orig_shaped)
     else:
-        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights)
+        mesh_pred_posed = mesh_pred
         mesh_orig_posed = mesh_orig
     
     mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
@@ -273,10 +252,9 @@ def plot_everything(batch: dict, type: str):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
     
     mesh_pred = uv2mesh(pred).numpy()
-    mesh_weigths = uv2mesh_label(weights)
     
     orig_img = uv_orig
     uv_static_img = batch['uv_static']
@@ -301,12 +279,7 @@ def plot_everything(batch: dict, type: str):
             mesh_pred[i, mask[i], :] += shape_offsets.numpy()[i, mask[i], :]
         mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred).numpy()
     else:
-        shape = batch['pose_shape'][:, 72:]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-        mesh_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths).numpy()
+        mesh_posed = mesh_pred
         gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
         garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
 
@@ -325,16 +298,13 @@ def plot_everything(batch: dict, type: str):
     collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(garment_posed))]
     collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(garment_posed))]
 
-    # figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], garment_posed[i], faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
-    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i],) for i in range(4) }
-    figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i],) for i in range(4) }
-    figs_weights = { type + '/weights_' + str(i): plot_weights(mesh_weigths[0,:,i], body[0], F) for i in range(24) }
-    # figs_weights = { type + '/weights_' + str(i): plot_weights(smpl.weights[0,:,i], body[0], F) for i in range(24) }
+    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
+    figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
 
     mean_hist = wandb.Histogram(sequence=mean.numpy().mean(axis=0))
     logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0))
 
-    return { **figs, **figs_coll, **figs_weights, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
+    return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
 
 
 def sample(folder): 
@@ -457,6 +427,8 @@ def sample(folder):
 
 
 
+
+
 def test():
     str_split = config['name'].split('_')
     test_idx = str_split.index('test')

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_res_skirt import config
+from configs.post.config_abl_pyr_64_128_5 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -43,11 +43,10 @@ from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
 from models.pyramid_model_optimized import PyramidNew as Pyramid
 from postprocessing import fix_collision
-from custom_utils.custom_utils import Accumulator
 
 
 def init_wandb():
-    run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
+    run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags'])
 
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('cvae_pyramid.py')
@@ -60,11 +59,9 @@ 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.post.')]
     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'])
@@ -793,9 +790,7 @@ if __name__ == '__main__':
     # generate_results()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/iccv/' + config['name'], max_to_keep=20)
-    train_accumulator = Accumulator()
-    valid_accumulator = Accumulator()
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -851,32 +846,31 @@ if __name__ == '__main__':
 
 
         train_loss = train_step(batch)
-        train_accumulator.update(train_loss)
 
-        if step % 25 == 0:
         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 % 100 == 0):
-            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
-            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+        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)) } }
-
-            to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
-                
-            wandb.log(to_log, step=step)
-            train_accumulator.reset()
-            valid_accumulator.reset()
 
         if step % 5000 == 0:
             manager.save(checkpoint_number=step)
+        if step == 0:
+            to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+
+        if train_loss['train/euclid_error'] < 0.004:
+            if balancing_activated_step == 0:
+                balancing_activated_step = step
+            balancing_coeff = balancing_coeff + 1 / 20000
+
+
+        to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
+        
+        wandb.log(to_log, step = step)
 
         print(step)
 

dataset.py

@@ -176,7 +176,7 @@ class DatasetFactory():
             elif key == 'frame_nr':
                 tf_signature.append(tf.TensorSpec(shape = (), dtype = tf.string))
             elif key == 'mesh_curvature':
-                tf_signature.append(tf.TensorSpec(shape = signature[key], dtype = tf.int32))
+                tf_signature.append(tf.TensorSpec(shape = signature[key], dtype = tf.float32))
             else:
                 tf_signature.append(tf.TensorSpec(shape = signature[key], dtype = tf.float32))
         return tf_signature
@@ -260,8 +260,8 @@ class DatasetFactory():
 
 
             if 'mesh_curvature' in signature.keys():
-                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)
+                mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature_raw', id + separator + frame_nr + '.npz')); mesh_curvature = mesh_curvature['mesh_curvature_raw']
+                item['mesh_curvature'] = mesh_curvature
 
 
             for res in resolutions:
@@ -270,13 +270,13 @@ class DatasetFactory():
                     res_string = '_' + str(res)
 
                 if 'uv_curvature' + res_string in signature.keys():
-                    uv_curvature = np.load(os.path.join(folder, 'uv_curvature' + res_string, id + separator + frame_nr + '.npz')); 
+                    uv_curvature = np.load(os.path.join(folder, 'curvature_uv_raw' + res_string, id + separator + frame_nr + '.npz')); 
                     if res_string != '':
                         uv_curvature = uv_curvature['uv_curvature'] 
                     else:
-                        uv_curvature = uv_curvature['curvature_uv']
-                    uv_curvature = tf.one_hot(uv_curvature, 7)
-                    item['uv_curvature' + res_string] = uv_curvature
+                        uv_curvature = uv_curvature['curvature_uv_raw']
+                    # uv_curvature = tf.one_hot(uv_curvature, 7)
+                    item['uv_curvature' + res_string] = uv_curvature[:,:,tf.newaxis]
 
                 if 'uv_unposed' + res_string in signature.keys():
                     uv_unposed_no_shape = np.load(os.path.join(folder, 'uv_unposed_no_shape' + one_hot_2 + res_string, id + separator + frame_nr + '.npz')); uv_unposed_no_shape = uv_unposed_no_shape['uv_unposed_no_shape']
@@ -370,8 +370,8 @@ if __name__ == '__main__':
                         #   'mesh_unposed': (14475, 3,),
                           'uv_unposed': (512, 256, 3),
                         #   'uv_unposed_32': (3, 32, 16,),
-                          'uv_curvature': (512, 256, 7),
-                        #   'mesh_curvature':  (14475)
+                          'uv_curvature': (512, 256, 1),
+                          'mesh_curvature':  (14475)
                         }
     signature_static = { #'uv_static': (3, 512, 256,),
                         #  'uv_static_32': (3, 32, 16,),
@@ -381,15 +381,14 @@ if __name__ == '__main__':
                         #  'uv_shaped_body': (3, 512, 256,),
                           }
 
-    dataset = factory.get_dataset(folder='/home/workspace/local-data/train_skirt',
+    dataset = factory.get_dataset(folder='/home/workspace/local-data/train',
                                   batch_size=1,
                                   signature=signature_dynamic,
                                   resolutions=[512],
                                   do_repeat=False,
                                   use_one_hot=False,
-                                  is_cape=False,
-                                  frames_file='frames_dress_30k.txt')
-    static_dataset = StaticDataset(folder='/home/workspace/local-data/train_skirt',
+                                  is_cape=False,)
+    static_dataset = StaticDataset(folder='/home/workspace/local-data/train',
                                    signature=signature_static,
                                    resolutions=[512],
                                   is_cape=False)
@@ -404,7 +403,7 @@ if __name__ == '__main__':
     for i, batch in enumerate(dataset):
         print(i)
         batch = static_dataset.expand_batch(batch_to_dict(batch, signature_dynamic))
-        ex.imshow(batch['uv_curvature'][0].numpy().argmax(-1) / 6.0).show()
+        ex.imshow(batch['uv_curvature'][0,:,:,0].numpy()).show()
         sum_uv += batch['uv_unposed'].numpy().sum(axis=0)
         sum_mask += batch['uv_mask'].numpy().sum(axis=0)
 

docker/Dockerfile

@@ -2,41 +2,9 @@ FROM tensorflow/tensorflow:2.9.0-gpu
 
 RUN apt-get update
 RUN apt-get upgrade -y
-
-# Add the current user to the image
-ARG USER_NAME=lhunor
-ARG USER_ID=11017
-ARG GROUP_NAME=guest
-ARG GROUP_ID=11000
-
-# Update the system and install required packages
-RUN apt-get update && apt-get upgrade -y && apt-get install -y sudo git
-
-# Create a new group with the same GID as the host
-RUN groupadd --gid $GROUP_ID $GROUP_NAME
-
-# Create a new user with the same UID and GID as the host
-RUN useradd --uid $USER_ID --gid $GROUP_ID --shell /bin/bash --create-home $USER_NAME
-
-# don't require password with sudo, for convenience
-# not the safest thing to do, but hopefully okay inside the container
-RUN echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers
-
-# Add the new user to the sudo group
-RUN usermod -aG sudo $USER_NAME
-
-# Set the default user to the new user
-USER $USER_NAME
-
-WORKDIR //home-net
-
 RUN apt-get install git ffmpeg libsm6 libxext6 libopenexr-dev zip unzip htop nano -y
 RUN pip install numpy matplotlib opencv-python wandb OpenEXR tensorflow-graphics scipy plotly pandas tensorboardX opencv-python cmapy
 
-# defining the volumes that will be mounted
-VOLUME [ "/data-net" ]
-VOLUME [ "/data-local" ]
-VOLUME [ "/home-net" ]
 
-# Start the container with a bash shell
-CMD ["/bin/bash"]
+WORKDIR /home/workspace/data
+# RUN wandb login

evaluate_ae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_abl_all import config
+from configs.config_abl_all_post import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -39,7 +39,7 @@ else:
 from losses import collision_ratio, kl_loss #, concept_loss
 # from losses import collision_penalty as collision_penalty
 from losses import collision_loss as collision_penalty
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, UV2MeshLabel, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
+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 CVAENew as CVAE
@@ -48,7 +48,6 @@ from custom_utils.supersmpl_io import writeOBJ
 
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
-uv2mesh_label = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
 
 @tf.function
 def step(batch):
@@ -57,10 +56,9 @@ def step(batch):
     else:
         uv_orig =  batch['uv_posed']
     
-    pred, _, _, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, _, _ = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
-    mesh_weigths = uv2mesh_label(weights)
 
     if config['use_skinning']:
         shape = batch['pose_shape'][:, 72:]
@@ -70,13 +68,7 @@ def step(batch):
         mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
     else:
-        shape = batch['pose_shape'][:, 72:]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
-
+        mesh_pred_posed = mesh_pred
         
     # mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
 

evaluate_ae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.iccv.config_abl_pyr_32_res_skirt import config
+from configs.config_abl_2_pyr_32_64_128_256_512 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -27,7 +27,7 @@ import numpy as np
 import plotly.graph_objects as go
 import plotly.express as ex
 from PIL import Image
-from models.pyramid_model_optimized import PyramidNew as Pyramid
+from models.pyramid_model_optimized import Pyramid
 from postprocessing import fix_collision
 
 if config['is_skirt']:
@@ -97,12 +97,12 @@ if __name__ == '__main__':
     ids = [id.split('_')[0] for id in ids]
     ids = set(ids)
 
-    iteration = '170000'
+    iteration = '50000'
 
-    load_model(model, 'checkpoints/iccv/' + checkpoint_name, iteration=iteration)
+    load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')
 
-    output_folder = '/home/workspace/data/results/iccv/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
 
 
     os.makedirs(output_folder, exist_ok=True)

merge_data.py

@@ -179,7 +179,7 @@ if __name__ == '__main__':
         start = time.perf_counter()
         # offsets_static = sio.loadmat(os.path.join(folder, id, garment + '_offsets_static.mat'))['label'][:,:3]
         # body_static = sio.loadmat(os.path.join(garment_dir, 'info_body.mat'))['B']
-        # mask = np.squeeze(sio.loadmat(os.path.join(garment_dir, garment + '_mask.mat'))['mask'].astype(bool))
+        mask = np.squeeze(sio.loadmat(os.path.join(garment_dir, garment + '_mask.mat'))['mask'].astype(bool))
         # verts_static = (body_static + offsets_static) * mask[:, np.newaxis]
         # # dfassert verts_static.min() > -1 and verts_static.max() < 1
 
@@ -257,10 +257,12 @@ if __name__ == '__main__':
         # for i in range(body_posed.shape[0]):
         #     shutil.copyfile(os.path.join(garment_dir, 'curvature_uv', garment + '_' + str(i) + '.npz'), os.path.join(output_folder, 'uv_curvature', id + '_' + str(i) + '.npz'))
        
-        os.makedirs(os.path.join(output_folder, 'mesh_curvature'), exist_ok=True)
-        mesh_curvature = np.load(os.path.join(garment_dir, 'curvature_label_6_25.npy'))
+        os.makedirs(os.path.join(output_folder, 'mesh_curvature_raw'), exist_ok=True)
+        data = np.load(os.path.join(garment_dir, 'curvature_25_raw.npy'))
+        mesh_curvature_raw = np.zeros((data.shape[0], 14475), dtype=np.float32)
+        mesh_curvature_raw[:, mask] = data
         for i in range(pose.shape[1]):
-            np.savez_compressed(os.path.join(output_folder, 'mesh_curvature', id + '_' + str(i) + '.npz'), mesh_curvature=mesh_curvature[i])
+            np.savez_compressed(os.path.join(output_folder, 'mesh_curvature_raw', id + '_' + str(i) + '.npz'), mesh_curvature_raw=mesh_curvature_raw[i])
        
 
         # os.makedirs(os.path.join(output_folder, 'uv_posed_body_no_orient'), exist_ok=True)

models/base.py

@@ -1,7 +1,5 @@
 import tensorflow as tf
 from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block, ConvNeXtReverseLabels
-from models.resnet import resnet_18, make_basic_block_layer, resnet_34, resnet_50, resnet_101, resnet_152
-
 
 class Bottleneck(tf.keras.Model):
     
@@ -113,34 +111,20 @@ class Decoder(tf.keras.Model):
 
 class VariationalEncoderNew(tf.keras.Model):
     
-    def __init__(self, layer_params, features):
+    def __init__(self, depths, dims, kernel_size=7):
         super(VariationalEncoderNew, self).__init__()
 
-        self.encoder = resnet_18(layer_params, features)
+        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
 
-        self.mean_branch = tf.keras.Sequential([
-            tf.keras.layers.Conv2D(filters=features,
-                                            kernel_size=(3, 3),
-                                            strides=1,
-                                            padding="same"),
-            tf.keras.layers.BatchNormalization(),
-            tf.keras.layers.Conv2D(filters=features,
-                                            kernel_size=(3, 3),
-                                            strides=1,
-                                            padding="same")
-        ])
+        self.mean_branch = tf.keras.Sequential(
+                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
+            )
 
-        self.var_branch = tf.keras.Sequential([
-            tf.keras.layers.Conv2D(filters=features,
-                                            kernel_size=(3, 3),
-                                            strides=1,
-                                            padding="same"),
-            tf.keras.layers.BatchNormalization(),
-            tf.keras.layers.Conv2D(filters=features,
-                                            kernel_size=(3, 3),
-                                            strides=1,
-                                            padding="same")
-        ])
+        self.var_branch = tf.keras.Sequential(
+                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
+            )
 
         self.flatten_mean = tf.keras.layers.Flatten()
         self.flatten_var = tf.keras.layers.Flatten()
@@ -163,10 +147,10 @@ class VariationalEncoderNew(tf.keras.Model):
 
 class AEEncoderNew(tf.keras.Model):
     
-    def __init__(self, layer_params, features, activation='tanh'):
+    def __init__(self, depths, dims, kernel_size=7, activation='tanh'):
         super(AEEncoderNew, self).__init__()
 
-        self.encoder = resnet_18(layer_params, features)
+        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
         self.act = tf.keras.layers.Activation(activation)
 
 
@@ -187,15 +171,15 @@ class AEEncoderNew(tf.keras.Model):
 
 class DecoderNew(tf.keras.Model):
     
-    def __init__(self, layer_params, features, is_label=False, is_cvae=False, learn_weights=False):
+    def __init__(self, depths, dims, kernel_size=7, is_label=False):
         super(DecoderNew, self).__init__()
 
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = resnet_18(layer_params, features, reversed=True, is_cvae=is_cvae)
+            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
         else:
-            self.decoder = resnet_18(layer_params, features, reversed=True, labels=6, is_cvae=is_cvae)
+            self.decoder = ConvNeXtReverseLabels(depths=depths, dims=dims, nr_of_classes=7)
             
 
     def call(self, inputs, training):
@@ -206,13 +190,7 @@ class DecoderNew(tf.keras.Model):
 
         x = self.decoder(x, training=training)
 
-        if self.is_label:
-            x = x * mask[:,:,:,tf.newaxis]
-
-            background = tf.ones((mask.shape[0],512,256,1)) * (1 - mask[:,:,:,tf.newaxis])
-            x = tf.concat((background, x), axis=-1)
-
-            x = tf.math.softmax(x)
+        # if self.is_label:
 
         if len(inputs) == 2:
             if len(mask.shape) == 2:

models/cond_encoder.py

@@ -25,8 +25,8 @@ class AutoEncoderNew(tf.keras.Model):
     def __init__(self, config):
         super(AutoEncoderNew, self).__init__()
 
-        self.encoder : AEEncoderNew = AEEncoderNew(config['layer_params'], config['bottleneck_size'], config['activation'])
-        self.decoder : DecoderNew = DecoderNew(config['layer_params'], config['bottleneck_size'], is_label=config['is_label'])
+        self.encoder : AEEncoderNew = AEEncoderNew(config['encoder_depths'], config['encoder_dims'], config['kernel_size'], config['activation'])
+        self.decoder : DecoderNew = DecoderNew(config['decoder_depths'], config['decoder_dims'], kernel_size=config['kernel_size'], is_label=config['is_label'])
 
 
     def call(self, inputs, training):

models/cvae_model.py

@@ -159,16 +159,16 @@ class CVAENew(tf.keras.Model):
         self.size = config['resolution']
 
         if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
-            self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['bottleneck_size'], config['cond_ae_static']['activation'])
+            self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['encoder_depths'], config['cond_ae_static']['encoder_dims'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'])
             if config['static_model'] != '':
                 load_model(self.static_enc, config['static_model'] + '_enc')
 
-            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['bottleneck_size'])
+            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_size'])
             if config['body_model'] != '':
                 load_model(self.body_enc, config['body_model'] + '_enc')
 
         if config['use_curvature']:
-            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['bottleneck_size'], config['cond_ae_curv']['activation'])
+            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'])
             if config['curvature_model'] != '':
                 load_model(self.curv_enc, config['curvature_model'] + '_enc')
 
@@ -181,11 +181,8 @@ class CVAENew(tf.keras.Model):
 
         self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
         self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
-        self.decoder_weights = DecoderNew(config['cvae']['decoder_weights_depths'], config['cvae']['decoder_weights_dims'], config['cvae']['kernel_size'], learn_weights=True)
-        self.encoder = VariationalEncoderNew(config['cvae']['encoder_dims'][-1])
-        self.decoder = DecoderNew(config['cvae']['decoder_dims'][-1], is_cvae=True)
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, config['cvae']['decoder_dims'][-1]))
+        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
 
         if config['avg_garment_path'] != '':
             self.avg_garment = np.load(config['avg_garment_path'])
@@ -196,12 +193,12 @@ class CVAENew(tf.keras.Model):
         self.noise_amount = config['cvae']['noise_amount']
         self.use_curvature = config['use_curvature']
         self.only_curvatures = config['only_curvatures'] if 'only_curvatures' in config.keys() and config['only_curvatures'] == True else None
-        self.use_offsets_over_body = False
+        self.use_offsets_over_body = not config['use_skinning']
 
         if self.use_offsets_over_body:
             assert self.avg_garment is None, 'When we are not using skinning, we can\'t use avg_garment!'
-        # if self.avg_garment is not None:
-        #     assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
+        if self.avg_garment is not None:
+            assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
 
     # @tf.function
     def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
@@ -217,7 +214,6 @@ class CVAENew(tf.keras.Model):
         z = tf.concat([eps, z_cond], axis=-1)
 
         x = self.decoder(z, training=False)
-        weights = self.decoder_weights(z, training=False)
         
         if self.avg_garment is not None:
             x = x + self.avg_garment[tf.newaxis,:,:,:]
@@ -227,7 +223,7 @@ class CVAENew(tf.keras.Model):
 
         x = x * uv_mask[:,:,:,tf.newaxis]
 
-        return x, weights
+        return x
 
 
     def reparameterize(self, mean, logvar, training, fix_noise=False):
@@ -276,7 +272,6 @@ class CVAENew(tf.keras.Model):
 
         z = tf.concat([z, z_cond], axis=-1)
         x = self.decoder(z, training=training)
-        weights = self.decoder_weights(z, training=training)
 
         if self.avg_garment is not None:
             x = x + self.avg_garment[tf.newaxis,:,:,:]
@@ -286,5 +281,5 @@ class CVAENew(tf.keras.Model):
 
         x = x * uv_mask[:,:,:,tf.newaxis]
 
-        return x, mean, logvar, weights
+        return x, mean, logvar
 

models/pyramid_level.py

@@ -102,8 +102,8 @@ class PyramidLevelNew(tf.keras.Model):
         super(PyramidLevelNew, self).__init__()
         self.size = config['resolution']
 
-        self.encoder = VariationalEncoderNew(config['layer_params'], config['bottleneck_size'])
-        self.decoder = DecoderNew(config['layer_params'], config['bottleneck_size'])
+        self.encoder = VariationalEncoderNew(config['encoder_depths'], config['encoder_dims'], kernel_size=config['kernel_size'])
+        self.decoder = DecoderNew(config['decoder_depths'], config['decoder_dims'], config['kernel_size'])
 
         self.upscale_enhancer = None
         if config['upscale_enhancer'] != '':
@@ -117,7 +117,7 @@ class PyramidLevelNew(tf.keras.Model):
         else:
             self.avg_garment = None
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, config['bottleneck_size']))
+        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
 
 
     def enhance(self, low, mask, training=None):

models/pyramid_model_optimized.py

@@ -256,15 +256,15 @@ class PyramidNew(tf.keras.Model):
     def __init__(self, config):
         super(PyramidNew, self).__init__()
 
-        self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['layer_params'], config['cond_ae_static']['bottleneck_size'], config['cond_ae_static']['activation'])
+        self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['encoder_depths'], config['cond_ae_static']['encoder_dims'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'])
         if config['pyramid']['static_model'] != '':
             load_model(self.static_enc, config['pyramid']['static_model'] + '_enc')
 
-        self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['layer_params'], config['cond_ae_body']['bottleneck_size'], config['cond_ae_static']['activation'])
+        self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_size'])
         if config['pyramid']['body_model'] != '':
             load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
 
-        self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['layer_params'], config['cond_ae_curv']['bottleneck_size'], config['cond_ae_curv']['activation'])
+        self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'])
         if config['pyramid']['curvature_model'] != '':
             load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
 

models/resnet.py

@@ -1,307 +0,0 @@
-# taken from https://github.com/calmisential/TensorFlow2.0_ResNet/blob/master/models/resnet.py
-
-import tensorflow as tf
-
-
-class BasicBlock(tf.keras.layers.Layer):
-
-    def __init__(self, filter_num, stride=1, upsample=False):
-        super(BasicBlock, self).__init__()
-        if not upsample:
-            self.conv1 = tf.keras.layers.Conv2D(filters=filter_num,
-                                                kernel_size=(3, 3),
-                                                strides=stride,
-                                                padding="same")
-        else:
-            self.conv1 = tf.keras.layers.Conv2DTranspose(filters=filter_num,
-                                                kernel_size=(3, 3),
-                                                strides=stride,
-                                                padding="same")
-        self.bn1 = tf.keras.layers.BatchNormalization()
-        self.conv2 = tf.keras.layers.Conv2D(filters=filter_num,
-                                            kernel_size=(3, 3),
-                                            strides=1,
-                                            padding="same")
-        self.bn2 = tf.keras.layers.BatchNormalization()
-        if stride != 1:
-            if not upsample:
-                self.updownsample = tf.keras.Sequential()
-                self.updownsample.add(tf.keras.layers.Conv2D(filters=filter_num,
-                                                        kernel_size=(1, 1),
-                                                        strides=stride))
-                self.updownsample.add(tf.keras.layers.BatchNormalization())
-            else:
-                self.updownsample = tf.keras.Sequential()
-                self.updownsample.add(tf.keras.layers.Conv2DTranspose(filters=filter_num,
-                                                        kernel_size=(1, 1),
-                                                        strides=stride))
-                self.updownsample.add(tf.keras.layers.BatchNormalization())
-        else:
-            self.updownsample = lambda x: x
-
-    def call(self, inputs, training=None, **kwargs):
-        residual = self.updownsample(inputs)
-
-        x = self.conv1(inputs)
-        x = self.bn1(x, training=training)
-        x = tf.nn.relu(x)
-        x = self.conv2(x)
-        x = self.bn2(x, training=training)
-
-        output = tf.nn.relu(tf.keras.layers.add([residual, x]))
-
-        return output
-
-
-class BottleNeck(tf.keras.layers.Layer):
-    def __init__(self, filter_num, stride=1, upsample=False):
-        super(BottleNeck, self).__init__()
-        self.conv1 = tf.keras.layers.Conv2D(filters=filter_num,
-                                            kernel_size=(1, 1),
-                                            strides=1,
-                                            padding='same')
-        self.bn1 = tf.keras.layers.BatchNormalization()
-        if not upsample:
-            self.conv2 = tf.keras.layers.Conv2D(filters=filter_num,
-                                                kernel_size=(3, 3),
-                                                strides=stride,
-                                                padding='same')
-        else:
-            self.conv2 = tf.keras.layers.Conv2DTranspose(filters=filter_num,
-                                                kernel_size=(3, 3),
-                                                strides=stride,
-                                                padding='same')
-        self.bn2 = tf.keras.layers.BatchNormalization()
-        self.conv3 = tf.keras.layers.Conv2D(filters=filter_num * 4,
-                                            kernel_size=(1, 1),
-                                            strides=1,
-                                            padding='same')
-        self.bn3 = tf.keras.layers.BatchNormalization()
-
-        self.updownsample = tf.keras.Sequential()
-        if not upsample:
-            self.updownsample.add(tf.keras.layers.Conv2D(filters=filter_num * 4,
-                                                    kernel_size=(1, 1),
-                                                    strides=stride))
-        else:
-            self.updownsample.add(tf.keras.layers.Conv2DTranspose(filters=filter_num * 4,
-                                                    kernel_size=(1, 1),
-                                                    strides=stride))
-        self.updownsample.add(tf.keras.layers.BatchNormalization())
-
-    def call(self, inputs, training=None, **kwargs):
-        residual = self.updownsample(inputs)
-
-        x = self.conv1(inputs)
-        x = self.bn1(x, training=training)
-        x = tf.nn.relu(x)
-        x = self.conv2(x)
-        x = self.bn2(x, training=training)
-        x = tf.nn.relu(x)
-        x = self.conv3(x)
-        x = self.bn3(x, training=training)
-
-        output = tf.nn.relu(tf.keras.layers.add([residual, x]))
-
-        return output
-
-
-def make_basic_block_layer(filter_num, blocks, stride=1, upsample=False):
-    res_block = tf.keras.Sequential()
-    res_block.add(BasicBlock(filter_num, stride=stride, upsample=upsample))
-
-    for _ in range(1, blocks):
-        res_block.add(BasicBlock(filter_num, stride=1))
-
-    return res_block
-
-
-def make_bottleneck_layer(filter_num, blocks, stride=1, upsample=False):
-    res_block = tf.keras.Sequential()
-    res_block.add(BottleNeck(filter_num, stride=stride, upsample=upsample))
-
-    for _ in range(1, blocks):
-        res_block.add(BottleNeck(filter_num, stride=1))
-
-    return res_block
-
-
-class ResNetTypeI(tf.keras.Model):
-    def __init__(self, layer_params, features, reversed=False, labels=None, is_cvae=False):
-        super(ResNetTypeI, self).__init__()
-        self.reversed = reversed
-        self.labels = labels
-        self.layer_params = layer_params
-
-        if not reversed:
-            self.conv1 = tf.keras.layers.Conv2D(filters=32 if len(layer_params) > 1 else features,
-                                                kernel_size=(7, 7),
-                                                strides=2,
-                                                padding="same")
-            self.bn1 = tf.keras.layers.BatchNormalization()
-            self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
-                                                strides=2,
-                                                padding="same")
-        else:
-            self.conv1 = tf.keras.layers.Conv2DTranspose(filters=3 if labels is None else labels,
-                                                kernel_size=(7, 7),
-                                                strides=2 if len(layer_params) > 1 else 1,
-                                                padding="same")
-            self.bn1 = tf.keras.layers.BatchNormalization()
-            self.pool1 = tf.keras.layers.UpSampling2D()
-
-        self.layer1 = make_basic_block_layer(filter_num=32 if len(layer_params) > 1 else (features if not is_cvae else features*2),
-                                             blocks=layer_params[0],
-                                             stride=1 if not reversed else 2,
-                                             upsample=reversed)
-        if len(layer_params) >= 2:
-            self.layer2 = make_basic_block_layer(filter_num=32,
-                                                blocks=layer_params[1],
-                                                stride=2,
-                                                upsample=reversed)
-        if len(layer_params) >= 3:
-            self.layer3 = make_basic_block_layer(filter_num=32,
-                                                blocks=layer_params[2],
-                                                stride=2,
-                                                upsample=reversed)
-        if len(layer_params) >= 4:
-            self.layer4 = make_basic_block_layer(filter_num=64,
-                                                blocks=layer_params[3],
-                                                stride=2,
-                                                upsample=reversed)
-            
-        if len(layer_params) >= 5:
-            self.layer5 = make_basic_block_layer(filter_num=features if not is_cvae else features*2,
-                                                blocks=layer_params[4],
-                                                stride=2 if not reversed else 1,
-                                                upsample=reversed)
-
-    def call(self, inputs, training=None, mask=None):
-        if not self.reversed:
-            x = self.conv1(inputs)
-            x = self.bn1(x, training=training)
-            x = tf.nn.relu(x)
-            x = self.pool1(x)
-            x = self.layer1(x, training=training)
-            if len(self.layer_params) >= 2:
-                x = self.layer2(x, training=training)
-            if len(self.layer_params) >= 3:
-                x = self.layer3(x, training=training)
-            if len(self.layer_params) >= 4:
-                x = self.layer4(x, training=training)
-            if len(self.layer_params) >= 5:
-                x = self.layer5(x, training=training)
-        else:
-            x = inputs
-            if len(self.layer_params) >= 5:
-                x = self.layer5(x, training=training)
-            if len(self.layer_params) >= 4:
-                x = self.layer4(x, training=training)
-            if len(self.layer_params) >= 2:
-                x = self.layer3(x, training=training)
-            if len(self.layer_params) >= 3:
-                x = self.layer2(x, training=training)
-            x = self.layer1(x, training=training)
-
-            x = self.pool1(x)
-            x = self.bn1(x, training=training)
-            # x = tf.nn.relu(x)
-            x = self.conv1(x)
-            if self.labels is None:
-                x = tf.nn.tanh(x)
-            # else:
-            #     x = tf.nn.softmax(x)
-
-        return x
-
-
-class ResNetTypeII(tf.keras.Model):
-    def __init__(self, layer_params, features, reversed=False, labels=None, is_cvae=False):
-        super(ResNetTypeII, self).__init__()
-        self.reversed = reversed
-        self.labels = labels
-
-        if not reversed:
-            self.conv1 = tf.keras.layers.Conv2D(filters=32,
-                                                kernel_size=(7, 7),
-                                                strides=2,
-                                                padding="same")
-            self.bn1 = tf.keras.layers.BatchNormalization()
-            self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
-                                                strides=2,
-                                                padding="same")
-        else:
-            self.conv1 = tf.keras.layers.Conv2DTranspose(filters=3 if labels is None else labels,
-                                                kernel_size=(7, 7),
-                                                strides=2,
-                                                padding="same")
-            self.bn1 = tf.keras.layers.BatchNormalization()
-            self.pool1 = tf.keras.layers.UpSampling2D()
-
-        self.layer1 = make_bottleneck_layer(filter_num=32,
-                                            blocks=layer_params[0],
-                                            stride=1 if not reversed else 2,
-                                            upsample=reversed)
-        self.layer2 = make_bottleneck_layer(filter_num=64,
-                                            blocks=layer_params[1],
-                                            stride=2,
-                                            upsample=reversed)
-        self.layer3 = make_bottleneck_layer(filter_num=64,
-                                            blocks=layer_params[2],
-                                            stride=2,
-                                            upsample=reversed)
-        self.layer4 = make_bottleneck_layer(filter_num=128,
-                                            blocks=layer_params[3],
-                                            stride=2,
-                                            upsample=reversed)
-        self.layer5 = make_bottleneck_layer(filter_num=features if not is_cvae else features*2,
-                                            blocks=layer_params[4],
-                                            stride=2 if not reversed else 1,
-                                            upsample=reversed)
-        
-
-    def call(self, inputs, training=None, mask=None):
-        if not self.reversed:
-            x = self.conv1(inputs)
-            x = self.bn1(x, training=training)
-            x = tf.nn.relu(x)
-            x = self.pool1(x)
-            x = self.layer1(x, training=training)
-            x = self.layer2(x, training=training)
-            x = self.layer3(x, training=training)
-            x = self.layer4(x, training=training)
-            x = self.layer5(x, training=training)
-        else:
-            x = self.layer5(inputs, training=training)
-            x = self.layer4(x, training=training)
-            x = self.layer3(x, training=training)
-            x = self.layer2(x, training=training)
-            x = self.layer1(x, training=training)
-
-            x = self.pool1(x)
-            x = self.bn1(x, training=training)
-            x = self.conv1(x)
-            if self.labels is None:
-                x = tf.nn.tanh(x)
-
-        return x
-
-
-def resnet_18(layer_params, features, reversed=False, labels=None, is_cvae=False):
-    return ResNetTypeI(layer_params=layer_params, features=features, reversed=reversed, labels=labels, is_cvae=is_cvae)
-
-
-def resnet_34():
-    return ResNetTypeI(layer_params=[3, 4, 6, 3])
-
-
-def resnet_50():
-    return ResNetTypeII(layer_params=[3, 4, 6, 3])
-
-
-def resnet_101(layer_params, features, reversed=False, labels=None, is_cvae=False):
-    return ResNetTypeII(layer_params=layer_params, features=features, reversed=reversed, labels=labels, is_cvae=is_cvae)
-
-
-def resnet_152():
-    return ResNetTypeII(layer_params=[3, 8, 36, 3])

models/upscaler.py

@@ -131,13 +131,13 @@ class UpscalerBasicConv(tf.keras.Model):
         self.low_res = low_res
 
         self.seq = tf.keras.Sequential([
-                    tf.keras.layers.Conv2D(64, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_1'),
+                    tf.keras.layers.Conv2D(256, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_1'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_1'),
-                    tf.keras.layers.Conv2D(64, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_2'),
+                    tf.keras.layers.Conv2D(128, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_2'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_2'),
-                    tf.keras.layers.Conv2D(16, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_3'),
+                    tf.keras.layers.Conv2D(64, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_3'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_3'),
-                    tf.keras.layers.Conv2D(16, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_4'),
+                    tf.keras.layers.Conv2D(32, kernel_size=kernel_size, padding='same', activation='relu', name='upscale_enhancer_conv_4'),
                     tf.keras.layers.BatchNormalization(name='upscale_enhancer_batch_norm_4'),
                     tf.keras.layers.Dense(3, activation='tanh', name='upscale_enhancer_dense_final'),
         ])

run_parallel.py

@@ -4,24 +4,24 @@ import os
 
 if __name__ == '__main__':
 
-    folder = '/home/workspace/data/dataset/test_skirt_ready_2'
+    # folder = '/home/workspace/data/dataset/test_skirt_ready_2'
     # folder = '/home/workspace/local-data/cape_processed/train/male'
     # folder = '/home/workspace/local-data/valid_skirt'
-    # folder = '/home/workspace/local-data/valid'
-    # ids = os.listdir(folder)
-    ids = os.listdir(folder + '/mesh_posed_no_orient')#[280000:]
+    folder = '/home/workspace/data/dataset/test_ready'
+    ids = os.listdir(folder)
+    # ids = os.listdir('/home/workspace/data/dataset/validation')#[280000:]
     skirt = 0
 
     count = 0
-    step = 2000
+    step = 25
 
     # !!!!!!! change skirt parameter in script
 
-    while count < len(ids):
+    while count < 400:
         # os.system('nohup python convert_to_uv_cape.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_2_cape_train_male_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_2_cape_train_male_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_train_unposed_onehot_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_train_unposed_onehot_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv_local.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_train_local_unposed_onehot_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_train_local_unposed_onehot_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
-        os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_posed_no_orient_test_skirt_ready_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_posed_no_orient_test_skirt_ready_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
+        os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_curv_raw_test_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_curv_raw_test_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_train_skirt_local_unposed_onehot_3_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_train_skirt_local_unposed_onehot_3_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python convert_to_uv_local_single.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'to_uv_valid_skirt_local_unposed_onehot_3_' + str(count) + '_' + str(count+step) + ' > nohup/to_uv_valid_skirt_local_unposed_onehot_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')
         # os.system('nohup python downscale.py -f ' + folder + ' -s ' + str(count) + ' -e ' + str(count + step) + ' -n ' + 'downscale_valid_posed_no_orient_' + str(count) + '_' + str(count+step) + ' > nohup/downscale_valid_posed_no_orient_' + str(count) + '_' + str(count+step) + '.out' + ' 2>&1 &')