helper

aaa_helpers.txt

@@ -1,11 +1,5 @@
-nohup python auto_encoder_static.py --name="lhunor_ae_static_r7_3" > nohup/review/ae_static_r7_3.out 2>&1 &
-nohup python auto_encoder_body.py --name="lhunor_ae_body_r7_3" > nohup/review/ae_body_r7_3.out 2>&1 &
-nohup python auto_encoder_curv.py --name="lhunor_ae_curv_r7_3" > nohup/review/ae_curv_r7_3.out 2>&1 &
-nohup python cvae.py --name="lhunor_abl_all_resnet_r7" > nohup/review/abl_all_resnet_r7.out 2>&1 &
-nohup python calculate_error.py --name abl_all_resnet_r7_70k > nohup/error/abl_all_resnet_r7_70k.out 2>&1 &
-nohup python evaluate_ae.py --name abl_all_resnet_r7_70k > nohup/evaluate/abl_all_resnet_r7_70k.out 2>&1 &
-
 one final convolutional layer for smoothing, on the final coordinates
+nohup python calculate_error.py --name error_al_all_150k > nohup/error/post_al_all_150k.out 2>&1 &
 
 skirts!!!!
 pyramid next week

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_ae_body import config
+from configs.config_ae_body_post import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -34,7 +34,7 @@ from models.cond_encoder import AutoEncoderNew as AutoEncoder
 
 
 def init_wandb():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_body.py')
     artifact.add_file('losses.py')
@@ -42,7 +42,7 @@ 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.review.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
         artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
@@ -137,10 +137,7 @@ def train():
         if step == 0:
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-        if step % 1000 == 0:    
+        wandb.log(to_log, step=step)  
-            wandb.log(to_log, step=step, commit=True)
-        else:
-            wandb.log(to_log, step=step, commit=False)
             
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_ae_curv import config
+from configs.config_ae_curv_post import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -37,7 +37,7 @@ from models.cond_encoder import AutoEncoderNew as AutoEncoder
 testing = False
 def init_wandb():
     if not testing:
-        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
+        run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp/')
         artifact = wandb.Artifact('code', type='code')
         artifact.add_file('auto_encoder_curv.py')
         artifact.add_file('losses.py')
@@ -45,7 +45,7 @@ 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.review.')]
+        config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
         for config_file_name in config_file_names:
             artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
         run.log_artifact(artifact)
@@ -177,11 +177,8 @@ def train():
         if step == 0:
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
  
-        if step % 1000 == 0:    
+        wandb.log(to_log, step=step)  
-            wandb.log(to_log, step=step, commit=True)
+        print(step)
-        else:
-            wandb.log(to_log, step=step, commit=False)  
-        # print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -209,7 +206,7 @@ def test():
 
 if __name__ == '__main__':
     init_wandb()
-    # allow_memory_growth()
+    allow_memory_growth()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.review.config_ae_static import config
+from configs.config_ae_static import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -37,16 +37,15 @@ from models.cond_encoder import AutoEncoderNew as AutoEncoder
 
 
 def init_wandb():
-    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/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.review.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
         artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
@@ -139,10 +138,7 @@ def train():
         if step == 0:
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
 
-        # if step % 1000 == 0:    
+            
-        #     wandb.log(to_log, step=step, commit=True)
-        # else:
-            # wandb.log(to_log, step=step, commit=False)
         wandb.log(to_log, step=step)
 
         if step % 10000 == 0:

calculate_error.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

configs/config_abl_all_post.py

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

configs/config_ae_static.py

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

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,),
-                        }

cvae.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
@@ -58,9 +58,7 @@ 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'
+        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
-        if os.path.exists(file_name):
-            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
@@ -75,7 +73,7 @@ def kl_loss(mean, logvar):
 
 # 3d loss on posed !!!!!!!!!!!!
 
-@tf.function
+# @tf.function
 def train_step(batch):
 
     with tf.GradientTape() as tape:
@@ -427,6 +425,8 @@ def sample(folder):
 
 
 
+
+
 def test():
     str_split = config['name'].split('_')
     test_idx = str_split.index('test')
@@ -476,7 +476,7 @@ def test():
 
 
 if __name__ == '__main__':
-    init_wandb()
+    # init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())

docker/Dockerfile

@@ -2,9 +2,41 @@ 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" ]
 
-WORKDIR /home/workspace/data
+# Start the container with a bash shell
-# RUN wandb login
+CMD ["/bin/bash"]

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

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
-
 
 class Bottleneck(tf.keras.Model):
     
@@ -113,34 +111,20 @@ class Decoder(tf.keras.Model):
 
 class VariationalEncoderNew(tf.keras.Model):
     
-    def __init__(self, features):
+    def __init__(self, depths, dims, kernel_size=7):
         super(VariationalEncoderNew, self).__init__()
 
-        self.encoder = resnet_18(features)
+        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
 
-        self.mean_branch = tf.keras.Sequential([
+        self.mean_branch = tf.keras.Sequential(
-            tf.keras.layers.Conv2D(filters=features,
+                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
-                                            kernel_size=(3, 3),
+                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
-                                            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([
+        self.var_branch = tf.keras.Sequential(
-            tf.keras.layers.Conv2D(filters=features,
+                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
-                                            kernel_size=(3, 3),
+                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
-                                            strides=1,
+            )
-                                            padding="same"),
-            tf.keras.layers.BatchNormalization(),
-            tf.keras.layers.Conv2D(filters=features,
-                                            kernel_size=(3, 3),
-                                            strides=1,
-                                            padding="same")
-        ])
 
         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, features, activation='tanh'):
+    def __init__(self, depths, dims, kernel_size=7, activation='tanh'):
         super(AEEncoderNew, self).__init__()
 
-        self.encoder = resnet_18(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, features, is_label=False, is_cvae=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(features, reversed=True, is_cvae=is_cvae)
+            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
         else:
-            self.decoder = resnet_18(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):

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['bottleneck_size'], config['activation'])
+        self.encoder : AEEncoderNew = AEEncoderNew(config['encoder_depths'], config['encoder_dims'], config['kernel_size'], config['activation'])
-        self.decoder : DecoderNew = DecoderNew(config['bottleneck_size'], is_label=config['is_label'])
+        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')
 
@@ -179,10 +179,10 @@ class CVAENew(tf.keras.Model):
             if config['use_curvature']:
                 self.curv_enc.trainable = False
 
-        self.encoder = VariationalEncoderNew(config['cvae']['encoder_dims'][-1])
+        self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
-        self.decoder = DecoderNew(config['cvae']['decoder_dims'][-1], is_cvae=True)
+        self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
 
-        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'])

models/resnet.py

@@ -1,254 +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):
-        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()
-        self.conv2 = tf.keras.layers.Conv2D(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.downsample = tf.keras.Sequential()
-        self.downsample.add(tf.keras.layers.Conv2D(filters=filter_num * 4,
-                                                   kernel_size=(1, 1),
-                                                   strides=stride))
-        self.downsample.add(tf.keras.layers.BatchNormalization())
-
-    def call(self, inputs, training=None, **kwargs):
-        residual = self.downsample(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):
-    res_block = tf.keras.Sequential()
-    res_block.add(BottleNeck(filter_num, stride=stride))
-
-    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
-
-        if not reversed:
-            self.conv1 = tf.keras.layers.Conv2D(filters=64,
-                                                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.MaxPool2D(pool_size=(3, 3),
-            #                                     strides=2,
-            #                                     padding="same")
-            self.pool1 = tf.keras.layers.UpSampling2D()
-
-        self.layer1 = make_basic_block_layer(filter_num=64,
-                                             blocks=layer_params[0],
-                                             stride=1 if not reversed else 2,
-                                             upsample=reversed)
-        self.layer2 = make_basic_block_layer(filter_num=64,
-                                             blocks=layer_params[1],
-                                             stride=2,
-                                             upsample=reversed)
-        self.layer3 = make_basic_block_layer(filter_num=64,
-                                             blocks=layer_params[2],
-                                             stride=2,
-                                             upsample=reversed)
-        self.layer4 = make_basic_block_layer(filter_num=128,
-                                             blocks=layer_params[3],
-                                             stride=2,
-                                             upsample=reversed)
-        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)
-            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 = 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):
-        super(ResNetTypeII, self).__init__()
-        self.conv1 = tf.keras.layers.Conv2D(filters=64,
-                                            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")
-
-        self.layer1 = make_bottleneck_layer(filter_num=64,
-                                            blocks=layer_params[0])
-        self.layer2 = make_bottleneck_layer(filter_num=128,
-                                            blocks=layer_params[1],
-                                            stride=2)
-        self.layer3 = make_bottleneck_layer(filter_num=256,
-                                            blocks=layer_params[2],
-                                            stride=2)
-        self.layer4 = make_bottleneck_layer(filter_num=512,
-                                            blocks=layer_params[3],
-                                            stride=2)
-
-        self.avgpool = tf.keras.layers.GlobalAveragePooling2D()
-        self.fc = tf.keras.layers.Dense(units=NUM_CLASSES, activation=tf.keras.activations.softmax)
-
-    def call(self, inputs, training=None, mask=None):
-        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.avgpool(x)
-        output = self.fc(x)
-
-        return output
-
-
-def resnet_18(features, reversed=False, labels=None, is_cvae=False):
-    return ResNetTypeI(layer_params=[2, 2, 2, 2, 2], 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():
-    return ResNetTypeII(layer_params=[3, 4, 23, 3])
-
-
-def resnet_152():
-    return ResNetTypeII(layer_params=[3, 8, 36, 3])