evaluate training

aaa_helpers.txt

@@ -1,3 +1,10 @@
+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
 
 skirts!!!!

auto_encoder_body.py

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

auto_encoder_curv.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_curv_post import config
+from configs.review.config_ae_curv 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/')
+        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')
@@ -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.')]
+        config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
         for config_file_name in config_file_names:
             artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
         run.log_artifact(artifact)
@@ -95,7 +95,7 @@ def dice_dense(prediction, ground_truth, weight_map=None):
     return tf.reduce_mean(dice_score)
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     with tf.GradientTape() as tape:
         pred = model([batch['uv_curvature'], batch['uv_mask']], training=True)
@@ -177,8 +177,11 @@ def train():
         if step == 0:
             to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
  
-        wandb.log(to_log, step=step)  
+        if step % 1000 == 0:    
-        print(step)
+            wandb.log(to_log, step=step, commit=True)
+        else:
+            wandb.log(to_log, step=step, commit=False)  
+        # print(step)
 
         if step % 10000 == 0:
             manager_enc.save(checkpoint_number=step)
@@ -206,7 +209,7 @@ def test():
 
 if __name__ == '__main__':
     init_wandb()
-    allow_memory_growth()
+    # allow_memory_growth()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str)
     args = vars(parser.parse_args())

auto_encoder_static.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_static import config
+from configs.review.config_ae_static import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -37,15 +37,16 @@ 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')
+    run = wandb.init(project='ae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('auto_encoder_static.py')
     artifact.add_file('losses.py')
     artifact.add_file('models/base.py')
+    artifact.add_file('models/resnet.py')
     artifact.add_file('models/cond_encoder.py')
     artifact.add_file('dataset.py')
     artifact.add_file('convnext/models/convnext_tf.py')
-    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.review.')]
     for config_file_name in config_file_names:
         artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
     run.log_artifact(artifact)
@@ -138,7 +139,10 @@ 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.config_abl_all_post import config
+from configs.review.config_abl_all import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf

configs/config_abl_overfit_jumpsuit_2.py

@@ -19,7 +19,7 @@ config['only_curvatures'] =           True
 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'] = '3'
+config['gpu'] = '5'
 config['name'] = 'abl_overfit_jumpsuit_2'
 config['notes'] = 'remove other conditions from input as well'
 

configs/config_abl_pyr_32.py

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

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,8 @@
 config = dict()
 
 config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_r1'
+config['name'] = 'pyr_abl_32_skirt_2'
-config['notes'] = ''
+config['notes'] = 'continued from pyr_abl_32_skirt-180k'
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -24,10 +24,7 @@ config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
 config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
 
-config['pretrained_model'] = ''
+config['train_dir'] = '/home/workspace/local-data/train_skirt'
-config['pretrained_model_iteration'] = ''
-
-config['train_dir'] = '/home/workspace/data/dataset/local-cache/train_skirt'
 config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
 config['test_dir'] = '/home/workspace/data/dataset/test_skirt_ready_2'
 config['batch_size'] = 4
@@ -38,7 +35,7 @@ config['pyramid']['static_model'] = 'checkpoints/static_1_skirt'
 config['pyramid']['body_model'] = 'checkpoints/body_1_skirt_2_2'
 config['pyramid']['curvature_model'] = 'checkpoints/curv_1_skirt'
 
-config['dataset_in_memory'] = True
+config['dataset_in_memory'] = False
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -68,7 +65,6 @@ config['signature_static'] = { 'uv_static': (512, 256, 3),
 config['pyramid']['is_label'] = False
 config['pyramid']['latent_dim'] = config['latent_dim']
 config['pyramid']['add_noise'] = True
-config['pyramid']['noise_amount'] = 0.001
 
 config['pyramid']['loss_weights'] = [1,1,1,1,1]
 

configs/config_ae_static.py

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

configs/review/config_abl_all.py

@@ -0,0 +1,126 @@
+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

@@ -0,0 +1,51 @@
+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

@@ -0,0 +1,50 @@
+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

@@ -0,0 +1,51 @@
+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,),
+                        }

curvature_analysis.py

@@ -1,348 +0,0 @@
-import os
-import sys
-os.environ["CUDA_VISIBLE_DEVICES"] = '4'
-
-
-import tqdm
-import argparse
-import random
-import string
-import time
-import numpy as np
-import trimesh as tm
-import cmapy as cm
-import scipy as sp
-import scipy.io as sio
-import plotly.graph_objects as go
-from pyntcloud import PyntCloud
-from scipy.sparse import csr_matrix, coo_matrix
-from scipy.sparse.csgraph import floyd_warshall, dijkstra
-from plotly.subplots import make_subplots
-from custom_utils.custom_utils import _maskFaces
-from postprocessing import fix_collision
-
-from custom_utils.supersmpl_io import readPC2, readPC2Frame, writePC2, readOBJ
-from custom_utils.custom_utils import _maskFaces
-from auto_encoder_curv import dice_dense
-
-def postprocess(mesh, faces, mask=None, body=None, do_smoothing=True):
-    if body is not None:
-        mesh_fixed = fix_collision(mesh, body[np.newaxis,:,:], mask[np.newaxis,:])[0].numpy()[mask, :]
-    else:
-        mesh_fixed = mesh
-
-    if do_smoothing:
-        m = tm.Trimesh(mesh_fixed, faces, process=False, validate=False)
-        outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
-        outliers = np.nonzero(outliers)[0]
-        outliers_n_neighbours = get_closest_n_points(mesh_fixed, outliers, 2)
-        outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
-        faces_fixed = np.concatenate((faces, outliers_faces), axis=0)
-        m = tm.Trimesh(mesh_fixed, faces_fixed, process=False, validate=False)
-        tm.smoothing.filter_humphrey(m, iterations=1, alpha=0.6, beta=0.4)
-
-        mesh = m.vertices
-    else:
-        mesh = mesh_fixed
-
-    return mesh
-
-def export_to_ply(mesh, file):
-    ply = tm.exchange.ply.export_ply(mesh, encoding='binary', vertex_normal=True, include_attributes=True)
-    output_file = open(file, "wb+")
-    output_file.write(ply)
-    output_file.close()
-
-
-def get_closest_n_points(verts, idx, n):
-    dist = sp.spatial.distance.cdist(verts[idx, :], verts)
-    dist[dist == 0] = 1e9
-    idx_sort = np.argsort(dist, axis=-1)
-    closest = idx_sort[:, :n]
-    return closest
-
-
-def calculate_dist(folder, neighbourhood):
-    out = dict()
-    frames = sorted(os.listdir(os.path.join(folder, 'mesh_posed')))[int(args.start):int(args.end)]
-
-    for frame in tqdm.tqdm(frames):
-        id = frame.split('_')[0]
-        if id in out.keys():
-            continue
-
-        mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-        k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-        out[id] = k_neighbors
-
-    return out
-
-
-def histedges_equalN(x, nbin):
-    npt = len(x)
-    return np.interp(np.linspace(0, npt, nbin + 1),
-                     np.arange(npt),
-                     np.sort(x))
-
-
-def get_bins(values, nr_of_bins):
-    flattened = []
-    for c in values:
-        flattened.extend(c.flatten())
-    flattened = np.array(flattened)
-    bins = histedges_equalN(flattened, nr_of_bins)
-    return bins
-
-
-def generate_curvatures(v, faces, mask, neighbourhood=25, nr_of_labels=6):
-    # id = frame.split('_')[0]
-    # frame_nr = int(frame.split('_')[1].split('.')[0])
-
-    # mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-    # _, faces = _maskFaces(np.zeros((14475,3)), F, mask)
-    # v = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
-    
-    m = tm.Trimesh(v, faces, process=False, validate=False)
-
-    outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
-    outliers = np.nonzero(outliers)[0]
-    outliers_n_neighbours = get_closest_n_points(v, outliers, 2)
-    outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
-    faces = np.concatenate((faces, outliers_faces), axis=0)
-
-    verts = v
-
-    m = tm.Trimesh(verts, faces, process=False, validate=False)
-    export_to_ply(m, temp_file)
-
-    cloud = PyntCloud.from_file(temp_file)
-
-    k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood]
-    # k_neighbors = cloud.get_neighbors(k=neighbourhood)
-    # tree = sp.spatial.cKDTree(verts)
-    # k_neighbors = tree.query(verts, 25)[1]
-    #k_neighbors = k_neighbors_cache[id] # np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-    ev = cloud.add_scalar_field("eigen_values", k_neighbors=k_neighbors)
-    cloud.add_scalar_field("curvature", ev=ev)
-    curvature = np.array(cloud.points["curvature(" + str(neighbourhood+1) + ")"])
-    
-    bins = np.load(f'custom_data/train_bins.npy')
-    # bins = get_bins(curvature, nr_of_labels)
-    labels = np.linspace(0, bins.shape[0] - 2, bins.shape[0] - 1)
-
-    frame_labels = np.zeros((curvature.shape[0]), dtype=np.float32)
-    for j in range(bins.shape[0] - 2):
-        frame_labels[(curvature >= bins[j]) * (curvature < bins[j+1])] = labels[j]
-    frame_labels[curvature >= bins[-2]] = labels[-1]
-       
-    return frame_labels, curvature
-
-import tensorflow as tf
-from configs.config_abl_overfit_jumpsuit_2 import config
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision, UV2MeshLabel
-
-from custom_utils.smpl import SMPL
-from models.cvae_model import CVAE
-
-uv2mesh = UV2Mesh(res=256, is_skirt=False, is_adaptive=False, is_smpl_orig=False)
-uv2meshlabel = UV2MeshLabel(res=256, is_skirt=False)
-
-def get_prediction(folder, frame, curv):
-    smpl = SMPL(use_one_hot=False, orig_smpl=False)
-    model = CVAE(config)
-    load_model(model, 'checkpoints/' + config['name'])
-
-    id = frame.split('_')[0]
-    frame_nr = frame.split('_')[1].split('.')[0]
-
-    mesh_mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-    uv_mask = np.load(os.path.join(folder, 'uv_mask', f'{id}.npz'))['uv_mask'].astype(np.float32)  
-    pose_shape = np.load(os.path.join(folder, 'pose_shape', f'{id}_{frame_nr}.npy')).astype(np.float32)  
-    pose_shape[:3] = 0
-    uv_unposed = np.load(os.path.join(folder, 'uv_unposed_no_shape', f'{id}_{frame_nr}.npz'))['uv_unposed_no_shape']
-    uv_static = np.load(os.path.join(folder, 'uv_static', f'{id}.npz'))['uv_static']
-    uv_body_posed = np.load(os.path.join(folder, 'uv_posed_body_no_orient_2', f'{id}_{frame_nr}.npz'))['uv_posed_body_no_orient']
-
-    pred, _, _ = model([uv_unposed[None,:,:,:], uv_static[None,:,:,:], uv_body_posed[None,:,:,:], curv[None,:,:,:], uv_mask[None,:,:]], training=False)
-    mesh_pred = uv2mesh(pred)
-
-    shape = pose_shape[None, 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 * mesh_mask[tf.newaxis,:,tf.newaxis]
-    mesh_pred_posed = smpl.run_garment(pose_shape[None, :72], pose_shape[None, 72:], mesh_pred_shaped)
-    
-    return mesh_pred_posed.numpy()[0,mesh_mask,:]
-
-
-def visualize_curvature_labels(folder, results_folder, frame):
-    id = frame.split('_')[0]
-    frame_nr = frame.split('_')[1].split('.')[0]
-
-    mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-    _, faces = _maskFaces(np.zeros((14475,3)), F, mask)
-    verts = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
-    pred = np.load(os.path.join(results_folder, frame + '.npy'))
-    pred = postprocess(pred, faces)
-
-    uv_curvature = np.load(os.path.join(folder, 'uv_curvature', f'{id}_{frame_nr}.npz'))['curvature_uv']
-    mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature', f'{id}_{frame_nr}.npz'))['mesh_curvature'][mask]
-    mesh_curvature_raw = np.load(os.path.join(folder, 'mesh_curvature_raw', f'{id}_{frame_nr}.npz'))['mesh_curvature_raw'][mask]
-    uv_curvature = tf.one_hot(uv_curvature, 7)
-    pred_new = get_prediction(folder, frame, uv_curvature)
-    pred_new = postprocess(pred_new, faces)
-
-    curvature_labels_gt, curv_gt = generate_curvatures(verts, faces, mask, 25)
-    curvature_labels_pred, _ = generate_curvatures(pred, faces, mask, 25)
-    curvatures_new = (uv2meshlabel(uv_curvature[None,:,:,:])[0].numpy() * mask[:,None])[mask, :]
-    curvatures_pred_new, curv_gt_new = generate_curvatures(pred_new, faces, mask, 25)
-    dice = dice_dense(tf.one_hot(curvature_labels_pred, 7)[None,:], tf.one_hot(curvature_labels_gt, 7)[None,:])
-    dice_new = dice_dense(tf.one_hot(curvatures_pred_new, 7)[None,:], curvatures_new[None,:])
-    curvatures_new = curvatures_new.argmax(axis=-1) - 1
-
-    colors_binned_all = []
-
-    for curvature_labels in [curvature_labels_gt, curvature_labels_pred, curvatures_new, curvatures_pred_new]:
-        colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, int(curvature_labels.max()+1))])
-        colors_binned = np.zeros((curvature_labels.shape[0], 3))
-        for i in range(int(curvature_labels.max())+1):
-            # print(np.count_nonzero(curvature_labels == i))
-            colors_binned[curvature_labels == i, :] = colors[i]
-        colors_binned_all.append(colors_binned)
-
-    fig = make_subplots(rows=1, cols=4, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(4)] ])
-
-    fig.add_trace(go.Mesh3d(
-                # 8 vertices of a cube
-                x=verts[:,0],
-                y=verts[:,1],
-                z=verts[:,2],
-                # i, j and k give the vertices of triangles
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors_binned_all[0]
-            ),
-            row=1, col=1)
-
-    fig.add_trace(go.Mesh3d(
-                # 8 vertices of a cube
-                x=-pred[:,0],
-                y=pred[:,2],
-                z=pred[:,1],
-                # i, j and k give the vertices of triangles
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors_binned_all[1],
-                text=f'dice: {dice}'
-            ),
-            row=1, col=2)
-    
-    fig.add_trace(go.Mesh3d(
-                # 8 vertices of a cube
-                x=verts[:,0],
-                y=verts[:,1],
-                z=verts[:,2],
-                # i, j and k give the vertices of triangles
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors_binned_all[2]
-            ),
-            row=1, col=3)
-
-    fig.add_trace(go.Mesh3d(
-                # 8 vertices of a cube
-                x=-pred_new[:,0],
-                y=pred_new[:,2],
-                z=pred_new[:,1],
-                # i, j and k give the vertices of triangles
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors_binned_all[3],
-                text=f'dice: {dice_new}'
-            ),
-            row=1, col=4)
-
-    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),
-                    scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
-                    # scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
-                    )
-    helper = dict(xaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
-                yaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),
-                zaxis = dict(range=[-1,1], showbackground=False, showticklabels=False, showaxeslabels=False, showspikes=False, visible=False),)
-        
-    fig.update_layout(scene = helper,
-                        scene2 = helper,
-                        scene3 = helper,
-                        scene4 = helper,
-                        # scene5 = helper,
-                        )
-
-
-    # meshes = [go.Mesh3d(
-    #             x=x[:,0],
-    #             y=x[:,1],
-    #             z=x[:,2],
-    #             i = faces[:,0],
-    #             j = faces[:,1],
-    #             k = faces[:,2],
-    #             vertexcolor=colors_binned
-    #             )]
-
-    # fig = go.Figure(data=meshes)
-    # fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1))
-    # fig.update_layout(
-    #     scene = dict(
-    #         xaxis = dict(nticks=4, range=[-1,1],),
-    #                     yaxis = dict(nticks=4, range=[-1,1],),
-    #                     zaxis = dict(nticks=4, range=[-1,1],),)
-    #                     )
-
-    return fig, dice
-
-import wandb
-
-def init_wandb():
-    run = wandb.init(project='plots', name='review_5', dir='/home/workspace/local-data/temp/')
-    artifact = wandb.Artifact('code', type='code')
-    artifact.add_file('curvature_analysis.py')
-    run.log_artifact(artifact)
-
-if __name__ == '__main__':
-    # init_wandb()
-
-    is_skirt = False
-    skirt_modifier = '_skirt' if is_skirt else ''
-    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
-    # k_neighbours(k=25)
-
-    folder = '/home/workspace/local-data/train'
-    results_folder = '/home/workspace/data/results/post/abl_overfit_jumpsuit_2-'
-
-    frames_file = 'frames_jumpsuit_30k.txt'
-    frames = []
-    with open(os.path.join(folder, frames_file), 'r') as f:
-        lines = f.readlines()
-        lines = [line.strip() for line in lines]
-    frames = lines
-
-    temp_file = '/home/workspace/local-data/temp/' + ''.join(random.choice(string.ascii_lowercase) for i in range(10)) + '.ply'
-    if not is_skirt:
-        dist = np.load('custom_data/dijkstra.npy')
-    else:
-        dist = np.load('custom_data/dijkstra_skirt.npy')
-
-    i = 0
-    while True:
-        # frame = np.random.choice(frames)
-        frame = '02806_129'
-        fig, dice = visualize_curvature_labels(folder, results_folder, frame)
-        wandb.log({f'{frame}-dice:{dice}': fig}, step=i)
-        i += 1
-        print(frame)

cvae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_overfit_jumpsuit_2 import config
+from configs.review.config_abl_all import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -41,7 +41,7 @@ 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 models.cvae_model import CVAENew as CVAE
 
 
 def init_wandb():
@@ -58,7 +58,9 @@ def init_wandb():
     artifact.add_file('convnext/models/convnext_tf.py')
     config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
@@ -73,7 +75,7 @@ def kl_loss(mean, logvar):
 
 # 3d loss on posed !!!!!!!!!!!!
 
-# @tf.function
+@tf.function
 def train_step(batch):
 
     with tf.GradientTape() as tape:
@@ -425,8 +427,6 @@ 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())

cvae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_pyr_32_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
@@ -41,7 +41,7 @@ from losses import collision_loss as collision_penalty
 from custom_utils.custom_utils import batch_to_dict, load_model
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
-from models.pyramid_model_optimized import Pyramid
+from models.pyramid_model_optimized import PyramidNew as Pyramid
 from postprocessing import fix_collision
 
 
@@ -59,11 +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'
+        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_smpl_orig=config['is_cape'])
@@ -210,7 +208,7 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col
     return fig
 
 
-# @tf.function
+@tf.function
 def train_step(batch):
     levels_input, conds = group_inputs_for_levels(batch, config)
 
@@ -263,8 +261,8 @@ def train_step(batch):
         else:
             reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
 
-        # if config['use_norm_loss'] and step > 2000:
+        if config['use_norm_loss'] and step > 2000:
-        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
         kl_total += kl
 
@@ -336,8 +334,8 @@ def valid_step(batch):
     else:
         reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
     
-    # if config['use_norm_loss'] and step > 2000:
+    if config['use_norm_loss'] and step > 2000:
-    #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
     kl_total += kl
 
@@ -733,7 +731,7 @@ def speed_step(levels_input, conds):
 
 
 if __name__ == '__main__':
-    # init_wandb()
+    init_wandb()
     parser = argparse.ArgumentParser(description='')
     parser.add_argument('--name', type=str, default='lhunor')
     args = vars(parser.parse_args())
@@ -792,7 +790,7 @@ if __name__ == '__main__':
     # generate_results()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -809,18 +807,18 @@ if __name__ == '__main__':
         model.static_enc.trainable = False
         model.body_enc.trainable = False
         model.curv_enc.trainable = False
-        model.cond_encoder.trainable = False
+
 
     # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
     # model.levels[0].upscale_enhancer.trainable = False
 
 
-    for i in range(len(model.levels)-1):
+    for i in range(len(model.levels)):
         load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer'])
         model.levels[i].upscale_enhancer.trainable = False
-    if config['pyramid']['resolutions'][-1] != 512:
+    # if config['pyramid']['resolutions'][-1] != 512:
-        load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
+    #     load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-        model.upscale_enhancer.trainable = False
+    #     model.upscale_enhancer.trainable = False
 
     for i in range(len(model.levels)-1):
         model.levels[i].trainable = False

evaluate_ae.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_overfit_jumpsuit_2 import config
+from configs.review.config_abl_all import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf
@@ -42,7 +42,7 @@ 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 models.cvae_model import CVAENew as CVAE
 from custom_utils.supersmpl_io import writeOBJ
 # from unif_metric import chamfer_and_score
 
@@ -104,7 +104,7 @@ if __name__ == '__main__':
 
     iteration = ''
 
-    load_model(model, 'checkpoints/' + checkpoint_name, iteration=iteration)
+    load_model(model, 'checkpoints/post/' + checkpoint_name, iteration=iteration)
     # load_model(model, 'checkpoints/' + 'abl_all_120k')
 
     output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration

models/base.py

@@ -1,5 +1,7 @@
 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):
     
@@ -111,20 +113,34 @@ class Decoder(tf.keras.Model):
 
 class VariationalEncoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7):
+    def __init__(self, features):
         super(VariationalEncoderNew, self).__init__()
 
-        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
+        self.encoder = resnet_18(features)
 
-        self.mean_branch = tf.keras.Sequential(
+        self.mean_branch = tf.keras.Sequential([
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+            tf.keras.layers.Conv2D(filters=features,
-                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
+                                            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(
+        self.var_branch = tf.keras.Sequential([
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
+            tf.keras.layers.Conv2D(filters=features,
-                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
+                                            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.flatten_mean = tf.keras.layers.Flatten()
         self.flatten_var = tf.keras.layers.Flatten()
@@ -147,10 +163,10 @@ class VariationalEncoderNew(tf.keras.Model):
 
 class AEEncoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, activation='tanh'):
+    def __init__(self, features, activation='tanh'):
         super(AEEncoderNew, self).__init__()
 
-        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
+        self.encoder = resnet_18(features)
         self.act = tf.keras.layers.Activation(activation)
 
 
@@ -171,15 +187,15 @@ class AEEncoderNew(tf.keras.Model):
 
 class DecoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, is_label=False):
+    def __init__(self, features, is_label=False, is_cvae=False):
         super(DecoderNew, self).__init__()
 
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
+            self.decoder = resnet_18(features, reversed=True, is_cvae=is_cvae)
         else:
-            self.decoder = ConvNeXtReverseLabels(depths=depths, dims=dims, nr_of_classes=7)
+            self.decoder = resnet_18(features, reversed=True, labels=6, is_cvae=is_cvae)
             
 
     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['encoder_depths'], config['encoder_dims'], config['kernel_size'], config['activation'])
+        self.encoder : AEEncoderNew = AEEncoderNew(config['bottleneck_size'], config['activation'])
-        self.decoder : DecoderNew = DecoderNew(config['decoder_depths'], config['decoder_dims'], kernel_size=config['kernel_size'], is_label=config['is_label'])
+        self.decoder : DecoderNew = DecoderNew(config['bottleneck_size'], is_label=config['is_label'])
 
 
     def call(self, inputs, training):

models/cvae_model.py

@@ -43,7 +43,7 @@ class CVAE(tf.keras.Model):
         self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
                                                  tf.keras.layers.Dense(256, activation='relu'),
                                                  tf.keras.layers.Dense(128, activation='relu'),
-                                                #  tf.keras.layers.Lambda(lambda x: x / 1000),
+                                                 tf.keras.layers.Lambda(lambda x: x / 1000),
                                                  tf.keras.layers.Dense(config['latent_dim'], activation='tanh')])
 
         self.encoder = VariationalEncoder(config['cvae']['latent_dim'], config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
@@ -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']['encoder_depths'], config['cond_ae_static']['encoder_dims'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'])
+            self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['bottleneck_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']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_size'])
+            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['bottleneck_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']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'])
+            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['bottleneck_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_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
+        self.encoder = VariationalEncoderNew(config['cvae']['encoder_dims'][-1])
-        self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
+        self.decoder = DecoderNew(config['cvae']['decoder_dims'][-1], is_cvae=True)
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
+        self.reshape = tf.keras.layers.Reshape((8, 4, config['cvae']['decoder_dims'][-1]))
 
         if config['avg_garment_path'] != '':
             self.avg_garment = np.load(config['avg_garment_path'])

models/resnet.py

@@ -0,0 +1,254 @@
+# 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])