calcualte error second level

aaa_helpers.txt

@@ -1,7 +1,11 @@
-nohup python cvae.py --name="lhunor_weights_test_6" > nohup/iccv/weights_test_6.out 2>&1 &
-nohup python evaluate_ae.py --name iccv_weights_test_6 > nohup/iccv/evaluate_iccv_weights_test_6.out 2>&1 &
-nohup python calculate_error.py --name iccv_weights_test_6 > nohup/iccv/error_iccv_weights_test_6.out 2>&1 &
-
+nohup python cvae_pyramid.py --name="lhunor_abl_pyr_32_no_curv_r1" > nohup/review/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python auto_encoder_static.py --name="lhunor_ae_static_orig_10p_r1" > nohup/review/static_orig_10p_r1.out 2>&1 &
+nohup python auto_encoder_body.py --name="lhunor_ae_body_orig_10p_r1" > nohup/review/body_orig_10p_r1.out 2>&1 &
+nohup python cvae_pyramid.py --name="lhunor_abl_32_64_skirt_no_curv_r1" > nohup/review/abl_pyr_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_pyr_32_no_curv_r1 > nohup/evaluate/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python evaluate_ae_pyramid.py --name evaluate_ae_abl_32_64_skirt_no_curv_r1 > nohup/evaluate/abl_32_64_skirt_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_abl_pyr_32_no_curv_r1 > nohup/error/abl_pyr_32_no_curv_r1.out 2>&1 &
+nohup python calculate_error.py --name error_pyr_abl_32_64_skirt_no_curv_r1 > nohup/error/pyr_abl_32_64_skirt_no_curv_r1.out 2>&1 &
 
 one final convolutional layer for smoothing, on the final coordinates
 

auto_encoder_body.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_ae_body_post import config
+from configs.config_ae_body import config
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 
 import tensorflow as tf
@@ -30,7 +30,7 @@ from tf_utils import check_tf_version, allow_memory_growth
 from losses import edge_loss, uv_mask_loss
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict, plot_3d
-from models.cond_encoder import AutoEncoderNew as AutoEncoder
+from models.cond_encoder import AutoEncoder
 
 
 def init_wandb():
@@ -171,7 +171,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'],
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'],
-                                        use_no_orient=config['remove_global_orientation'],
                                         frames_file=config['frames_file'] if 'frames_file' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_train = StaticDataset(folder=config['train_dir'],
@@ -185,7 +184,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'], 
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'], 
-                                        use_no_orient=config['remove_global_orientation'], 
                                         frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_valid = StaticDataset(folder=config['valid_dir'],

auto_encoder_static.py

@@ -33,7 +33,7 @@ else:
 from tf_utils import check_tf_version, allow_memory_growth
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.custom_utils import batch_to_dict, plot_3d
-from models.cond_encoder import AutoEncoderNew as AutoEncoder
+from models.cond_encoder import AutoEncoder
 
 
 def init_wandb():
@@ -205,7 +205,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'],
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'],
-                                        use_no_orient=config['remove_global_orientation'],
                                         frames_file=config['frames_file'] if 'frames_file' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_train = StaticDataset(folder=config['train_dir'],
@@ -219,7 +218,6 @@ if __name__ == '__main__':
                                         signature=config['signature_dynamic'], 
                                         resolutions=[config['resolution']], 
                                         in_memory=config['dataset_in_memory'], 
-                                        use_no_orient=config['remove_global_orientation'], 
                                         frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None, 
                                         is_cape=config['is_cape'])
     static_dataset_valid = StaticDataset(folder=config['valid_dir'],

calculate_error.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_all_post import config
+from configs.config_abl_pyr_32_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 # import tensorflow as tf
@@ -59,13 +59,13 @@ if __name__ == '__main__':
     folder = config['test_dir']
 
     checkpoint_name = config['name']
-    iteration = ''
+    iteration = '50000'
 
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
     garment_type_table = np.load('custom_data/garment_type_table_test.npy', allow_pickle=True).item()
 
 
-    output_folder = '/home/workspace/data/results/post/' + checkpoint_name + '-' + iteration
+    output_folder = '/home/workspace/data/results/' + checkpoint_name + '-' + iteration
 
 
     faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config['is_skirt'] else '')
@@ -107,7 +107,7 @@ if __name__ == '__main__':
     for key in per_garment_errors.keys():
         print(key + ': ' + str(np.mean(per_garment_errors[key])))
 
-    with open('/home/workspace/data/results/errors/post/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
+    with open('/home/workspace/data/results/errors/' + checkpoint_name + '-' + iteration + '.csv', mode='w') as f:
         file_writer = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
 
         for key in sorted(errors.keys()):

compare_models_saved.py

@@ -1,188 +0,0 @@
-import os
-import sys
-from configs.config_abl_all_post import config as config_a
-
-os.environ["CUDA_VISIBLE_DEVICES"] = '5'
-import tensorflow as tf
-
-gpus = tf.config.experimental.list_physical_devices('GPU')
-if gpus:
-    try:
-        # Currently, memory growth needs to be the same across GPUs
-        for gpu in gpus:
-            tf.config.experimental.set_memory_growth(gpu, True)
-        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
-        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
-    except RuntimeError as e:
-        # Memory growth must be set before GPUs have been initialized
-        print(e)
-
-import glob
-import time
-import argparse
-import wandb
-import tqdm
-import random
-import numpy as np
-import plotly.graph_objects as go
-import plotly.express as ex
-from PIL import Image
-from postprocessing import fix_collision
-
-if config_a['is_skirt']:
-    from losses import edge_loss_skirt as edge_loss
-else:
-    from losses import edge_loss
-
-
-
-from losses import collision_ratio, kl_loss #, concept_loss
-# from losses import collision_penalty as collision_penalty
-from losses import collision_loss as collision_penalty
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
-from dataset import DatasetFactory, StaticDataset
-from custom_utils.smpl import SMPL
-from models.cvae_model import CVAE
-from custom_utils.supersmpl_io import writeOBJ
-from plotly.subplots import make_subplots
-
-
-# uv2mesh = UV2Mesh(res=256, is_skirt=config_a['is_skirt'], is_adaptive=False)
-
-
-
-def plot(mesh_gt, pred_a, pred_b, body, mask):
-    fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
-    
-    _, faces_garment = _maskFaces(np.zeros((14475, 3), np.float32), F, mask)
-    faces = np.concatenate((F, faces_garment + 14475), axis=0)
-    mesh_gt = np.concatenate((body, mesh_gt[mask, :]), axis=0)
-    pred_a = np.concatenate((body, pred_a), axis=0)
-    pred_b = np.concatenate((body, pred_b), axis=0)
-    colors = np.concatenate((np.ones_like(body, dtype=np.int32)*100, np.ones_like(mesh_gt, dtype=np.int32)*230), axis=0)
-    # colors = np.ones_like(mesh_gt, dtype=np.int32)*230
-
-    fig.add_trace(go.Mesh3d(
-            x=mesh_gt[:,0],
-            y=mesh_gt[:,2],
-            z=mesh_gt[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Ground Truth",
-            vertexcolor=colors,
-        ),
-        row=1, col=1)
-
-    fig.add_trace(go.Mesh3d(
-            x=pred_a[:,0],
-            y=pred_a[:,2],
-            z=pred_a[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Pred A",
-            vertexcolor=colors,
-        ),
-        row=1, col=2)
-
-    fig.add_trace(go.Mesh3d(
-            x=pred_b[:,0],
-            y=pred_b[:,2],
-            z=pred_b[:,1],
-            i = faces[:,0],
-            j = faces[:,1],
-            k = faces[:,2],
-            text="Pred B",
-            vertexcolor=colors,
-        ),
-        row=1, col=3)
-
-
-
-    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1), 
-                    scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1), 
-                    scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1), 
-                    )
-    helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
-                yaxis = dict(nticks=4, range=[-1,1],),
-                zaxis = dict(nticks=4, range=[-1,1],),)
-    fig.update_layout(scene = helper,
-                        scene2 = helper,
-                        scene3 = helper,
-                        )
-
-    return fig
-
-
-
-if __name__ == '__main__':
-    run = wandb.init(project='plots', name=config_a['name'], notes=config_a['notes'], dir='/wandb')
-
-    parser = argparse.ArgumentParser(description='')
-    parser.add_argument('--name', type=str)
-    args = vars(parser.parse_args())
-
-    skirt_modifier = '_skirt' if config_a['is_skirt'] else ''
-
-    folder = config_a['test_dir']
-    # smpl = SMPL(use_one_hot=False)
-
-    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
-
-    iteration = ''
-
-    # load_model(model, 'checkpoints/' + 'abl_all_120k')
-
-
-    factory = DatasetFactory()
-    dataset_a = factory.get_dataset(folder=config_a['test_dir'], 
-                                       batch_size=config_a['batch_size'], 
-                                       signature=config_a['signature_dynamic'], 
-                                       resolutions=[config_a['resolution']], 
-                                       in_memory=False, 
-                                       do_repeat=False,
-                                       use_one_hot=config_a['use_one_hot'],
-                                       use_no_orient=config_a['remove_global_orientation'],
-                                       shuffle=False,
-                                       testing=True,
-                                    #    frames_file='frames_abl.txt',
-                                       )
-    static_dataset_a = StaticDataset(folder=config_a['test_dir'], 
-                                        signature=config_a['signature_static'], 
-                                        resolutions=[config_a['resolution']], 
-                                        in_memory=True)
-
-    iterator_a = iter(dataset_a)
-    
-
-    faces_folder = '/home/workspace/data/results/support/faces' + ('_skirt' if config_a['is_skirt'] else '')
-    ids = os.listdir(faces_folder)
-    ids = [id.split('.')[0] for id in ids]
-    faces = {id : np.load(faces_folder + '/' + id + '.npy') for id in ids }
-
-    results_folder = '/home/workspace/data/results/post'
-
-    count = 0
-    while True:
-        batch = iterator_a.get_next()
-
-        batch = static_dataset_a.expand_batch(batch_to_dict(batch, config_a['signature_dynamic']))
-
-        mask = batch['mesh_mask'].numpy().astype(bool)
-        gt = batch['mesh_posed'].numpy()
-        body = batch['mesh_body_posed'].numpy()
-
-        for i in range(mask.shape[0]):
-            id, frame_nr = batch['id'][i].numpy().decode("utf-8"), batch['frame_nr'][i].numpy().decode("utf-8")
-            pred_a = np.load(results_folder + '/al_all_post-/' + id + '_' + frame_nr + '.npy')
-            pred_b = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
-            # pred_c = np.load(results_folder + '/iccv_weights_test_6-/' + id + '_' + frame_nr + '.npy')
-
-            fig = plot(gt[i], pred_a, pred_b, body[i], mask[i])
-
-            wandb.log({f'{id}_{frame_nr}': fig}, step = count)
-            count += 1
-
-            print(count)
-

configs/config_abl_all_post.py

@@ -7,7 +7,7 @@ config = dict()
 # DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
 # DON'T FORGET TO CHECK AVG GARMENT USED
 
-config['use_skinning'] =              False # and deshaping
+config['use_skinning'] =              True # and deshaping
 config['remove_global_orientation'] = True
 config['use_curvature'] =             True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
@@ -19,9 +19,9 @@ 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'] = '5'
-config['name'] = 'iccv_weights_test_8'
-config['notes'] = 'smaller weight loss coeff, 1e-6, convolutional weight learning, changed convnext reverse'
+config['gpu'] = '1'
+config['name'] = 'al_all_post'
+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']:
@@ -86,15 +86,14 @@ config['use_one_hot'] = False
 config['cvae'] = dict()
 config['cvae']['is_label'] = False
 config['cvae']['add_noise'] = True
-config['cvae']['noise_amount'] = 0.00001
+config['cvae']['noise_amount'] = 0.001
 
 config['cvae']['kernel_size'] = 7
 config['cvae']['encoder_depths'] = [3, 3, 3, 9, 3]
 config['cvae']['encoder_dims'] = [32, 64, 128, 256, 64]
-config['cvae']['decoder_depths'] = [3, 9, 3, 3, 3, 3]
-config['cvae']['decoder_dims'] = [3, 32, 128, 128, 256, 512]
-config['cvae']['decoder_weights_depths'] = [3, 9, 3, 3, 3]
-config['cvae']['decoder_weights_dims'] = [24, 32, 64, 128, 256]
+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

configs/config_abl_pyr_32.py

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

configs/config_abl_pyr_32_64_skirt_r1.py

@@ -0,0 +1,189 @@
+config = dict()
+
+config['gpu'] = '1'
+config['name'] = 'pyr_abl_32_64_skirt_no_curv_r1'
+config['notes'] = 'no curv, 10p data'
+config['tags'] = ['review_1']
+
+# DON'T FORGET TO RESET SSIM LOSS USAGE
+# DON'T FORGET TO CHECK MODEL LOADING
+# DON'T FORGET TO CHECK IF STORE IN MEMORY
+# DON'T FORGET TO CHECK REG LOSS COEFF
+# DON'T FORGET TO LOAD FINAL UPSCALER UNLESS HAVE LEVEL 512
+# DON'T FORGET TO CHECK IF SKIRT
+# DON'T FORGET TO CHECK IF CAPE
+# DON'T FORGET TO CHECK IF USING DOWNSCALE NONE OR _2
+# DON'T FORGET TO CHECK UPSCALING and ENCODER CHECKPOINTS
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               False
+config['use_curvature'] =             False
+
+config['pyramid'] = dict()
+config['pyramid']['resolutions'] = [32, 64]
+config['pyramid']['pretrained_pyramid'] = 'checkpoints/pyr_abl_32_skirt_no_curv_r1'
+config['pyramid']['final_upscale_enhancer'] = 'checkpoints/64_512_skirt'
+
+config['pretrained_model'] = ''
+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
+config['is_skirt'] = True
+config['is_cape'] = False
+config['frames_file'] = 'frames_skirt_10p.txt'
+config['frames_file_valid'] = 'frames_skirt_10p.txt'
+
+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['resolution'] = None
+config['latent_dim'] = 128
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['lr'] = 0.0001
+config['starting_balancing_coeff'] = 0.0001
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+config['avg_garment_path'] = ''
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (),
+                          'pose_shape': (72 + 11,),
+                          'uv_body_posed': (512, 256, 3),
+                          'mesh_body_posed': (config['smpl_res'], 3,),
+                          'mesh_posed': (config['smpl_res'], 3,),
+                          'mesh_unposed': (config['smpl_res'], 3,),
+                          'uv_unposed': (512, 256, 3),
+                          'uv_curvature': (512, 256, 7),
+                        }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                              'mesh_mask': (config['smpl_res'],),
+                              'uv_mask': (512, 256,),
+                              }
+
+config['pyramid']['is_label'] = False
+config['pyramid']['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]
+
+for res in config['pyramid']['resolutions']:
+  if res != 512:
+      res_modifier = '_' + str(res)
+      config['signature_dynamic']['uv_body_posed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_unposed' + res_modifier] = (res, res//2, 3)
+      config['signature_dynamic']['uv_curvature' + res_modifier] = (res, res//2, 7)
+      config['signature_static']['uv_static' + res_modifier] = (res, res//2, 3)
+      config['signature_static']['uv_mask' + res_modifier] = (res, res//2)
+
+
+
+config['pyramid']['freeze_encoders'] = True
+
+config['pyramid']['levels'] = []
+for res in config['pyramid']['resolutions']:
+  if res == 512:
+    level = dict()
+    level['resolution'] = 512
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [3, 3, 9, 3]
+    level['encoder_dims'] = [32, 64, 128, 256]
+    level['decoder_input'] = (16, 8, 80)
+    level['decoder_depths'] = [3, 3, 9, 3]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''
+    config['pyramid']['levels'].append(level)
+  elif res == 256:
+    level = dict()
+    level['resolution'] = 256
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 7
+    level['encoder_depths'] = [9, 9, 9, 9]
+    level['encoder_dims'] = [32, 64, 128, 256]
+    level['decoder_input'] = (8, 4, 128)
+    level['decoder_depths'] = [9, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64, 16]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''#'checkpoints/up_3_d256_512_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 128:
+    level = dict()
+    level['resolution'] = 128
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [16, 9, 9, 9]
+    level['encoder_dims'] = [64, 128, 128, 256]
+    level['decoder_input'] = (4, 2, 128)
+    level['decoder_depths'] = [16, 9, 9, 9]
+    level['decoder_dims'] = [256, 128, 128, 64]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''#'checkpoints/up_3_d128_256_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  elif res == 64:
+    level = dict()
+    level['resolution'] = 64
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 5
+    level['encoder_depths'] = [9, 9, 9]
+    level['encoder_dims'] = [64, 128, 256]
+    level['decoder_input'] = (4, 2, 256)
+    level['decoder_depths'] = [9, 9, 9]
+    level['decoder_dims'] = [256, 128, 64]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = ''#checkpoints/up_3_d64_128_2'
+    level['upscale_enhancer_freeze'] = False
+    config['pyramid']['levels'].append(level)
+  elif res == 32:
+    level = dict()
+    level['resolution'] = 32
+    level['latent_dim'] = config['latent_dim']
+    level['kernel_size'] = 3
+    level['encoder_depths'] = [9, 9]
+    level['encoder_dims'] = [256, 256]
+    level['decoder_input'] = (4, 2, 256)
+    level['decoder_depths'] = [9, 9]
+    level['decoder_dims'] = [256, 256]
+    level['avg_garment_path'] = ''
+    level['upscale_enhancer'] = 'checkpoints/32_512_skirt'#'checkpoints/up_3_d32_64_2'
+    level['upscale_enhancer_freeze'] = True
+    config['pyramid']['levels'].append(level)
+  else:
+    raise NotImplementedError
+
+
+
+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'] = 64
+config['cond_ae']['encoder_depths'] = [3, 3, 9, 9, 3]
+config['cond_ae']['encoder_dims'] = [32, 64, 128, 256, config['cond_ae']['bottleneck_size']]
+config['cond_ae']['decoder_input'] = (8, 4, config['cond_ae']['bottleneck_size'])
+config['cond_ae']['decoder_depths'] = [3, 3, 9, 3, 3]
+config['cond_ae']['decoder_dims'] = [config['cond_ae']['bottleneck_size'], 256, 128, 64, 16]
+
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['upscale_output'] = True
+config['cond_ae_body']['bottleneck_size'] = 512
+config['cond_ae_body']['encoder_depths'] = [3, 3, 9, 9, 3, 3]
+config['cond_ae_body']['encoder_dims'] = [32, 64, 128, 256, 256, config['cond_ae_body']['bottleneck_size']]
+config['cond_ae_body']['decoder_input'] = (4, 2, config['cond_ae_body']['bottleneck_size'])
+config['cond_ae_body']['decoder_depths'] = [3, 3, 9, 3]
+config['cond_ae_body']['decoder_dims'] = [config['cond_ae_body']['bottleneck_size'], 128, 64, 16]

configs/config_abl_pyr_32_skirt.py

@@ -1,8 +1,9 @@
 config = dict()
 
-config['gpu'] = '3'
-config['name'] = 'pyr_abl_32_skirt_2'
-config['notes'] = 'continued from pyr_abl_32_skirt-180k'
+config['gpu'] = '4'
+config['name'] = 'pyr_abl_32_skirt_no_curv_r1'
+config['notes'] = 'no curv, 10p data'
+config['tags'] = ['review_1']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING
@@ -18,24 +19,30 @@ config['use_skinning'] =              True # and deshaping
 config['remove_global_orientation'] = True
 config['use_extra_losses'] =          True # edge, collision, 3d mesh
 config['use_offsets'] =               False
+config['use_curvature'] =             False
 
 config['pyramid'] = dict()
 config['pyramid']['resolutions'] = [32]
 config['pyramid']['pretrained_pyramid'] = ''
 config['pyramid']['final_upscale_enhancer'] = 'checkpoints/32_512_skirt'
 
-config['train_dir'] = '/home/workspace/local-data/train_skirt'
+config['pretrained_model'] = ''
+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
 config['is_skirt'] = True
 config['is_cape'] = False
+config['frames_file'] = 'frames_skirt_10p.txt'
+config['frames_file_valid'] = 'frames_skirt_10p.txt'
 
 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'] = False
+config['dataset_in_memory'] = True
 config['resolution'] = None
 config['latent_dim'] = 128
 
@@ -65,6 +72,7 @@ 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_body.py

@@ -1,8 +1,9 @@
 from configs.config_base import config
 
-config['gpu'] = '2'
+config['gpu'] = '1'
 config['lr'] = 0.0001
-config['name'] = 'body_1_skirt_2_2'
+config['name'] = 'body_orig_10p_r1'
+config['tags'] = ['review_1']
 
 config['notes'] = 'convnext + convnext, add dense with tanh at the end of reverse convnext, | \
     flattened bottleneck with 128 latent_dim\ remove global orientation | \
@@ -15,7 +16,7 @@ config['notes'] = 'convnext + convnext, add dense with tanh at the end of revers
     continued from body_1_skirt_2 | \
     '
 
-config['dataset_in_memory'] = False
+config['dataset_in_memory'] = True
 config['batch_size'] = 32
 
 config['signature_dynamic'] = { 'id': (), 'frame_nr': (),

configs/config_ae_static.py

@@ -1,44 +1,14 @@
-config = dict()
+from configs.config_base import config
 
-
-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'] = '5'
+config['gpu'] = '3'
 config['lr'] = 0.0005
-config['name'] = 'static_post_4'
-config['notes'] = 'convnext + convnext, | \
- \
-| \
+config['name'] = 'static_orig_10p_r1'
+config['tags'] = ['review_1']
+config['notes'] = 'convnext + convnext, add dense with tanh at the end of reverse convnext, | \
+    flattened latent dim to 128 | \
+    train on 100 garments | \
     deeper model | \
-linear activation| \
+    larger batch size | \
     ' 
 
 config['cond_ae']['upscale_output'] = False

configs/config_ae_static_post.py

@@ -0,0 +1,53 @@
+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'] = '5'
+config['lr'] = 0.0005
+config['name'] = 'static_post_4'
+config['notes'] = 'convnext + convnext, | \
+ \
+| \
+    deeper model | \
+linear activation| \
+    ' 
+
+config['cond_ae']['upscale_output'] = False
+config['pretrained_model'] = ''
+
+
+config['signature_dynamic'] = { 'id': (), 'frame_nr': (), }
+config['signature_static'] = { 'uv_static': (512, 256, 3),
+                         'mesh_static': (config['smpl_res'], 3,),
+                         'mesh_mask': (config['smpl_res'],),
+                         'uv_mask': (512, 256,),
+                        }

configs/config_base.py

@@ -5,17 +5,19 @@ config['batch_size'] = 4
 # config['train_dir'] = '/home/workspace/local-data/cape_processed/train/female'
 # config['valid_dir'] = '/home/workspace/local-data/cape_processed/test/female'
 # config['test_dir'] = '/home/workspace/local-data/cape_processed/test/female'
-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['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_ready_skirt_2'
 # config['train_dir'] = '/home/workspace/local-data/train_skirt'
 # config['valid_dir'] = '/home/workspace/local-data/valid_skirt'
 # config['test_dir'] = '/home/workspace/local-data/test_skirt_ready'
 config['use_filled'] = False
 config['resolution'] = 512
 config['is_skirt'] = False
-config['dataset_in_memory'] = False
+config['dataset_in_memory'] = True
 config['is_cape'] = False
+config['frames_file'] = 'frames_skirt_10p.txt'
+config['frames_file_valid'] = 'frames_skirt_10p.txt'
 
 config['smpl_res'] = 14475
 if config['is_cape']:

configs/post/config_abl_pyr_32.py

@@ -1,9 +1,9 @@
 config = dict()
 
-config['gpu'] = '2'
+config['gpu'] = '6'
 config['name'] = 'abl_pyr_32'
-config['notes'] = 'fixed noise handling'
-config['tags'] = ['pyr_post']
+config['notes'] = ''
+config['tags'] = ['review_1']
 
 # DON'T FORGET TO RESET SSIM LOSS USAGE
 # DON'T FORGET TO CHECK MODEL LOADING

convnext/models/convnext_tf.py

@@ -2,7 +2,7 @@ from unittest import skip
 import numpy as np
 import tensorflow as tf
 from tensorflow.keras.layers import (Conv2D, Conv2DTranspose, Dense, DepthwiseConv2D,
-                                     GlobalAveragePooling2D, Layer, Activation, Lambda,
+                                     GlobalAveragePooling2D, Layer,
                                      LayerNormalization, Flatten, Reshape, UpSampling2D)
 
 def drop_path(inputs, drop_prob, is_training):
@@ -222,31 +222,29 @@ class ConvNeXtReverse(tf.keras.Model):
 
     def __init__(self, 
                  depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], kernel_size=7,
-                 drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1., learn_weights=False,
+                 drop_path_rate=0., layer_scale_init_value=1e-6, head_init_scale=1.,
                  ):
         super().__init__()
-        self.upsample_layers = [] 
-
+        self.upsample_layers = []  # stem and 3 intermediate downsampling conv layers
         stem = tf.keras.Sequential([
-            LayerNormalization(epsilon=1e-6),
-            Conv2DTranspose(dims[0], kernel_size=2, strides=2, padding='same'),
-        ])
+            Conv2DTranspose(dims[0], kernel_size=4, strides=4, padding='same'),
+            # UpSampling2D((4, 4), interpolation='nearest'),
+            # Conv2D(dims[0], kernel_size=4, strides=1, padding='same'),
+            # Dense(dims[0]),
+            LayerNormalization(epsilon=1e-6)]
+        )
         self.upsample_layers.append(stem)
-
-        for i in range(len(depths) - 2):
+        for i in range(len(depths) - 1):
             downsample_layer = tf.keras.Sequential([
                 LayerNormalization(epsilon=1e-6),
-                Conv2DTranspose(dims[i+1], kernel_size=2, strides=2, padding='same'),
+                Conv2DTranspose(dims[i+1], kernel_size=2, strides=2, padding='same')
+                # UpSampling2D((2,2), interpolation='nearest'),
+                # Conv2D(dims[i+1], kernel_size=2, strides=1, padding='same'),
+                # Dense(dims[i+1]),
             ])
             self.upsample_layers.append(downsample_layer)
 
-        downsample_layer = tf.keras.Sequential([
-            Conv2DTranspose(dims[i+2], kernel_size=2, strides=2, padding='same'),
-            LayerNormalization(epsilon=1e-6),
-        ])
-        self.upsample_layers.append(downsample_layer)
-
-        self.stages = []  
+        self.stages = []  # 4 feature resolution stages, each consisting of multiple residual blocks
         dp_rates = [x for x in np.linspace(0, drop_path_rate, sum(depths))]
         cur = 0
         for i in range(len(depths)):
@@ -257,19 +255,12 @@ class ConvNeXtReverse(tf.keras.Model):
             self.stages.append(stage)
             cur += depths[i]
 
-        if not learn_weights:
-            self.last = Dense(3, activation='tanh')
-            # self.last = Activation('tanh')
-        else:
-            self.last = Activation('softmax')
-            # self.last = Dense(24, activation='softmax')
-
+        self.last = Dense(3, activation='tanh')
 
     def call(self, x, training):
         for i in reversed(range(len(self.upsample_layers))):
             x = self.upsample_layers[i](x, training=training)
             x = self.stages[i](x, training=training)
-
         x = self.last(x, training=training)
         return x
 

custom_utils/custom_utils.py

@@ -2,7 +2,6 @@ import json
 import numpy as np
 import tensorflow as tf
 import scipy as sp
-import cmapy as cm
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
 
@@ -217,35 +216,6 @@ def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, colli
     return fig
 
 
-def plot_weights(weights, body, faces):
-    fig = go.Figure()
-    colors = np.array([cm.color('jet', 1 - w) for w in weights.numpy()])
-
-    # if flip_xy:
-    #     mesh_gt = flip_axis(mesh_gt)
-    #     mesh_pred_unposed = flip_axis(mesh_pred_unposed)
-    #     collision = flip_axis(collision, ind=14475)
-
-    fig.add_trace(go.Mesh3d(
-                x=body[:,0],
-                y=body[:,2],
-                z=body[:,1],
-                i = faces[:,0],
-                j = faces[:,1],
-                k = faces[:,2],
-                vertexcolor=colors
-            ))
-    
-
-    fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),)
-    helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
-                yaxis = dict(nticks=4, range=[-1,1],),
-                zaxis = dict(nticks=4, range=[-1,1],),)
-    fig.update_layout(scene = helper,)
-
-    return fig
-
-
 def plot_3d_collision(gt, collision_1, collision_2, collision_faces, collision_color, flip_xy=False):
     fig = make_subplots(rows=1, cols=3, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(3)] ])
 
@@ -341,7 +311,7 @@ def load_model(model, checkpoint, disable_assert=False, assert_consumed_on=False
 
 def get_summary_str(model):
     lines = []
-    model.summary(print_fn=lines.append, line_length=150,expand_nested=True,show_trainable=True)
+    model.summary(print_fn=lines.append, line_length=150, expand_nested=True, show_trainable=True)
     # Add initial spaces to avoid markdown formatting in TensorBoard
     return lines
 

custom_utils/smpl.py

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

cvae.py

@@ -38,7 +38,7 @@ else:
 from losses import collision_ratio, kl_loss, normal_loss #, concept_loss
 # from losses import collision_penalty as collision_penalty
 from losses import collision_loss as collision_penalty
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, UV2MeshLabel, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision, plot_weights
+from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
 from dataset import DatasetFactory, StaticDataset
 from custom_utils.smpl import SMPL
 from models.cvae_model import CVAENew as CVAE
@@ -62,7 +62,6 @@ def init_wandb():
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False, is_smpl_orig=config['is_cape'])
-uv2mesh_label = UV2MeshLabel(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
 
 
 def kl_loss(mean, logvar):
@@ -72,15 +71,9 @@ def kl_loss(mean, logvar):
     return kl_loss
 
 
-def blend_weights_reg(pred_w, gender=None):
-    orig = smpl.weights
-    l1 = tf.reduce_mean(tf.abs(pred_w - orig[None, 0, :, :]))
-    return l1
-
-
 # 3d loss on posed !!!!!!!!!!!!
 
-@tf.function
+# @tf.function
 def train_step(batch):
 
     with tf.GradientTape() as tape:
@@ -89,10 +82,9 @@ def train_step(batch):
         else:
             mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-        pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
+        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
 
         mesh_pred = uv2mesh(pred)
-        mesh_weigths = uv2mesh_label(weights)
 
         if config['use_skinning']:
             shape = batch['pose_shape'][:, 72:]
@@ -102,31 +94,25 @@ def train_step(batch):
             mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
             mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
         else:
-            shape = batch['pose_shape'][:, 72:]
-            gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-            shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-            mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
+            mesh_pred_posed = mesh_pred
 
         # is the output already masked?
 
         e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
         c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
         c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-        # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+        l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
         l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
         n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
         # conc_loss = concept_loss(pred, batch['uv_unposed'])
         kl = kl_loss(mean, logvar)
-        weights_l = blend_weights_reg(mesh_weigths)
 
-        reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
+        reconstr_loss = l2_loss
         if config['use_extra_losses']:
             if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True:
-                reconstr_loss = reconstr_loss + (e_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff']
             else:
-                reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
         if config['use_norm_loss'] and step > 2000:
             reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
@@ -136,14 +122,14 @@ def train_step(batch):
         logvar = tf.reduce_mean(logvar)
 
     # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     gradients = tape.gradient(loss, model.trainable_variables)
     optimizer.apply_gradients(zip(gradients, model.trainable_variables))
     return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
              'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio,
              'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
-             'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss, 'train/weights_loss': weights_l,
-             # 'train/ms_ssim': ms_ssim, 'train/l2_loss': l2_loss, 
+             'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
+             # 'train/ms_ssim': ms_ssim, 
             }
 
 
@@ -154,10 +140,9 @@ def valid_step(batch):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
-    mesh_weigths = uv2mesh_label(weights)
 
     if config['use_skinning']:
         shape = batch['pose_shape'][:, 72:]
@@ -167,28 +152,22 @@ def valid_step(batch):
         mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
     else:
-        shape = batch['pose_shape'][:, 72:]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths)
+        mesh_pred_posed = mesh_pred
 
     # is the output already masked?
 
     e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
     c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
     c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
-    # l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+    l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
     l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1))
     n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
     # conc_loss = concept_loss(pred, batch['uv_unposed'])
     kl = kl_loss(mean, logvar)
-    weights_l = blend_weights_reg(mesh_weigths)
 
-    reconstr_loss = l2_mesh_loss + 1e-6 * weights_l
+    reconstr_loss = l2_loss
     if config['use_extra_losses']:
-        reconstr_loss = reconstr_loss + (e_loss + c_loss) * config['reg_loss_coeff']
+        reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
     if config['use_norm_loss']:
         reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
 
@@ -198,12 +177,12 @@ def valid_step(batch):
     logvar = tf.reduce_mean(logvar)
 
     # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
-    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
+    metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
     # c_ratio = tf.reduce_mean(collision_ratio(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
 
     return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric, 
              'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/collision_ratio': c_ratio,
-             'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar, 'valid/weights_loss': weights_l,
+             'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
               'valid/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim, 
               }
 
@@ -215,7 +194,7 @@ def test_step(batch):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
     
-    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
 
     mesh_pred = uv2mesh(pred)
 
@@ -229,7 +208,7 @@ def test_step(batch):
         mesh_orig_shaped = mesh_orig + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
         mesh_orig_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_orig_shaped)
     else:
-        mesh_pred_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred, weights)
+        mesh_pred_posed = mesh_pred
         mesh_orig_posed = mesh_orig
     
     mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
@@ -271,10 +250,9 @@ def plot_everything(batch: dict, type: str):
     else:
         mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-    pred, mean, logvar, weights = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
     
     mesh_pred = uv2mesh(pred).numpy()
-    mesh_weigths = uv2mesh_label(weights)
     
     orig_img = uv_orig
     uv_static_img = batch['uv_static']
@@ -299,12 +277,7 @@ def plot_everything(batch: dict, type: str):
             mesh_pred[i, mask[i], :] += shape_offsets.numpy()[i, mask[i], :]
         mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred).numpy()
     else:
-        shape = batch['pose_shape'][:, 72:]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
-        shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
-
-        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
-        mesh_posed = smpl.run_garment_with_weights(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped, mesh_weigths).numpy()
+        mesh_posed = mesh_pred
         gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
         garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
 
@@ -323,16 +296,13 @@ def plot_everything(batch: dict, type: str):
     collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(garment_posed))]
     collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(garment_posed))]
 
-    # figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], garment_posed[i], faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
-    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i],) for i in range(4) }
-    figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i],) for i in range(4) }
-    figs_weights = { type + '/weights_' + str(i): plot_weights(mesh_weigths[0,:,i], body[0], F) for i in range(24) }
-    # figs_weights = { type + '/weights_' + str(i): plot_weights(smpl.weights[0,:,i], body[0], F) for i in range(24) }
+    figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
+    figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
 
     mean_hist = wandb.Histogram(sequence=mean.numpy().mean(axis=0))
     logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0))
 
-    return { **figs, **figs_coll, **figs_weights, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
+    return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
 
 
 def sample(folder): 
@@ -506,7 +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.post.config_abl_pyr_64_128_5 import config
+from configs.config_abl_pyr_32_64_skirt_r1 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 PyramidNew as Pyramid
+from models.pyramid_model_optimized import Pyramid
 from postprocessing import fix_collision
 
 
@@ -59,9 +59,11 @@ 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.post.')]
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs')]
     for config_file_name in config_file_names:
-        artifact.add_file('/'.join(config_file_name.split('.')) + '.py')
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
     run.log_artifact(artifact)
 
 uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
@@ -261,8 +263,8 @@ 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:
-            reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        # if config['use_norm_loss'] and step > 2000:
+        #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
         kl_total += kl
 
@@ -334,8 +336,8 @@ 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:
-        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+    # if config['use_norm_loss'] and step > 2000:
+    #     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
         
     kl_total += kl
 
@@ -790,7 +792,7 @@ if __name__ == '__main__':
     # generate_results()
 
     ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
+    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
 
     # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
 
@@ -801,24 +803,26 @@ if __name__ == '__main__':
     if len(config['pyramid']['resolutions']) == 1:
         model.static_enc.trainable = False
         model.body_enc.trainable = False
-        model.curv_enc.trainable = False
+        if config['use_curvature']:
+            model.curv_enc.trainable = False
     else:
         load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
         model.static_enc.trainable = False
         model.body_enc.trainable = False
-        model.curv_enc.trainable = False
-
+        if config['use_curvature']:
+            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)):
+    for i in range(len(model.levels)-1):
         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:
-    #     load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-    #     model.upscale_enhancer.trainable = False
+    if config['pyramid']['resolutions'][-1] != 512:
+        load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
+        model.upscale_enhancer.trainable = False
 
     for i in range(len(model.levels)-1):
         model.levels[i].trainable = False

docker/Dockerfile

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

evaluate_ae.py

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

evaluate_ae_pyramid.py

@@ -1,6 +1,6 @@
 import os
 import sys
-from configs.config_abl_2_pyr_32_64_128_256_512 import config
+from configs.config_abl_pyr_32_64_skirt_r1 import config
 
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
 import tensorflow as tf

models/base.py

@@ -171,13 +171,13 @@ class AEEncoderNew(tf.keras.Model):
 
 class DecoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, is_label=False, learn_weights=False):
+    def __init__(self, depths, dims, kernel_size=7, is_label=False):
         super(DecoderNew, self).__init__()
 
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size, learn_weights=learn_weights)
+            self.decoder = ConvNeXtReverse(depths=depths, dims=dims, kernel_size=kernel_size)
         else:
             self.decoder = ConvNeXtReverseLabels(depths=depths, dims=dims, nr_of_classes=7)
             

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'])
@@ -181,7 +181,6 @@ class CVAENew(tf.keras.Model):
 
         self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
         self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
-        self.decoder_weights = DecoderNew(config['cvae']['decoder_weights_depths'], config['cvae']['decoder_weights_dims'], config['cvae']['kernel_size'], learn_weights=True)
 
         self.reshape = tf.keras.layers.Reshape((8, 4, 64))
 
@@ -194,12 +193,12 @@ class CVAENew(tf.keras.Model):
         self.noise_amount = config['cvae']['noise_amount']
         self.use_curvature = config['use_curvature']
         self.only_curvatures = config['only_curvatures'] if 'only_curvatures' in config.keys() and config['only_curvatures'] == True else None
-        self.use_offsets_over_body = False
+        self.use_offsets_over_body = not config['use_skinning']
 
         if self.use_offsets_over_body:
             assert self.avg_garment is None, 'When we are not using skinning, we can\'t use avg_garment!'
-        # if self.avg_garment is not None:
-        #     assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
+        if self.avg_garment is not None:
+            assert not self.use_offsets_over_body, 'When avg_garment is given, we must use skinning!'
 
     # @tf.function
     def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
@@ -215,7 +214,6 @@ class CVAENew(tf.keras.Model):
         z = tf.concat([eps, z_cond], axis=-1)
 
         x = self.decoder(z, training=False)
-        weights = self.decoder_weights(z, training=False)
         
         if self.avg_garment is not None:
             x = x + self.avg_garment[tf.newaxis,:,:,:]
@@ -225,7 +223,7 @@ class CVAENew(tf.keras.Model):
 
         x = x * uv_mask[:,:,:,tf.newaxis]
 
-        return x, weights
+        return x
 
 
     def reparameterize(self, mean, logvar, training, fix_noise=False):
@@ -274,7 +272,6 @@ class CVAENew(tf.keras.Model):
 
         z = tf.concat([z, z_cond], axis=-1)
         x = self.decoder(z, training=training)
-        weights = self.decoder_weights(z, training=training)
 
         if self.avg_garment is not None:
             x = x + self.avg_garment[tf.newaxis,:,:,:]
@@ -284,5 +281,5 @@ class CVAENew(tf.keras.Model):
 
         x = x * uv_mask[:,:,:,tf.newaxis]
 
-        return x, mean, logvar, weights
+        return x, mean, logvar
 

models/pyramid_model_optimized.py

@@ -25,14 +25,16 @@ class Pyramid(tf.keras.Model):
         if config['pyramid']['body_model'] != '':
             load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
         
-        self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
-        if config['pyramid']['curvature_model'] != '':
-            load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
+        if config['use_curvature']:
+            self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
+            if config['pyramid']['curvature_model'] != '':
+                load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
 
         if config['pyramid']['freeze_encoders']:
             self.static_enc.trainable = False
             self.body_enc.trainable = False
-            self.curv_enc.trainable = False
+            if config['use_curvature']:
+                self.curv_enc.trainable = False
 
         self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
                                                  tf.keras.layers.Dense(256, activation='relu'),
@@ -70,11 +72,12 @@ class Pyramid(tf.keras.Model):
         self.add_noise = config['pyramid']['add_noise']
         self.noise_amount = config['pyramid']['noise_amount']
         self.use_offsets = config['use_offsets']
+        self.use_curvature = config['use_curvature']
  
         self.upscale_enhancer = None
         if config['pyramid']['final_upscale_enhancer'] != '':
             k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-            self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
+            self.upscale_enhancer : tf.keras.Model = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
             load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
             self.upscale_enhancer.trainable = False
 
@@ -85,9 +88,11 @@ class Pyramid(tf.keras.Model):
     def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
         z_static = self.static_enc(uv_template, training)
         z_body = self.body_enc(uv_body_posed, training)
-        z_curv = self.curv_enc(uv_curv, training)
-
-        z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        if self.use_curvature:
+            z_curv = self.curv_enc(uv_curv, training=training)
+            z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        else:
+            z_cond = tf.concat([z_static, z_body], axis=-1)
         z_cond = self.cond_encoder(z_cond, training=training)
 
         return z_cond
@@ -294,6 +299,7 @@ class PyramidNew(tf.keras.Model):
         self.add_noise = config['pyramid']['add_noise']
         self.noise_amount = config['pyramid']['noise_amount']
         self.use_offsets = config['use_offsets']
+        self.use_curvature = config['use_curvature']
 
         self.upscale_enhancer = None
         if config['pyramid']['final_upscale_enhancer'] != '':
@@ -309,9 +315,11 @@ class PyramidNew(tf.keras.Model):
     def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
         z_static = self.static_enc(uv_template, training)
         z_body = self.body_enc(uv_body_posed, training)
-        z_curv = self.curv_enc(uv_curv, training)
-
-        z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        if self.use_curvature:
+            z_curv = self.curv_enc(uv_curv, training=training)
+            z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
+        else:
+            z_cond = tf.concat([z_static, z_body], axis=-1)
 
         return z_cond
 

preprocessing.py

@@ -232,17 +232,17 @@ def generate_frames_file(folder, ratio=0.1):
     selected = []
 
     for id in tqdm.tqdm(sub_ids):
-        if garment_type_table[id] != 'Dress':
-            continue
-        if len(selected) > 30000:
-            break
+        # if garment_type_table[id] != 'Dress':
+        #     continue
+        # if len(selected) > 30000:
+        #     break
 
         # frames = glob.glob(os.path.join(folder, 'pose_shape', id + '_*'))
         frames = [frame for frame in all_frames if frame.startswith(id + '_')]
         frames = [frame.split('/')[-1].split('.')[0] for frame in frames]
         selected.extend(frames)
 
-    with open(os.path.join(folder, 'frames_dress_30k.txt'), 'w') as f:
+    with open(os.path.join(folder, 'frames_skirt_10p.txt'), 'w') as f:
         for i, frame in enumerate(selected):
             f.write(frame + '\n')
 
@@ -293,9 +293,9 @@ def generate_frames_file_filtered_cape():
 
 if __name__ == '__main__':
 
-    src_folder = '/home/workspace/local-data/train_skirt' #cloth3d_skirt
+    src_folder = '/home/workspace/local-data/valid_skirt' #cloth3d_skirt
     # src_folder = r'D:\Work\Dataset\validation_2'
-    dest_folder = '/home/workspace/data/dataset/validation' 
+    dest_folder = '/home/workspace/data/dataset/local-cache/train_skirt' 
 
 
     # create_no_orient_body(src_folder)
@@ -306,5 +306,5 @@ if __name__ == '__main__':
     # verify_poses(src_folder)
     # create_garment_type_table()
     # generate_faces()
-    generate_frames_file(src_folder, ratio=1)
+    generate_frames_file(src_folder, ratio=0.1)
     # generate_frames_file_filtered_cape()