small updates

custom_utils/custom_utils.py

@@ -35,32 +35,14 @@ class UV2Mesh(nn.Module):
         self.uv_pixels = self.uv_map_discreet[m2uv]
         self.smpl_res = 14475 if not is_smpl_orig else 3638
 
+        self.resizer = Resize(size=(512, 256), interpolation=InterpolationMode.BILINEAR)
+
 
     def uv_to_mesh(self, uv):
         if uv.shape[1] == 3 or uv.shape[1] == 7:
             uv = torch.permute(uv, [0,2,3,1])
         if uv.shape[1] != 512:
-            uv = Resize(uv[:,:,None], size=(512, 256), interpolation=InterpolationMode.BILINEAR)
+            uv = torch.permute(self.resizer(torch.permute(uv, [0,3,1,2])), [0,2,3,1])
-            
-        # batch_size = uv.shape[0]
-
-        # x1_ind = tf.concat((tf.tile(self.uv_pixels[:, 0, :][tf.newaxis, :, :], [batch_size, 1, 1]), tf.zeros((batch_size, self.smpl_res, 1), dtype=tf.int32)), axis=-1)
-        # y1_ind = tf.concat((tf.tile(self.uv_pixels[:, 0, :][tf.newaxis, :, :], [batch_size, 1, 1]), tf.ones((batch_size, self.smpl_res, 1), dtype=tf.int32)), axis=-1)
-        # z1_ind = tf.concat((tf.tile(self.uv_pixels[:, 0, :][tf.newaxis, :, :], [batch_size, 1, 1]), tf.ones((batch_size, self.smpl_res, 1), dtype=tf.int32) * 2), axis=-1)
-        # x2_ind = tf.concat((tf.tile(self.uv_pixels[:, 1, :][tf.newaxis, :, :], [batch_size, 1, 1]), tf.zeros((batch_size, self.smpl_res, 1), dtype=tf.int32)), axis=-1)
-        # y2_ind = tf.concat((tf.tile(self.uv_pixels[:, 1, :][tf.newaxis, :, :], [batch_size, 1, 1]), tf.ones((batch_size, self.smpl_res, 1), dtype=tf.int32)), axis=-1)
-        # z2_ind = tf.concat((tf.tile(self.uv_pixels[:, 1, :][tf.newaxis, :, :], [batch_size, 1, 1]), tf.ones((batch_size, self.smpl_res, 1), dtype=tf.int32) * 2), axis=-1)
-
-
-        # x1 = tf.gather_nd(uv, x1_ind, batch_dims=1)
-        # y1 = tf.gather_nd(uv, y1_ind, batch_dims=1)
-        # z1 = tf.gather_nd(uv, z1_ind, batch_dims=1)
-        # x2 = tf.gather_nd(uv, x2_ind, batch_dims=1)
-        # y2 = tf.gather_nd(uv, y2_ind, batch_dims=1)
-        # z2 = tf.gather_nd(uv, z2_ind, batch_dims=1)
-
-        # p1 = tf.stack((x1, y1, z1), axis=-1)
-        # p2 = tf.stack((x2, y2, z2), axis=-1)
 
         mesh = torch.mean(uv[:, self.uv_pixels[:,:,0], self.uv_pixels[:,:,1]].float(), dim=2)
         return mesh

data/dataset_cape.py

@@ -29,7 +29,7 @@ def read_frames(folder, shuffle=True, is_cape=False, testing=False, frames_file=
 
         if is_cape:
             frames = ['.'.join(frame.split('.')[:-1]) for frame in frames] # .split('_')[0]
-            frames = [Frame(frame.split('.')[0], frame.split('.')[1]) for frame in frames]
+            frames = [Frame(frame.split('.')[0], frame.split('.')[1], 'cape') for frame in frames]
         else:
             frames = [frame.split('.')[0] for frame in frames] # .split('_')[0]
             frames = [Frame(frame.split('_')[0], frame.split('_')[1]) for frame in frames]
@@ -91,11 +91,10 @@ class StaticCache():
 
         if 'mesh_static' in self.signature:
             mesh_static = np.load(os.path.join(self.folder, 'mesh_static', id +  '.npz')); mesh_static = mesh_static['mesh_static']; data['mesh_static'] = mesh_static.astype(np.float32)
-        if 'mesh_mask' in self.signature:
+        if self.is_cape:
-            if self.is_cape:
+            data['mesh_mask'] = np.ones((3638), np.float32)
-                data['mesh_mask'] = np.ones((3638), np.float32)
+        else:
-            else:
+            mesh_mask = np.load(os.path.join(self.folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32); data['mesh_mask'] = mesh_mask
-                mesh_mask = np.load(os.path.join(self.folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32); data['mesh_mask'] = mesh_mask
         # if 'uv_shaped_body' in self.signature:
         #     uv_shaped_body = np.load(os.path.join(self.folder, 'uv_shaped_body', id + '.npz')); uv_shaped_body = uv_shaped_body['uv_shaped_body']; data['uv_shaped_body'] = uv_shaped_body
 
@@ -198,7 +197,12 @@ class DatasetCape(torch.utils.data.Dataset):
                 item['uv_posed' + res_string] = uv_posed.astype(np.float32)
 
             if 'uv_normals' + res_string in self.signature:
-                uv_normals = np.load(os.path.join(self.folder, 'uv_normals' + res_string, frame.id + separator + frame.frame_nr + '.npz')); uv_normals = uv_normals['uv_normals']
+                try:
+                    uv_normals = np.load(os.path.join(self.folder, 'uv_normals' + res_string, frame.id + separator + frame.frame_nr + '.npz')); uv_normals = uv_normals['uv_normals']
+                except:
+                    print('Warning: uv_normals not found for frame ' + frame.id + separator + frame.frame_nr + '.npz')
+                    uv_normals = np.zeros((res, int(res/2), 3), dtype=np.float32)
+
                 item['uv_normals' + res_string] = uv_normals
 
 
@@ -223,27 +227,28 @@ if __name__ == '__main__':
 
     signature = { 'id', 
                   'frame_nr',
-                  'pose_shape',
+                #   'pose_shape',
-                  'uv_posed',
+                #   'uv_posed',
-                  'uv_body_posed',
+                #   'uv_body_posed',
-                  'mesh_body_posed',
+                #   'mesh_body_posed',
-                  'mesh_posed',
+                #   'mesh_posed',
-                  'mesh_unposed',
+                #   'mesh_unposed',
-                  'uv_unposed',
+                #   'uv_unposed',
-                  'uv_curvature',
+                  'uv_normals',
-                  'mesh_curvature',
+                #   'mesh_curvature',
-                  'uv_static',
+                #   'uv_static',
-                  'mesh_static',
+                #   'mesh_static',
-                  'mesh_mask',
+                #   'mesh_mask',
-                  'uv_mask',
+                #   'uv_mask',
-                  'uv_shaped_body',
+                #   'uv_shaped_body',
                   }
     
-    dataset = Dataset('/data-local/127/train', signature, resolutions=[512], device=device, frames_file='frames_jumpsuit.txt')
+    dataset = DatasetCape('/data-local/127_2/cape_processed/train/female', signature, resolutions=[512, 256, 128, 64], device=device, frames_file=None, is_cape=True)
     train_dataloader = DataLoader(dataset, batch_size=4, drop_last=True, shuffle=False)
 
-    for batch in train_dataloader:
+    for i, batch in enumerate(train_dataloader):
         batch
+        print(i)
         pass
 
     pass 

data/utils.py

@@ -12,6 +12,8 @@ class Frame:
     def __eq__(self, other):
         return (self.id, self.frame_nr, self.garment) == (other.id, other.frame_nr, self.garment)
     
+    def __str__(self):
+            return f'{self.id}_{self.frame_nr}_{self.garment}'
 
 def save_to_h5file(h5file, id, frame_nr, garment, data, name, type):
     filters = tb.Filters(complevel=9, complib='blosc2')

docker/Dockerfile2

@@ -42,6 +42,7 @@ COPY requirements.txt /tmp/
 RUN pip install torch-cluster -f https://data.pyg.org/whl/torch-2.0.0+cu117.html
 RUN pip install --requirement /tmp/requirements.txt
 
+RUN pip install pyvista flask==2.1.2 pyinstaller==5.1 sphinx ipyvtklink pythreejs tqdm imageio imageio-ffmpeg matplotlib cmocean
 
 # defining the volumes that will be mounted
 VOLUME [ "/data-net" ]

docker/docker-compose.yml

@@ -63,3 +63,45 @@ services:
         reservations:
           devices:
             - capabilities: [gpu]
+
+  lhunor_iccvw_2:
+    image: lhunor_iccvw:pt2.0.1
+    container_name: lhunor_iccvw_2_pt2.0.1
+    ipc: host
+    tty: true
+    ulimits:
+      memlock: -1
+      stack: 67108864
+    volumes:
+      - '/home-net/lhunor:/home-net'
+      - '/data-net/guest/lhunor/data:/data-net'
+      - '/data-fast/126-data1/lhunor/data:/data-local/126'
+      - '/data-fast/127-data1/lhunor/data:/data-local/127'
+      - '/data-fast/127-data2/lhunor/data:/data-local/127_2'
+      - '/data-fast/128-data1/lhunor/data:/data-local/128'
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - capabilities: [gpu]
+
+  lhunor_iccvw_pv:
+    image: lhunor_iccvw:pt2.0.1_pv
+    container_name: lhunor_iccvw_pt2.0.1_pv
+    ipc: host
+    tty: true
+    ulimits:
+      memlock: -1
+      stack: 67108864
+    volumes:
+      - '/home-net/lhunor:/home-net'
+      - '/data-net/guest/lhunor/data:/data-net'
+      - '/data-fast/126-data1/lhunor/data:/data-local/126'
+      - '/data-fast/127-data1/lhunor/data:/data-local/127'
+      - '/data-fast/127-data2/lhunor/data:/data-local/127_2'
+      - '/data-fast/128-data1/lhunor/data:/data-local/128'
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - capabilities: [gpu]

models/pyramid_level.py

@@ -13,91 +13,6 @@ from models.base import AEEncoder, VariationalEncoder, Decoder
 from models.upscaler import Upscaler
 
 
-
-# class PyramidLevel(nn.Module):
-    
-#     def __init__(self, config):
-#         super(PyramidLevel, self).__init__()
-#         self.latent_dim = config['latent_dim']
-#         self.size = config['resolution']
-
-#         self.encoder: VariationalEncoder = VariationalEncoder(config['encoder_block_settings'], config['input_features'],  kernel_size=config['kernel_size'])
-#         self.decoder: Decoder = Decoder(config['decoder_block_settings'], config['kernel_size'])
-
-#         self.upscale_enhancer = None
-#         if config['upscale_enhancer'] != '':
-#             k_size = config['upscale_enhancer_kernel_size']
-#             self.upscale_enhancer = Upscaler(config['resolution'], kernel_size=k_size)
-#             load_model(self.upscale_enhancer, config['upscale_enhancer'])
-#             for param in self.upscale_enhancer.parameters(): param.requires_grad = False
-
-#         if config['avg_garment_path'] != '':
-#             self.avg_garment = np.load(config['avg_garment_path'])
-#         else:
-#             self.avg_garment = None
-
-
-#     def enhance(self, low, mask, training=None):
-#         x = self.upscale_enhancer([low, mask], training=training)
-#         return x
-
-
-#     def sample(self, z_cond, uv_mask, noise=None):
-#         if noise is None:
-#             eps = torch.normal(shape=(uv_mask.shape[0], self.latent_dim))
-#         else:
-#             eps = noise
-
-#         z = torch.concat([eps, z_cond], dim=-1)
-
-#         x = self.decoder(z)
-        
-#         if self.avg_garment is not None:
-#             x = x + self.avg_garment[None,:,:,:]
-        
-#         x = x * uv_mask[:,None,:,:]
-
-#         return x
-
-
-#     def reparameterize(self, mean, logvar, training, fix_noise=False):
-#         if training == True:
-#             if not fix_noise:
-#                 eps = torch.normal(mean=0.0, std=1.0, size=mean.shape)
-#             else:
-#                 eps = torch.normal(mean=0.0, std=1.0, size=mean.shape)
-#                 eps = torch.tile(eps, [mean.shape[0],1])
-#             out = eps * torch.exp(logvar * .5) + mean
-#         else:
-#             out = torch.exp(logvar * .5) + mean
-#         return out
-
-
-#     def call(self, inputs, z_cond, training=None):
-#         uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs
-
-#         x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1)
-#         mean, logvar = self.encoder(x, training=training)
-#         z = self.reparameterize(mean, logvar, training)
-
-#         z = torch.concat([z, z_cond], dim=-1)
-#         x = self.decoder(z, training=training)
-
-#         if self.avg_garment is not None:
-#             x = x + self.avg_garment[None,:,:,:]
-
-#         x = x * uv_mask[:,None,:,:]
-
-#         # if self.upscale_enhancer is not None:
-#         #     pred_low = self.enhance(x, uv_mask, training=training)
-#         #     x = tf.image.resize(pred_low, (512, 256), tf.image.ResizeMethod.LANCZOS5)
-        
-#         # x = x * uv_mask_high[:,:,:,tf.newaxis]
-
-#         return x, mean, logvar
-
-
-
 class PyramidLevel(nn.Module):
     
     def __init__(self, config, use_normals=True):
@@ -115,6 +30,7 @@ class PyramidLevel(nn.Module):
             for param in self.upscale_enhancer.parameters(): param.requires_grad = False
 
         self.use_normals = use_normals
+        self.scaling = 1.0 if 'scaling' not in config else config['scaling']
 
     def enhance(self, low, mask):
         x = self.upscale_enhancer([low, mask])
@@ -175,4 +91,6 @@ class PyramidLevel(nn.Module):
         
         # x = x * uv_mask_high[:,:,:,tf.newaxis]
 
+        x = x * self.scaling
+
         return x, mean, logvar

models/pyramid_model.py

@@ -66,8 +66,8 @@ class Pyramid(nn.Module):
         #     pred = pred + levels_input[0][2] # uv_body_posed_32
         if 1 != len(self.levels):
             pred = self.levels[0].enhance(pred, levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
-            pred = self.resizers[self.levels[1].size](pred)
             out_levels.append([pred, mean, logvar])
+            pred = self.resizers[self.levels[1].size](pred)
             pred = pred * levels_input[1][-2][:,None,:,:]
         else:
             pred = self.levels[0].enhance(pred, levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
@@ -86,8 +86,9 @@ class Pyramid(nn.Module):
                 pred = self.resizers[self.levels[i+1].size](pred)
                 pred = pred * levels_input[i+1][-2][:,None,:,:]
             else:
-                pred = self.levels[-1].enhance(pred, levels_input[-1][-2])
+                if self.levels[-1].size != 512:
-                pred = self.resizers[512](pred)
+                    pred = self.levels[-1].enhance(pred, levels_input[-1][-2])
+                    pred = self.resizers[512](pred)
                 pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
                 out_levels.append([pred, mean, logvar])
 

scripts/cvae.py

@@ -509,7 +509,10 @@ if __name__ == '__main__':
 
     step = 0
     if config['pretrained_model'] != '':
-        step = load_model(model, config['pretrained_model'], optimizer)
+        if 'ignore_saved_optimizer' in config.keys()  and config['ignore_saved_optimizer']:
+            step = load_model(model, config['pretrained_model'])
+        else:
+            step = load_model(model, config['pretrained_model'], optimizer=optimizer)
 
     if not args['debug']:
         # model = torch.compile(model)

scripts/cvae_norm.py

@@ -10,10 +10,12 @@ parser.add_argument('--config', type=str)
 parser.add_argument('--debug', action='store_true')
 args = vars(parser.parse_args())
 
-config_module = importlib.import_module(args['config'])
+
-config = config_module.config
 if args['debug']:
-    from configs.cvae_norm_1 import config
+    from configs.iccvw.cvae_norm_1 import config
+else:
+    config_module = importlib.import_module(args['config'])
+    config = config_module.config
 
 os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
 os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
@@ -51,7 +53,8 @@ from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary
 
 
 def init_wandb():
-    run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags'])
+    wandb.login(host='https://wandb2.lnrweb.com', key='local-2a78b434e9bc51e9f12625f8321a9e3ee34af16d', relogin=True, force=True)
+    run = wandb.init(project='iccvw', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
     artifact.add_file('scripts/cvae_norm.py')
     artifact.add_file('losses/losses.py')
@@ -80,13 +83,13 @@ def kl_loss(mean: torch.Tensor, logvar: torch.Tensor) -> torch.Tensor:
 def train_step(batch):
     model.train()
     pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
-    pred = pred * 1.1
+    pred = pred * 1.4
     mesh_pred = uv2mesh(pred)
 
 
     l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_normals'] - pred) ** 2), axis=-1), axis=[1, 2]))
     l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_normals'] - mesh_pred) ** 2, axis=-1), axis=-1))
-    ms_ssim = torch.mean(_MSSSIM(pred + 1.1, batch['uv_normals'] + 1.1))
+    ms_ssim = torch.mean(_MSSSIM(pred + 1.4, batch['uv_normals'] + 1.4))
     kl = kl_loss(mean, logvar)
 
     reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim)
@@ -114,12 +117,12 @@ def valid_step(batch):
     model.eval()
     with torch.inference_mode():
         pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
-        pred = pred * 1.1
+        pred = pred * 1.4
         mesh_pred = uv2mesh(pred)
 
         l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_normals'] - pred) ** 2), axis=-1), axis=[1, 2]))
         l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_pred - batch['mesh_normals']) ** 2, axis=-1), axis=-1))
-        ms_ssim = torch.mean(_MSSSIM(pred + 1.1, batch['uv_static'] + 1.1))
+        ms_ssim = torch.mean(_MSSSIM(pred + 1.4, batch['uv_static'] + 1.4))
         kl = kl_loss(mean, logvar)
 
         reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim)
@@ -142,12 +145,12 @@ def plot_everything(batch: dict, type: str):
     with torch.inference_mode():
         pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
     
-    pred = pred * 1.1
+    pred = pred * 1.4
     # mesh_pred = uv2mesh(pred).detach().cpu().numpy()
     
     uv_static_img = torch.permute(batch['uv_static'], [0,2,3,1])
     uv_body_posed_img = torch.permute(batch['uv_body_posed'], [0,2,3,1])
-    orig_img = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.1) / 2.2
+    orig_img = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.4) / 2.8
     pred_img = torch.permute(pred, [0,2,3,1])
     img = torch.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img), axis=2)
     imgs = [wandb.Image((img[i].cpu().numpy() + 1) / 2.0) for i in range(4)]
@@ -281,54 +284,6 @@ def sample(folder):
 
 
 
-def test():
-    str_split = config['name'].split('_')
-    test_idx = str_split.index('test')
-    checkpoint_name = '_'.join(str_split[:test_idx])
-    load_model(model, 'checkpoints/' + checkpoint_name)
-
-    dataset_test = factory.get_dataset(folder=config['test_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False, do_repeat=False)
-    static_dataset_test = StaticDataset(folder=config['test_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False)
-   
-    step = 0
-    losses = []
-
-    for batch in tqdm.tqdm(dataset_test):
-        batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
-
-        test_loss = test_step(batch)
-        losses.append(test_loss)
-
-        to_log = { **{ 'current_step': step }, **test_loss }
-        if step % 1000 == 0:
-            figs = plot_everything(batch, 'test')
-            to_log = { **to_log, **figs }
-
-        wandb.log(to_log, step = step)
-        
-        # print(step)
-        step += 1
-   
-    # averages = dict()
-    path_to_plotly_html = "temp/plotly_figure.html"
-
-    histograms = dict()
-    for key in test_loss.keys():
-        accumulated = [losses[i][key].numpy() for i in range(len(losses))]
-        fig = ex.histogram(accumulated, title='Average: ' + str(np.asarray(accumulated).mean()))
-        fig.write_html(path_to_plotly_html, auto_play = False)
-
-        histograms['all/' + key.split('/')[-1] + '_hist'] = wandb.Html(path_to_plotly_html)
-        # averages['all/' + key.split('/')[-1] + '_avg'] = np.asarray(accumulated).mean()
-
-    
-
-    wandb.log({ **histograms }, step = step)
-    wandb.finish()
-    pass
-
-
-
 def train():
     global g_balancing_coeff
     global step
@@ -358,10 +313,10 @@ def train():
             valid_accumulator.reset()
             print(step)
 
-        if train_loss['train/euclid_error'] < (config['balancing_activation_limit'] if 'balancing_activation_limit' in config.keys() else 0.017):
+        if train_loss['train/euclid_error'] < config['balancing_activation_limit']:
             g_balancing_coeff += 1 / 10000 
 
-        if step % 10000 == 0:
+        if step % 20000 == 0:
             ckpt_saver(model, step, optimizer, None)
 
         step += 1
@@ -387,11 +342,14 @@ if __name__ == '__main__':
     _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
     g_balancing_coeff = config['starting_balancing_coeff']
 
-    ckpt_saver = CheckpointSaver('checkpoints/iccv/' + config['name'], top_n=5)
+    ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=25)
 
     step = 0
     if config['pretrained_model'] != '':
-        step = load_model(model, config['pretrained_model'])
+        if 'ignore_saved_optimizer' in config.keys()  and config['ignore_saved_optimizer']:
+            step = load_model(model, config['pretrained_model'])
+        else:
+            step = load_model(model, config['pretrained_model'], optimizer=optimizer)
 
     if not args['debug']:
         # model = torch.compile(model)

scripts/cvae_pyramid.py

@@ -11,7 +11,7 @@ parser.add_argument('--debug', action='store_true')
 args = vars(parser.parse_args())
 
 if args['debug']:
-    from configs.iccvw.pyr_64_reg import config
+    from configs.iccvw.pyr_64_128_256_512_cape_f import config
 else:
     config_module = importlib.import_module(args['config'])
     config = config_module.config
@@ -217,6 +217,9 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col
 
 
 def train_step(batch):
+    if config['is_cape']:
+        batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
+
     model.train()
     # with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp):
     levels_input, conds = group_inputs_for_levels(batch, config)
@@ -313,6 +316,9 @@ def train_step(batch):
 
 
 def valid_step(batch):
+    if config['is_cape']:
+        batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
+
     model.eval()
     with torch.inference_mode():
         levels_input, conds = group_inputs_for_levels(batch, config)
@@ -384,6 +390,9 @@ def valid_step(batch):
 
 
 def plot_everything(batch: dict, type: str):
+    if config['is_cape']:
+        batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
+
     if config['use_skinning']:
         mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed']
     else:
@@ -394,7 +403,7 @@ def plot_everything(batch: dict, type: str):
         levels_input = group_inputs_for_levels(batch, config)
         output_levels = model(levels_input)
 
-    mesh_pred_levels = [uv2mesh(output_levels[i][0]).detach().cpu() for i in range(len(output_levels))]
+    mesh_pred_levels = [uv2mesh(output_levels[i][0]).cpu() for i in range(len(output_levels))]
     mesh_orig_posed = batch['mesh_posed'].cpu()
     body = batch['mesh_body_posed'].cpu().numpy()
     
@@ -406,16 +415,16 @@ def plot_everything(batch: dict, type: str):
     uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2
     uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2
     uv_normals = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.4) / 2.8
-    pred_img = torch.concatenate([torch.permute(model.resizers[512](output_levels[i][0]), [0,2,3,1]) for i in range(len(output_levels))], dim=3)
+    pred_img = torch.concatenate([torch.permute(model.resizers[512](output_levels[i][0]), [0,2,3,1]) for i in range(len(output_levels))], dim=2)
     # pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis])
     pred_img = (pred_img - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) / (pred_img.flatten().reshape(pred_img.shape[0], -1).max(1)[0][:,None,None,None] - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None])
 
-    img = torch.concat((uv_static_img, uv_body_posed_img, uv_normals, orig_img, pred_img), axis=2)
+    img = torch.concat((uv_static_img, uv_body_posed_img, uv_normals, orig_img, pred_img), dim=2)
     imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)]
 
     _F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
     mask = batch['mesh_fix']['mesh_mask'].cpu().numpy().astype(bool)
-    if 'mesh_fix' in batch:
+    if 'mesh_fix' in batch and not config['is_cape']:
         faces = [np.load( (dataset_train if type == 'train' else dataset_valid).folder + "/mesh_fixed/" + batch['id'][i] + '_' + batch['garment'][i] + ".npz" )['faces'] for i in range(len(batch['id']))]
     else:
         _, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask)
@@ -553,7 +562,7 @@ if __name__ == '__main__':
 
     optimizer = optim.Adam(model.parameters(), lr=config['lr'])
     _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
-    ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=20)
+    ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'], top_n=50)
     scaler = torch.cuda.amp.GradScaler(enabled=use_amp)
 
     g_balancing_coeff = config['starting_balancing_coeff']
@@ -561,13 +570,10 @@ if __name__ == '__main__':
 
     step = 0
     if config['pretrained_model'] != '':
-        # assert len(config['pyramid']['resolutions']) == 1
+        if 'ignore_saved_optimizer' in config.keys()  and config['ignore_saved_optimizer']:
-        step = load_model(model, config['pretrained_model'], optimizer=optimizer, scaler=scaler, iteration=config['pretrained_model_iteration'])
+            step = load_model(model, config['pretrained_model'])
-
+        else:
-    # if not args['debug']:
+            step = load_model(model, config['pretrained_model'], optimizer=optimizer, iteration=config['pretrained_model_iteration'])
-    #     model = torch.compile(model)
-    #     wandb.watch(model, log='all', log_freq=1000, log_graph=True)
-
 
     if len(config['pyramid']['resolutions']) == 1:
         for param in model.static_enc.parameters(): param.requires_grad = False

scripts/cvae_pyramid_fine.py

@@ -0,0 +1,557 @@
+import os
+import sys
+sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
+
+import importlib
+import argparse
+parser = argparse.ArgumentParser(description='')
+parser.add_argument('--name', type=str)
+parser.add_argument('--config', type=str)
+parser.add_argument('--debug', action='store_true')
+args = vars(parser.parse_args())
+
+if args['debug']:
+    from configs.iccvw.pyr_64_128_256_512_cape_f import config
+else:
+    config_module = importlib.import_module(args['config'])
+    config = config_module.config
+
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
+if args['debug']:
+    os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
+
+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
+
+if config['is_skirt']:
+    from losses.losses import edge_loss_skirt as edge_loss
+else:
+    from losses.losses import edge_loss
+
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.nn.functional as F
+from data.dataset import Dataset
+from utils.checkpoints import CheckpointSaver, load_model
+from utils.utils import InfiniteDataLoader as DataLoader
+from utils.utils import text_to_html
+from utils.postprocess import fix_collision
+from losses.losses import collision_loss, normal_loss, kl_loss
+from pytorch_msssim import MS_SSIM
+from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels
+from smpl.smpl_torch import SMPL
+from plotly.subplots import make_subplots
+from models.pyramid_model import Pyramid
+
+
+def init_wandb():
+    wandb.login(host='https://wandb2.lnrweb.com', key='local-2a78b434e9bc51e9f12625f8321a9e3ee34af16d', relogin=True, force=True)
+    run = wandb.init(project='iccvw', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags'])
+    artifact = wandb.Artifact('code', type='code')
+    artifact.add_file('scripts/cvae_pyramid.py')
+    artifact.add_file('losses/losses.py')
+    artifact.add_file('models/base.py')
+    artifact.add_file('models/cond_encoder.py')
+    artifact.add_file('models/convnext.py')
+    artifact.add_file('models/pyramid_model.py')
+    artifact.add_file('models/pyramid_level.py')
+    artifact.add_file('data/dataset.py')
+    config_file_names = [key for key in sys.modules.keys()  if key.startswith('configs.')]
+    for config_file_name in config_file_names:
+        file_name = '/'.join(config_file_name.split('.')) + '.py'
+        if os.path.exists(file_name):
+            artifact.add_file(file_name)
+    run.log_artifact(artifact)
+
+uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+
+def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, collision_faces, collision_color):
+    fig = make_subplots(rows=1, cols=1+len(mesh_pred_unposed_levels)+1+1, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(1+len(mesh_pred_unposed_levels)+1+1)] ])
+    
+    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"
+        ),
+        row=1, col=1)
+
+    for i, mesh in enumerate(mesh_pred_unposed_levels):
+        fig.add_trace(go.Mesh3d(
+            x=mesh[:,0],
+            y=mesh[:,2],
+            z=mesh[:,1],
+            i = faces[:,0],
+            j = faces[:,1],
+            k = faces[:,2],
+            text='Unposed level_' + str(i)
+        ),
+        row=1, col=i+2)
+
+    fig.add_trace(go.Mesh3d(
+            x=mesh_posed[:,0],
+            y=mesh_posed[:,2],
+            z=mesh_posed[:,1],
+            i = faces[:,0],
+            j = faces[:,1],
+            k = faces[:,2],
+            text='Posed GT'
+        ),
+        row=1, col=1+len(mesh_pred_unposed_levels)+1)
+
+    fig.add_trace(go.Mesh3d(
+            x=collision[:,0],
+            y=collision[:,2],
+            z=collision[:,1],
+            i = collision_faces[:,0],
+            j = collision_faces[:,1],
+            k = collision_faces[:,2],
+            vertexcolor=collision_color,
+            text='Posed output on body'
+        ),
+        row=1, col=1+len(mesh_pred_unposed_levels)+1+1)
+
+    if len(mesh_pred_unposed_levels) == 1:
+        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), 
+                        )
+        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,
+                            scene4 = helper,
+                            )
+    if len(mesh_pred_unposed_levels) == 2:
+        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(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,
+                            scene4 = helper,
+                            scene5 = helper,
+                            )
+    if len(mesh_pred_unposed_levels) == 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),
+                        scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
+                        scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
+                        scene6_aspectmode='manual', scene6_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,
+                            scene4 = helper,
+                            scene5 = helper,
+                            scene6 = helper,
+                            )
+    if len(mesh_pred_unposed_levels) == 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),
+                        scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,), 
+                        scene7_aspectmode='manual', scene7_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,
+                            scene4 = helper,
+                            scene5 = helper,
+                            scene6 = helper,
+                            scene7 = helper,
+                            )
+    if len(mesh_pred_unposed_levels) == 5:
+        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),
+                        scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,), 
+                        scene7_aspectmode='manual', scene7_aspectratio=dict(x=1, y=1, z=1,), 
+                        scene8_aspectmode='manual', scene8_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,
+                            scene4 = helper,
+                            scene5 = helper,
+                            scene6 = helper,
+                            scene7 = helper,
+                            scene8 = helper,
+                            )
+    return fig
+
+
+def train_step(batch):
+    if config['is_cape']:
+        batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
+
+    model.train()
+    # with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp):
+    levels_input, conds = group_inputs_for_levels(batch, config)
+
+    out_levels = model([levels_input, conds])
+
+    if config['use_skinning']:
+        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+    else:
+        mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+
+    output = dict()
+    reconstr_loss_total = 0
+    kl_total = 0
+    posed_or_not = 'unposed' if config['use_skinning'] else 'posed'
+
+    for i, res in enumerate(config['pyramid']['resolutions']):
+        # i = -1
+        res = config['pyramid']['resolutions'][i]
+        res_modifier = '_' + str(res) if res != 512 else ''
+        pred, mean, logvar = out_levels[i]
+
+        l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((levels_input[i][0] - pred) ** 2), dim=-1), dim=[1, 2])) # levels_input[i][0] = uv_orig
+        kl = kl_loss(mean, logvar)
+
+        mesh_pred = uv2mesh(pred)
+
+        if config['use_skinning']:
+            shape = batch['pose_shape'][:, 72:]
+            gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
+            shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
+
+            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None]
+            mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+        else:
+            mesh_pred_posed = mesh_pred
+
+        e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask']))
+        c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask'])
+        c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
+        n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+        l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
+        
+        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+        if not config['is_cape']:
+            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+            if config['use_norm_loss'] and step > 2000:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * n_loss * config['reg_loss_coeff']
+        
+        kl_total += kl
+    loss: torch.Tensor = reconstr_loss_total + g_balancing_coeff * kl_total
+
+    optimizer.zero_grad()
+    loss.backward()
+    optimizer.step()
+
+    model.eval()
+    with torch.inference_mode():
+        mean = torch.mean(mean)
+        logvar = torch.mean(logvar)
+
+        ms_ssim = torch.mean(_MSSSIM(pred + 1, levels_input[i][0] + 1))
+        metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask'])
+
+    output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, 
+                                'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
+                                'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss,
+                                'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss, 'train/ms_ssim' + res_modifier: ms_ssim,
+                                'train/collision_ratio': c_ratio } } # 
+
+
+    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
+
+
+def valid_step(batch):
+    if config['is_cape']:
+        batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
+
+    model.eval()
+    with torch.inference_mode():
+        levels_input, conds = group_inputs_for_levels(batch, config)
+
+        out_levels = model([levels_input, conds])
+
+        if config['use_skinning']:
+            mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+        else:
+            mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+
+        output = dict()
+        reconstr_loss_total = 0
+        kl_total = 0
+
+        for i, res in enumerate(config['pyramid']['resolutions']):
+            # i = -1
+            res = config['pyramid']['resolutions'][i]
+            res_modifier = '_' + str(res) if res != 512 else ''
+            pred, mean, logvar = out_levels[i]
+
+            mesh_pred = uv2mesh(pred)
+
+            if config['use_skinning']:
+                shape = batch['pose_shape'][:, 72:]
+                gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
+                shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
+
+                mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None]
+                mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+            else:
+                mesh_pred_posed = mesh_pred
+
+            e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask']))
+            c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask'])
+            c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
+            l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
+            n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+            l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((levels_input[i][0] - pred) ** 2), dim=-1), dim=[1, 2]))
+            
+            kl = kl_loss(mean, logvar)
+
+            if config['use_extra_losses']:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
+                if not config['is_cape']:
+                    reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 
+                    if config['use_norm_loss'] and step > 2000:
+                        reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * n_loss * config['reg_loss_coeff']
+            else:
+                reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
+
+            kl_total += kl
+        loss = reconstr_loss_total + g_balancing_coeff * kl_total
+
+        mean = torch.mean(mean)
+        logvar = torch.mean(logvar)
+
+        ms_ssim = torch.mean(_MSSSIM(pred + 1, levels_input[i][0] + 1))
+        metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask'])
+
+        output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, 
+                                    'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
+                                    'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
+                                    'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/ms_ssim' + res_modifier: ms_ssim, } } # 
+
+
+
+    return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output }
+
+
+def plot_everything(batch: dict, type: str):
+    if config['is_cape']:
+        batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
+
+    if config['use_skinning']:
+        mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed']
+    else:
+        mesh_orig, uv_orig = batch['mesh_posed'].cpu().numpy(), batch['uv_posed']
+    
+    model.eval()
+    with torch.inference_mode():
+        levels_input = group_inputs_for_levels(batch, config)
+        output_levels = model(levels_input)
+
+    mesh_pred_levels = [uv2mesh(output_levels[i][0]).cpu() for i in range(len(output_levels))]
+    mesh_orig_posed = batch['mesh_posed'].cpu()
+    body = batch['mesh_body_posed'].cpu().numpy()
+    
+    # mesh_pred = torch.cat((mesh_pred[:, :, 0:1], -mesh_pred[:, :, 2:3], mesh_pred[:, :, 1:2]), dim=2)
+    # mesh_pred_levels = [torch.cat((mesh_pred_levels[i][:, :, 0:1], -mesh_pred_levels[i][:, :, 2:3], mesh_pred_levels[i][:, :, 1:2]), dim=2).numpy() for i in range(len(mesh_pred_levels))]
+    # mesh_orig_posed = torch.cat((mesh_orig_posed[:, :, 0:1], -mesh_orig_posed[:, :, 2:3], mesh_orig_posed[:, :, 1:2]), dim=2).numpy()
+
+    orig_img = (torch.permute(uv_orig, [0,2,3,1]) + 1) / 2
+    uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2
+    uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2
+    uv_normals = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.4) / 2.8
+    pred_img = torch.concatenate([torch.permute(model.resizers[512](output_levels[i][0]), [0,2,3,1]) for i in range(len(output_levels))], dim=2)
+    # pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis])
+    pred_img = (pred_img - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) / (pred_img.flatten().reshape(pred_img.shape[0], -1).max(1)[0][:,None,None,None] - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None])
+
+    img = torch.concat((uv_static_img, uv_body_posed_img, uv_normals, orig_img, pred_img), dim=2)
+    imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)]
+
+    _F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
+    mask = batch['mesh_fix']['mesh_mask'].cpu().numpy().astype(bool)
+    if 'mesh_fix' in batch and not config['is_cape']:
+        faces = [np.load( (dataset_train if type == 'train' else dataset_valid).folder + "/mesh_fixed/" + batch['id'][i] + '_' + batch['garment'][i] + ".npz" )['faces'] for i in range(len(batch['id']))]
+    else:
+        _, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask)
+    
+    if config['use_skinning']:
+        shape = batch['pose_shape'][:, 72:]
+        gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long)
+        shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]).cpu().numpy()
+
+        gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])]
+
+        mesh_unposed_shaped_levels = [[] for _ in range(mask.shape[0])]
+        for i in range(len(output_levels)):
+            mesh_unposed_shaped = [mesh_pred_levels[i][j, mask[j], :] + shape_offsets[j, mask[j]] for j in range(mask.shape[0])]
+            for k in range(mask.shape[0]):
+                mesh_unposed_shaped_levels[k].append(mesh_unposed_shaped[k])
+
+        # full res version
+        mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32)
+        for i in range(mask.shape[0]):
+            mesh_unposed_shaped_full[i, mask[i], :] = mesh_unposed_shaped[i]
+        mesh_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(mesh_unposed_shaped_full, device=config['device']))[0].cpu().numpy()
+    
+        # rotate gt 180 degrees along z axis
+        # gt = [np.matmul(gt[i], np.array([[np.cos(np.pi), -np.sin(np.pi), 0], [np.sin(np.pi), np.cos(np.pi), 0], [0, 0, 1]])) for i in range(mask.shape[0])]
+
+        # gt_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32)
+        # for i in range(mask.shape[0]):
+        #     gt_full[i, mask[i], :] = gt[i]
+        # mesh_orig_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(np.stack(gt_full, axis=0), device=config['device'], dtype=torch.float32))[0].cpu().numpy()
+    else:
+        mesh_posed = mesh_pred_levels[-1]
+        gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])]
+        mesh_unposed_shaped_levels = [[mesh_pred_levels[i][j, mask[j], :] for i in range(len(output_levels))] for j in range(mask.shape[0])]
+
+
+    gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(mask.shape[0])]
+    mesh_posed_fixed = fix_collision(torch.Tensor(mesh_posed).to('cuda'), torch.Tensor(body).to('cuda'), torch.Tensor(mask).to('cuda')).cpu().numpy()
+
+    mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])]
+    
+    if config['is_cape']:
+        collision = mesh_posed
+        collision_faces = faces
+        collision_color = [np.ones_like(mesh_posed[i], dtype=np.int32)*230 for i in range(len(mesh_posed))]
+    else:
+        collision = [np.concatenate((body[i], mesh_posed[i]), axis=0) for i in range(len(mesh_posed))]
+        collision_faces = [np.concatenate((_F, faces[i] + config['smpl_res']), axis=0) for i in range(len(mesh_posed))]
+        collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(mesh_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(mesh_posed))]
+
+    figs = { type + "/garment_" + str(i): plot_3d(gt[i], mesh_unposed_shaped_levels[i], faces[i], gt_posed[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
+    
+    if config['is_cape']:
+        figs_coll = dict()
+    else:
+        garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(body.shape[0])]
+        collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(mesh_posed))]
+        gt_posed = [batch['mesh_posed'].cpu().numpy()[i, mask[i], :] for i in range(mask.shape[0])]
+        collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(gt_posed))]
+        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) }
+
+    batch_id = batch['id']
+    batch_frame_nr = batch['frame_nr']
+    batch_garment = batch['garment']
+    batch_info = [f'batch_info: id: {batch_id[i]}, frame_nr: {batch_frame_nr[i]}, garment: {batch_garment[i]}' for i in range(len(batch_id))]
+    batch_info = text_to_html(batch_info)
+    batch_info = wandb.Html(batch_info)
+
+    return { **figs, **figs_coll, **{ type + '/images': imgs, }, **{ f'{type}/batch_info': batch_info }, }
+
+
+def speed_step(levels_input, conds):
+
+    return model.sample([levels_input, conds], training=False)
+
+
+
+def train():
+    global g_balancing_coeff
+    global step
+    valid_iterator = iter(valid_dataloader)
+
+    for batch in train_dataloader:
+        train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
+
+        data_valid = next(valid_iterator)
+        valid_loss = valid_step(data_valid)
+        valid_accumulator.update(valid_loss)
+
+        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
+            to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } })
+            if step % 5000 == 0 or (step < 5000 and step % 1000 == 0):
+                train_figs = plot_everything(batch, 'train')
+                valid_figs = plot_everything(data_valid, 'valid')
+                to_log = { **to_log, **train_figs, **valid_figs }
+            if step == 0:
+                to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
+
+            if not args['debug']:
+                wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            valid_accumulator.reset()
+            print(step)
+
+        if train_loss['train/euclid_error'] < config['balancing_activation_limit']:
+            g_balancing_coeff += 1 / 50000 
+
+        if step % 10000 == 0 and not args['debug']:
+            ckpt_saver(model, step, optimizer, None)
+
+        step += 1
+
+
+if __name__ == '__main__':
+    if not args['debug']:
+        init_wandb()
+
+    use_amp = True
+    smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
+    skirt_modifier = '_skirt' if config['is_skirt'] else ''
+    dataset_resolutions = config['pyramid']['resolutions'].copy()
+    if 512 not in dataset_resolutions:
+        dataset_resolutions.append(512)
+
+    dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
+    dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
+    train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, )
+    valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=True)
+    train_accumulator = Accumulator()
+    valid_accumulator = Accumulator()
+
+    model: Pyramid = Pyramid(config)
+
+    optimizer = optim.Adam(model.parameters(), lr=config['lr'] * 0.05)
+    _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
+    ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'] + '_fine_2', top_n=50)
+    scaler = torch.cuda.amp.GradScaler(enabled=use_amp)
+
+    g_balancing_coeff = config['starting_balancing_coeff']
+    config['pyramid']['loss_weights'] = [1,3,5,10,25]
+
+    step = load_model(model, f'checkpoints/iccvw/{config["name"]}', iteration='25000')
+
+    for param in model.static_enc.parameters(): param.requires_grad = False
+    for param in model.body_enc.parameters(): param.requires_grad = False
+    for param in model.norm_enc.parameters(): param.requires_grad = False
+    for i in range(len(model.levels)-1):
+        for param in model.levels[i].upscale_enhancer.parameters(): param.requires_grad = False
+
+    train()

scripts/cvae_pyramid_speed_test.py

@@ -0,0 +1,160 @@
+import os
+import sys
+sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
+
+import importlib
+import argparse
+parser = argparse.ArgumentParser(description='')
+parser.add_argument('--name', type=str)
+parser.add_argument('--config', type=str)
+parser.add_argument('--debug', action='store_true')
+args = vars(parser.parse_args())
+
+
+from configs.iccvw.pyr_64_2 import config
+
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"] = '5'
+if args['debug']:
+    os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
+
+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
+
+
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.nn.functional as F
+from torch.profiler import profile, record_function, ProfilerActivity
+from data.dataset import Dataset
+from utils.checkpoints import  load_model
+from utils.utils import InfiniteDataLoader as DataLoader
+from losses.losses import  kl_loss
+from custom_utils.custom_utils import UV2Mesh, Accumulator, group_inputs_for_levels
+from smpl.smpl_torch import SMPL
+from models.pyramid_model import Pyramid
+
+
+
+uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+
+def train_step(batch):
+    model.train()
+    # with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp):
+    levels_input, conds = group_inputs_for_levels(batch, config)
+
+    out_levels = model([levels_input, conds])
+
+    if config['use_skinning']:
+        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+    else:
+        mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+
+    reconstr_loss_total = 0
+    kl_total = 0
+
+    #for i, res in enumerate(config['pyramid']['resolutions']):
+    i = -1
+    pred, mean, logvar = out_levels[i]
+
+    mesh_pred = uv2mesh(pred)
+
+    if config['use_skinning']:
+        shape = batch['pose_shape'][:, 72:]
+        gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
+        shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
+
+        mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
+        mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+    else:
+        mesh_pred_posed = mesh_pred
+
+
+    kl = kl_loss(mean, logvar)
+
+    loss: torch.Tensor =  g_balancing_coeff * kl
+
+    optimizer.zero_grad()
+    loss.backward()
+    optimizer.step()
+
+    model.eval()
+    with torch.inference_mode():
+        metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
+
+
+    return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total } }
+
+
+def train():
+    global g_balancing_coeff
+    global step
+
+    for batch in train_dataloader:
+        train_step(batch)
+
+        step += 1
+        print(step)
+        profiler.step()
+
+        if step > 300:
+            break
+
+
+
+if __name__ == '__main__':
+    smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
+    skirt_modifier = '_skirt' if config['is_skirt'] else ''
+    dataset_resolutions = config['pyramid']['resolutions'].copy()
+    if 512 not in dataset_resolutions:
+        dataset_resolutions.append(512)
+
+    dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file='frames_single.txt', use_cache=True, resolutions=dataset_resolutions, is_cape=config['is_cape'])
+    train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, )
+    train_accumulator = Accumulator()
+
+    model: Pyramid = Pyramid(config)
+
+    optimizer = optim.Adam(model.parameters(), lr=config['lr'])
+
+    g_balancing_coeff = config['starting_balancing_coeff']
+    reg_coeff = 1
+
+    step = 0
+    if config['pretrained_model'] != '':
+        # assert len(config['pyramid']['resolutions']) == 1
+        load_model(model, config['pretrained_model'], optimizer=optimizer, iteration=config['pretrained_model_iteration'])
+
+    if len(config['pyramid']['resolutions']) == 1:
+        for param in model.static_enc.parameters(): param.requires_grad = False
+        for param in model.body_enc.parameters(): param.requires_grad = False
+        for param in model.norm_enc.parameters(): param.requires_grad = False
+    else:
+        load_model(model, config['pyramid']['pretrained_pyramid'], iteration=config['pyramid']['pretrained_pyramid_iteration'])
+        for param in model.static_enc.parameters(): param.requires_grad = False
+        for param in model.body_enc.parameters(): param.requires_grad = False
+        for param in model.norm_enc.parameters(): param.requires_grad = False
+
+    for i in range(len(model.levels)-1):
+        for param in model.levels[i].parameters(): param.requires_grad = False
+
+    # create a profiler object
+    profiler = torch.profiler.profile(
+        activities=[ProfilerActivity.CPU, ProfilerActivity.CUDA],
+        schedule=torch.profiler.schedule(wait=2, warmup=5, active=3, repeat=2),
+        on_trace_ready=torch.profiler.tensorboard_trace_handler("log_dir"),
+    )
+
+    with profiler:
+        train()
+
+    profiler.stop()
+    print(profiler.key_averages().table(sort_by="cpu_time_total", row_limit=25))

scripts/generate_results.py

@@ -7,17 +7,19 @@ import argparse
 parser = argparse.ArgumentParser(description='')
 parser.add_argument('--name', type=str)
 parser.add_argument('--config', type=str)
+parser.add_argument('--iteration', type=str, default='')
 parser.add_argument('--debug', action='store_true')
+parser.add_argument('-g', '--gpu', type=str)
 args = vars(parser.parse_args())
 
 if args['debug']:
-    from configs.iccvw.pyr_64 import config
+    from configs.iccvw.pyr_64_128_cape_f_2 import config
 else:
     config_module = importlib.import_module(args['config'])
     config = config_module.config
 
 os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
-os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
+os.environ["CUDA_VISIBLE_DEVICES"] = args['gpu']
 if args['debug']:
     os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
 
@@ -70,7 +72,10 @@ def step_pyramid(batch):
             shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
 
             mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
-            mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+            if not config['is_cape']:
+                mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
+            else:
+                mesh_pred_posed = mesh_pred_shaped
         else:
             mesh_pred_posed = mesh_pred
 
@@ -102,15 +107,32 @@ def step(batch):
 
 def generate():
     for batch in tqdm(test_dataloader):
-        if is_pyramid:
+        with torch.inference_mode():
-            mesh_pred = step_pyramid(batch)
+            if is_pyramid:
-        else: 
+                mesh_pred = step_pyramid(batch)
-            mesh_pred = step(batch)
+            else: 
+                mesh_pred = step(batch)
 
         ids = batch['id']
         frame_nrs = batch['frame_nr']
         garments = batch['garment']
 
+        # import plotly.graph_objects as go
+        # mesh_pred = mesh_pred.cpu().numpy()
+        # mask = batch['mesh_mask'].cpu().numpy()
+        # i = 3
+        # fig = go.Figure(data=[go.Scatter3d(x=mesh_pred[i,mask[i],0], y=mesh_pred[i,mask[i],2], z=mesh_pred[i,mask[i],1], mode='markers', marker=dict(size=1))])
+        # fig.update_layout(scene_aspectmode='cube')
+        # fig.show()
+
+        # import plotly.graph_objects as go
+        # mesh_pred = mesh_pred.cpu().numpy()
+        # i = 3
+        # fig = go.Figure(data=[go.Scatter3d(x=mesh_pred[i,:,0], y=mesh_pred[i,:,2], z=mesh_pred[i,:,1], mode='markers', marker=dict(size=1))])
+        # fig.update_layout(scene_aspectmode='cube')
+        # fig.update_layout(scene=dict(xaxis=dict(range=[-1,1]), yaxis=dict(range=[-1,1]), zaxis=dict(range=[-1,1])))
+        # fig.show()
+
         for i in range(len(ids)):
             np.savez_compressed(f'{out_folder}/{ids[i]}_{frame_nrs[i]}_{garments[i]}', mesh_pred[i].cpu().numpy())
 
@@ -121,11 +143,17 @@ if __name__ == '__main__':
 
     smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
     skirt_modifier = '_skirt' if config['is_skirt'] else ''
-    dataset_resolutions = config['pyramid']['resolutions'].copy()
+    dataset_resolutions = []
+    if 'pyramid' in config:
+        dataset_resolutions = config['pyramid']['resolutions'].copy()
     if 512 not in dataset_resolutions:
         dataset_resolutions.append(512)
 
+    # remove all values from config['signature] that start with mesh_
+    config['signature'] = set([x for x in config['signature'] if not x.startswith('mesh_')])
+
     dataset_test = Dataset(config['test_dir'], config['signature'], device=config['device'], frames_file=config['test_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
+    # dataset_test = Dataset(config['test_dir'], config['signature'], device=config['device'], frames_file='frames_temp.txt', use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
     test_dataloader = DataLoader(dataset_test, batch_size=4, drop_last=True, shuffle=True, )
 
     is_pyramid = config['name'].startswith('pyr')
@@ -135,7 +163,8 @@ if __name__ == '__main__':
     else:
         model: CVAE = CVAE(config)
 
-    it = load_model(model, 'checkpoints/iccv/torch/' + config['name'])
+    it = load_model(model, 'checkpoints/iccvw/' + config['name'], iteration=args['iteration'])
+    model.eval()
     # it = load_model(model, 'checkpoints/iccvw/' + config['name'])
 
     name = config['name'] + '_' + str(it)

utils/generate_figures.py

@@ -5,12 +5,11 @@ sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
 import numpy as np
 import cmapy as cm
 
-from utils import remove_long_edges
 
 from custom_utils.custom_utils import save_stl, write_obj
 from data.cloth3d_io import readPC2Frame
 from data.utils import Frame
-from custom_utils.custom_utils import _maskFaces
+from custom_utils.custom_utils import _maskFaces, remove_long_edges
 import plotly.graph_objects as go
 import plotly.express as ex
 from plotly.subplots import make_subplots

utils/postprocess.py

@@ -14,7 +14,7 @@ import plotly.graph_objects as go
 import plotly.express as ex
 from pytorch3d.structures import Meshes
 
-from custom_utils.custom_utils import _maskFaces
+from custom_utils.custom_utils import _maskFaces, remove_long_edges
 from losses.losses import _nearest_neighbour