add cvae training

configs/abl_all.py

@@ -0,0 +1,194 @@
+from utils.convnext_utils import CNBlockConfig
+
+config = dict()
+
+config['gpu'] = '0'
+config['name'] = 'abl_torch_all'
+config['notes'] = ''
+config['tags'] = ['iccv', 'abl_all', 'torch']
+config['script'] = 'scripts/cvae.py'
+
+
+config['use_skinning'] =              True # and deshaping
+config['remove_global_orientation'] = True
+config['use_curvature'] =             True
+config['use_extra_losses'] =          True # edge, collision, 3d mesh
+config['use_offsets'] =               True
+
+config['use_norm_loss'] =             True
+
+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['avg_garment_path'] = 'custom_data/avg/train_no_shape_avg_uv.npy' #custom_data/train_no_shape_avg_uv.npy # train_no_shape_avg_uv  train_no_shape_one_hot_avg_uv
+if config['use_skinning']:
+  assert (config['use_offsets'] and config['avg_garment_path'] != '') or (not config['use_offsets'] and config['avg_garment_path'] == '')
+
+config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
+
+config['batch_size'] = 4
+config['resolution'] = 512
+config['is_skirt'] = False
+config['dataset_in_memory'] = False
+config['is_cape'] = False
+config['device'] = 'cuda'
+
+config['train_dir'] = '/data-local/127/train'
+config['valid_dir'] = '/data-local/127/valid'
+config['test_dir'] = '/data-net/dataset/test_ready'
+config['train_frames'] = None
+config['valid_frames'] = None
+
+config['static_model'] = 'checkpoints/iccv/static_torch_orig_2'
+config['body_model'] = 'checkpoints/iccv/body_torch_1'
+config['curvature_model'] = 'checkpoints/iccv/curv_torch_1'
+
+
+config['smpl_res'] = 14475
+if config['is_cape']:
+  config['smpl_res'] = 3638
+
+config['latent_dim'] = 128
+
+config['pretrained_model'] = ''
+
+###############    
+config['lr'] = 0.0001#                 0.0001
+###############
+config['starting_balancing_coeff'] = 0.0001
+
+config['signature']: set = { 'id',
+                            'frame_nr',
+                            'pose_shape',
+                            'uv_body_posed',
+                            'mesh_body_posed',
+                            'mesh_posed',
+                            'uv_curvature',
+                            'uv_static',
+                            'mesh_mask',
+                            'uv_mask',
+                        }
+
+if config['use_skinning']:
+  config['signature'].add('uv_unposed')
+  config['signature'].add('mesh_unposed')
+else:
+  config['signature'].add('uv_posed')
+
+config['upscale_enhancer'] = ''
+config['freeze_encoders'] = True
+config['use_one_hot'] = False
+config['bottleneck_scale'] = 2
+
+config['cvae'] = dict()
+config['cvae']['device'] = config['device']
+config['cvae']['is_label'] = False
+config['cvae']['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
+config['cvae']['kernel_size'] = 7
+config['cvae']['bottleneck_size'] = 64 * config['bottleneck_scale']
+config['cvae']['latent_dim'] = config['cvae']['bottleneck_size']
+
+block_setting = [
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 3),
+    CNBlockConfig(128, 256, 3),
+    CNBlockConfig(256, config['cvae']['bottleneck_size'], 9),
+    CNBlockConfig(config['cvae']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cvae']['bottleneck_size'] * 2, 256, 3),
+    CNBlockConfig(256, 128, 9),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 3),
+    CNBlockConfig(32, 3, 3),
+]
+
+config['cvae']['encoder_block_settings'] = block_setting
+config['cvae']['decoder_block_settings'] = block_setting_reverse
+
+
+
+####################### cond_ae_curv ############################
+config['cond_ae_curv'] = dict()
+config['cond_ae_curv']['device'] = config['device']
+config['cond_ae_curv']['is_label'] = True
+config['cond_ae_curv']['latent_dim'] = config['latent_dim']
+config['cond_ae_curv']['kernel_size'] = 7
+config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_curv']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_curv']['encoder_block_settings'] = block_setting
+config['cond_ae_curv']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_curv']['activation'] = 'tanh'
+
+####################### cond_ae_body ############################
+config['cond_ae_body'] = dict()
+config['cond_ae_body']['device'] = config['device']
+config['cond_ae_body']['is_label'] = False
+config['cond_ae_body']['latent_dim'] = config['latent_dim']
+config['cond_ae_body']['kernel_size'] = 7
+config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, 128, 9),
+    CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
+    CNBlockConfig(128, 64, 9),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 3, 3),
+]
+
+config['cond_ae_body']['encoder_block_settings'] = block_setting
+config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_body']['activation'] = 'tanh'
+
+####################### cond_ae_static ############################
+config['cond_ae_static'] = dict()
+config['cond_ae_static']['device'] = config['device']
+config['cond_ae_static']['is_label'] = False
+config['cond_ae_static']['latent_dim'] = config['latent_dim']
+config['cond_ae_static']['kernel_size'] = 7
+config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
+
+block_setting = [
+    CNBlockConfig(8, 16, 3),
+    CNBlockConfig(16, 32, 3),
+    CNBlockConfig(32, 64, 3),
+    CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
+]
+
+block_setting_reverse = [
+    CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
+    CNBlockConfig(64, 32, 9),
+    CNBlockConfig(32, 16, 3),
+    CNBlockConfig(16, 8, 3),
+    CNBlockConfig(8, 3, 3),
+]
+
+config['cond_ae_static']['encoder_block_settings'] = block_setting
+config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
+config['cond_ae_static']['activation'] = 'tanh'

models/base.py

@@ -6,22 +6,24 @@ from typing import Any, Callable, List, Optional, Sequence
 
 class VariationalEncoder(nn.Module):
     
-    def __init__(self, block_setting: CNBlockConfig, kernel_size: int = 7):
+    def __init__(self, block_setting: List[CNBlockConfig], kernel_size: int = 7, input_features: int = 16, device: str = 'cuda'):
         super(VariationalEncoder, self).__init__()
 
-        self.encoder = ConvNeXt(block_setting=block_setting, kernel_size=kernel_size)
+        self.encoder = ConvNeXt(block_setting=block_setting, kernel_size=kernel_size, input_features=input_features, device=device)
 
-        self.mean_branch = nn.Sequential([CNBlock(block_setting[-1].out_channels, kernel_size=kernel_size) for _ in range(5)])
+        layers = [CNBlock(block_setting[-1].input_channels, kernel_size=kernel_size) for _ in range(5)]
-        self.var_branch = nn.Sequential([CNBlock(block_setting[-1].out_channels, kernel_size=kernel_size) for _ in range(5)])
+        self.mean_branch = nn.Sequential(*layers).to(device)
+        layers = [CNBlock(block_setting[-1].input_channels, kernel_size=kernel_size) for _ in range(5)]
+        self.var_branch = nn.Sequential(*layers).to(device)
 
         self.flatten_mean = nn.Flatten()
         self.flatten_var = nn.Flatten()
 
 
-    def call(self, inputs, training):
+    def forward(self, inputs):
         x = inputs
 
-        x = self.encoder(x, training=training)
+        x = self.encoder(x)
         mean = self.mean_branch(x)
         log_var = self.var_branch(x)
 

models/convnext_orig.py

@@ -66,6 +66,7 @@ class ConvNeXtBase(nn.Module):
         kernel_size: int = 7,
         is_label: bool = False,
         nr_of_labels: Optional[int] = None,
+        input_features: int = 3,
     ) -> None:
         super().__init__()
 
@@ -85,7 +86,7 @@ class ConvNeXtBase(nn.Module):
         # Stem
         firstconv_output_channels = block_setting[0].input_channels
         self.stem = Conv2dNormActivation(
-                3 if not is_label else nr_of_labels,
+                input_features if not is_label else nr_of_labels,
                 firstconv_output_channels,
                 kernel_size=4,
                 stride=4,
@@ -229,6 +230,7 @@ def _convnext(
     is_label: bool,
     nr_of_labels: Optional[int],
     kernel_size: int,
+    input_features: int,
     device='cuda',
     **kwargs: Any,
 ) -> ConvNeXtBase:
@@ -236,17 +238,17 @@ def _convnext(
     if reversed:
         model = ConvNeXtReverseBase(block_setting, stochastic_depth_prob=stochastic_depth_prob, is_label=is_label, nr_of_labels=nr_of_labels, kernel_size=kernel_size, device=device, **kwargs)
     else:
-        model = ConvNeXtBase(block_setting, stochastic_depth_prob=stochastic_depth_prob, kernel_size=kernel_size, is_label=is_label, nr_of_labels=nr_of_labels, device=device, **kwargs)
+        model = ConvNeXtBase(block_setting, stochastic_depth_prob=stochastic_depth_prob, kernel_size=kernel_size, is_label=is_label, nr_of_labels=nr_of_labels, input_features=input_features, device=device, **kwargs)
 
 
     return model
 
 
 class ConvNeXt(nn.Module):
-    def __init__(self, block_setting, stochastic_depth_prob=0.0, reversed=False, is_label=False, nr_of_labels=None, kernel_size=7, device='cuda', **kwargs) -> None:
+    def __init__(self, block_setting, stochastic_depth_prob=0.0, reversed=False, is_label=False, nr_of_labels=None, kernel_size=7, input_features=3, device='cuda', **kwargs) -> None:
         super().__init__()
 
-        self.model = _convnext(block_setting, stochastic_depth_prob, reversed, is_label, nr_of_labels, kernel_size, device=device, **kwargs)
+        self.model: nn.Module = _convnext(block_setting, stochastic_depth_prob, reversed, is_label, nr_of_labels, kernel_size, input_features=input_features, device=device, **kwargs)
 
     def forward(self, x: Tensor) -> Tensor:
         x = self.model(x)

models/cvae_model.py

@@ -1,63 +1,54 @@
 import os
 import time
 import random
-import tensorflow as tf
+import torch
+from torch import nn
 import numpy as np
 import scipy as sp
 # import plotly.graph_objects as go
 # import plotly.express as ex
 
-from custom_utils.custom_utils import load_model
+from utils.checkpoints import load_model
 from models.base import AEEncoder, VariationalEncoder, Decoder
-from models.base import AEEncoderNew, VariationalEncoderNew, DecoderNew
 
 
-class CVAE(tf.keras.Model):
+class CVAE(nn.Module):
     
     def __init__(self, config):
         super(CVAE, self).__init__()
-        self.latent_dim = config['cvae']['latent_dim']
         self.size = config['resolution']
 
         if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
-            self.static_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'])
+            self.static_enc : AEEncoder = AEEncoder(config['cond_ae_static']['encoder_block_settings'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'], device=config['device'])
             if config['static_model'] != '':
                 load_model(self.static_enc, config['static_model'] + '_enc')
 
-            self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['latent_dim'], config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['bottleneck_size'], config['cond_ae_body']['kernel_size'])
+            self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['encoder_block_settings'], config['cond_ae_body']['kernel_size'], config['cond_ae_body']['activation'], device=config['device'])
             if config['body_model'] != '':
                 load_model(self.body_enc, config['body_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'])
+            self.curv_enc : AEEncoder = AEEncoder(config['cond_ae_curv']['encoder_block_settings'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'], device=config['device'], is_label=True, nr_of_labels=7)
             if config['curvature_model'] != '':
                 load_model(self.curv_enc, config['curvature_model'] + '_enc')
 
         if config['freeze_encoders']:
-            if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
+            for param in self.static_enc.parameters(): param.requires_grad = False
-                self.static_enc.trainable = False
+            for param in self.body_enc.parameters(): param.requires_grad = False
-                self.body_enc.trainable = False
             if config['use_curvature']:
-                self.curv_enc.trainable = False
+                for param in self.curv_enc.parameters(): param.requires_grad = False
 
-        self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
+        self.encoder = VariationalEncoder(config['cvae']['encoder_block_settings'], config['cvae']['kernel_size'], config['cvae']['input_features'], device=config['device'])
-                                                 tf.keras.layers.Dense(256, activation='relu'),
+        self.decoder : Decoder = Decoder(config['cvae']['decoder_block_settings'], kernel_size=config['cvae']['kernel_size'], device=config['device'])
-                                                 tf.keras.layers.Dense(128, activation='relu'),
-                                                #  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'])
+        self.latent_shape = (config['cvae']['latent_dim'], 8, 4)
-        self.decoder = Decoder(config['cvae']['decoder_input'], config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
 
         if config['avg_garment_path'] != '':
-            self.avg_garment = np.load(config['avg_garment_path'])
+            self.avg_garment = torch.permute(torch.tensor(np.load(config['avg_garment_path']), device=config['device']), [2,0,1])
         else:
             self.avg_garment = None
 
-        self.add_noise = config['cvae']['add_noise']
-        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 = not config['use_skinning']
 
         if self.use_offsets_over_body:
@@ -68,7 +59,7 @@ class CVAE(tf.keras.Model):
     # @tf.function
     def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
         if noise is None:
-            eps = tf.random.normal(shape=(uv_template.shape[0], self.latent_dim))
+            eps = tf.random.normal(shape=(uv_template.shape[0], 8, 4, self.latent_dim))
         else:
             eps = noise
 
@@ -91,195 +82,49 @@ class CVAE(tf.keras.Model):
         return x
 
 
-    def reparameterize(self, mean, logvar, training, fix_noise=False):
+    def reparameterize(self, mean: torch.Tensor, logvar: torch.Tensor, training: bool = True, fix_noise: bool = False):
         if training == True:
             if not fix_noise:
-                eps = tf.random.normal(shape=mean.shape)
+                eps = torch.randn(size=mean.shape).to(mean.device)
             else:
-                eps = tf.random.normal(shape=(1, mean.shape[1]))
+                eps = torch.randn(size=(1, mean.shape[1]))
-                eps = tf.tile(eps, [mean.shape[0],1])
+                eps = torch.tile(eps, [mean.shape[0],1])
-            out = eps * tf.exp(logvar * .5) + mean
+            out = eps * torch.exp(logvar * 0.5) + mean
         else:
-            out = tf.exp(logvar * .5) + mean
+            out = torch.exp(logvar * 0.5) + mean
         return out
 
 
-    def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
+    def encode_conds(self, uv_template, uv_body_posed, uv_curv):
-        if self.only_curvatures:
+        z_body = self.body_enc(uv_body_posed)
-            z_cond = self.curv_enc(uv_curv, training=training)
+        z_static = self.static_enc(uv_template)
+        if self.use_curvature:
+            z_curv = self.curv_enc(uv_curv)
+            z_cond = torch.concat([z_static, z_body, z_curv], dim=1)
         else:
-            z_body = self.body_enc(uv_body_posed, training=training)
+            z_cond = torch.concat([z_static, z_body], dim=1)
-            z_static = self.static_enc(uv_template, training=training)
-            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
 
 
-    def call(self, inputs, training):
+    def forward(self, inputs):
         uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask = inputs
-        if self.only_curvatures:
+        x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1)
-            x = tf.concat([uv_unposed, uv_curv], axis=-1)
-        else:
-            x = tf.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], axis=-1)
         
-        mean, logvar = self.encoder(x, training=training)
+        mean, logvar = self.encoder(x)
-        z = self.reparameterize(mean, logvar, training)
+        z: torch.Tensor = self.reparameterize(mean, logvar)
-        z_cond = self.encode_conds(uv_template, uv_body_posed, uv_curv, training=training)
+        z = z.view((mean.shape[0], *self.latent_shape))
+        z_cond = self.encode_conds(uv_template, uv_body_posed, uv_curv)
 
-        if self.add_noise and training == True:
+        z = torch.concat([z, z_cond], dim=1)
-            z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
+        x = self.decoder(z)
-
-
-        z = tf.concat([z, z_cond], axis=-1)
-        x = self.decoder(z, training=training)
 
         if self.avg_garment is not None:
-            x = x + self.avg_garment[tf.newaxis,:,:,:]
+            x = x + self.avg_garment[None,:,:,:]
     
         if self.use_offsets_over_body:
             x = x + uv_body_posed
 
-        x = x * uv_mask[:,:,:,tf.newaxis]
+        x = x * uv_mask[:,None,:,:]
 
         return x, mean, logvar
-
-
-
-
-class CVAENew(tf.keras.Model):
-    
-    def __init__(self, config):
-        super(CVAENew, self).__init__()
-        self.size = config['resolution']
-
-        if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
-            self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['encoder_depths'], config['cond_ae_static']['encoder_dims'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'])
-            if config['static_model'] != '':
-                load_model(self.static_enc, config['static_model'] + '_enc')
-
-            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_size'])
-            if config['body_model'] != '':
-                load_model(self.body_enc, config['body_model'] + '_enc')
-
-        if config['use_curvature']:
-            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'])
-            if config['curvature_model'] != '':
-                load_model(self.curv_enc, config['curvature_model'] + '_enc')
-
-        if config['freeze_encoders']:
-            if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
-                self.static_enc.trainable = False
-                self.body_enc.trainable = False
-            if config['use_curvature']:
-                self.curv_enc.trainable = False
-
-        self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
-        self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
-
-        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
-
-        if config['avg_garment_path'] != '':
-            self.avg_garment = np.load(config['avg_garment_path'])
-        else:
-            self.avg_garment = None
-
-        self.add_noise = config['cvae']['add_noise']
-        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 = 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!'
-
-    # @tf.function
-    def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
-        if noise is None:
-            eps = tf.random.normal(shape=(uv_template.shape[0], self.latent_dim))
-        else:
-            eps = noise
-
-        z_cond = self.encode_conds(uv_template, uv_body_posed, uv_curv, training=False)
-        if add_noise:
-            z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
-        
-        z = tf.concat([eps, z_cond], axis=-1)
-
-        x = self.decoder(z, training=False)
-        
-        if self.avg_garment is not None:
-            x = x + self.avg_garment[tf.newaxis,:,:,:]
-        
-        if self.use_offsets_over_body:
-            x = x + uv_body_posed
-
-        x = x * uv_mask[:,:,:,tf.newaxis]
-
-        return x
-
-
-    def reparameterize(self, mean, logvar, training, fix_noise=False):
-        if training == True:
-            if not fix_noise:
-                eps = tf.random.normal(shape=mean.shape)
-            else:
-                eps = tf.random.normal(shape=(1, mean.shape[1]))
-                eps = tf.tile(eps, [mean.shape[0],1])
-            out = eps * tf.exp(logvar * .5) + mean
-        else:
-            out = tf.exp(logvar * .5) + mean
-        return out
-
-
-    def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
-        if self.only_curvatures:
-            z_cond = self.curv_enc(uv_curv, training=training)
-        else:
-            z_body = self.body_enc(uv_body_posed, training=training)
-            z_static = self.static_enc(uv_template, training=training)
-            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
-
-
-    def call(self, inputs, training):
-        uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask = inputs
-        if self.only_curvatures:
-            x = tf.concat([uv_unposed, uv_curv], axis=-1)
-        else:
-            x = tf.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], axis=-1)
-        
-        mean, logvar = self.encoder(x, training=training)
-        z = self.reparameterize(mean, logvar, training)
-        z = self.reshape(z)
-        z_cond = self.encode_conds(uv_template, uv_body_posed, uv_curv, training=training)
-
-        if self.add_noise and training == True:
-            z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
-
-
-        z = tf.concat([z, z_cond], axis=-1)
-        x = self.decoder(z, training=training)
-
-        if self.avg_garment is not None:
-            x = x + self.avg_garment[tf.newaxis,:,:,:]
-    
-        if self.use_offsets_over_body:
-            x = x + uv_body_posed
-
-        x = x * uv_mask[:,:,:,tf.newaxis]
-
-        return x, mean, logvar
-

scripts/cvae.py

@@ -1,21 +1,20 @@
 import os
 import sys
-from configs.config_abl_all_post import config
+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)
+args = vars(parser.parse_args())
+
+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']
-import tensorflow as tf
+# os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
-
-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 time
 import argparse
@@ -26,256 +25,205 @@ import numpy as np
 import plotly.graph_objects as go
 import plotly.express as ex
 from PIL import Image
-from utils.postprocess import fix_collision
 
 if config['is_skirt']:
-    from utils.losses import edge_loss_skirt as edge_loss
+    from losses.losses import edge_loss_skirt as edge_loss
 else:
-    from utils.losses import edge_loss
+    from losses.losses import edge_loss
 
-from utils.losses import collision_ratio, kl_loss, normal_loss, collision_loss
+import torch
-from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
+import torch.nn as nn
-from data.dataset import DatasetFactory, StaticDataset
+import torch.optim as optim
-from custom_utils.smpl import SMPL
+from data.dataset import Dataset
-from models.cvae_model import CVAENew as CVAE
+from models.cond_encoder import AutoEncoder
-from utils.utils import Accumulator
+from utils.checkpoints import CheckpointSaver, load_model
+from utils.utils import InfiniteDataLoader as DataLoader
+from utils.postprocess import fix_collision
+from losses.losses import collision_loss, normal_loss
+from pytorch_msssim import MS_SSIM
+from models.cvae_model import CVAE
+from smpl.smpl_torch import SMPL
+from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision
 
 
 def init_wandb():
-    run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags'])
+    run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
     artifact = wandb.Artifact('code', type='code')
-    config_file_names = [key for key in sys.modules.keys()  if (key.startswith('configs.') or key.startswith('custom_utils.') or key.startswith('utils.') or key.startswith('data.') or key.startswith('models.') or key.startswith('scripts.'))]
+    artifact.add_file('scripts/cvae.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/cvae_model.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_adaptive=False, is_smpl_orig=config['is_cape'])
+uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
 
 
-def kl_loss(mean, logvar):
+def kl_loss(mean: torch.Tensor, logvar: torch.Tensor) -> torch.Tensor:
-    kl_loss = 1 + logvar - tf.square(mean) - tf.exp(logvar)
+    kl_loss = 1 + logvar - torch.square(mean) - torch.exp(logvar)
-    kl_loss = tf.reduce_mean(kl_loss)
+    kl_loss = torch.mean(kl_loss)
     kl_loss *= -0.5
     return kl_loss
 
 
-# 3d loss on posed !!!!!!!!!!!!
-
-# @tf.function
 def train_step(batch):
+    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']
 
-    with tf.GradientTape() as tape:
+    model.train()
-        if config['use_skinning']:
+    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
-            mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+    mesh_pred = uv2mesh(pred)
-        else:
-            mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
 
-        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
+    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])])
+        # shape_offsets = torch.stack([torch.matmul(shape[i, :10], smpl.shapedirs[gender[i]][:, smpl.to_keep]) for i in range(shape.shape[0])])
 
-        mesh_pred = uv2mesh(pred)
+        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
 
-        if config['use_skinning']:
-            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]
+    e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
-            mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
+    c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
-        else:
+    c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
-            mesh_pred_posed = mesh_pred
+    l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+    l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (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'])
+    kl = kl_loss(mean, logvar)
 
-        # is the output already masked?
+    reconstr_loss = l2_loss
+    if config['use_extra_losses']:
+        reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss + n_loss) * config['reg_loss_coeff']
 
-        e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+    loss = reconstr_loss + g_balancing_coeff * kl
-        c_loss, c_ratio = collision_loss(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_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)
 
-        reconstr_loss = l2_loss
+    optimizer.zero_grad()
-        if config['use_extra_losses']:
+    loss.backward()
-            if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True:
+    optimizer.step()
-                reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff']
-            else:
-                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']
 
-        loss = reconstr_loss + g_balancing_coeff * kl
+    model.eval()
+    with torch.inference_mode():
+        mean = torch.mean(mean)
+        logvar = torch.mean(logvar)
+        ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1))
+        metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
     
-        mean = tf.reduce_mean(mean)
-        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) ** 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_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss, 'train/normal_loss': n_loss,
-             # 'train/ms_ssim': ms_ssim, 
+             'train/ms_ssim': ms_ssim, 
             }
  
 
-@tf.function
+
+
 def valid_step(batch):
     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']
 
-    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    model.eval()
+    with torch.inference_mode():
+        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
+        mesh_pred = uv2mesh(pred)
 
-    mesh_pred = uv2mesh(pred)
+        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])])
+            # shape_offsets = torch.stack([torch.matmul(shape[i, :10], smpl.shapedirs[gender[i]][:, smpl.to_keep]) for i in range(shape.shape[0])])
 
-    if config['use_skinning']:
+            mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
-        shape = batch['pose_shape'][:, 72:]
+            mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+        else:
-        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_posed = mesh_pred
 
-        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:
-        mesh_pred_posed = mesh_pred
 
-    # is the output already masked?
+        e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+        c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+        c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
+        l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
+        l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (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'])
+        kl = kl_loss(mean, logvar)
 
-    e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
+        reconstr_loss = l2_loss
-    c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
+        if config['use_extra_losses']:
-    c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio)
+            reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss + n_loss) * config['reg_loss_coeff']
-    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)
 
-    reconstr_loss = l2_loss
+        loss = reconstr_loss + g_balancing_coeff * kl
-    if config['use_extra_losses']:
-        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']
 
-    loss = reconstr_loss + g_balancing_coeff * kl
+        mean = torch.mean(mean)
+        logvar = torch.mean(logvar)
+        ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1))
+        metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
     
-    mean = tf.reduce_mean(mean)
-    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) ** 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/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim, 
+              'valid/normal_loss': n_loss, 'valid/ms_ssim': ms_ssim, 
               }
 
 
-@tf.function
-def test_step(batch):
-    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']
-    
-    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)
-
-    if config['use_skinning']:
-        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(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
-        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 = mesh_pred
-        mesh_orig_posed = mesh_orig
-    
-    mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
-
-
-    # is the output already masked?
-
-    e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
-    c_loss, c_ratio = collision_loss(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_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1), axis=-1))
-    # conc_loss = concept_loss(pred, batch['uv_unposed'])
-    kl = kl_loss(mean, logvar)
-
-    reconstr_loss = l2_loss
-    if config['use_extra_losses']:
-        reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
-            
-    loss = reconstr_loss + g_balancing_coeff * kl
-
-    mean = tf.reduce_mean(mean)
-    logvar = tf.reduce_mean(logvar)
-
-    ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, uv_orig + 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) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
-    euclid_posed = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_posed - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
-    euclid_posed_fixed = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_posed - mesh_pred_posed_fixed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
-
-    return { 'test/loss': loss, 'test/edge_loss': e_loss, 'test/collision_loss': c_loss, 'test/euclid_error': metric, 'test/ms_ssim': ms_ssim,
-             'test/reconstr_loss': reconstr_loss, 'test/collision_ratio': c_ratio, 'test/l2_mesh_loss': l2_mesh_loss, 
-             'test/mean': mean, 'test/logvar': logvar, 'test/kl_loss': kl, 'test/var': np.e ** logvar,
-             'test/euclid_posed': euclid_posed, 'test/euclid_posed_fixed': euclid_posed_fixed }
-
-
 def plot_everything(batch: dict, type: str):
     if config['use_skinning']:
-        mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
+        mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed']
     else:
-        mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
+        mesh_orig, uv_orig = batch['mesh_posed'].cpu().numpy(), batch['uv_posed']
 
-    pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
+    model.eval()
+    with torch.inference_mode():
+        pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
     
-    mesh_pred = uv2mesh(pred).numpy()
+    mesh_pred = uv2mesh(pred).detach().cpu().numpy()
     
-    orig_img = uv_orig
+    orig_img = torch.permute(uv_orig, [0,2,3,1])
-    uv_static_img = batch['uv_static']
+    uv_static_img = torch.permute(batch['uv_static'], [0,2,3,1])
-    uv_body_posed_img = batch['uv_body_posed']
+    uv_body_posed_img = torch.permute(batch['uv_body_posed'], [0,2,3,1])
-    pred_img = pred
+    pred_img = torch.permute(pred, [0,2,3,1])
-    img = tf.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img), axis=2)
+    img = torch.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img), axis=2)
-    imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)]
+    imgs = [wandb.Image((img[i].cpu().numpy() + 1) / 2.0) for i in range(4)]
     
-    F = np.load("custom_utils/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
+    F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
-    mask = batch['mesh_mask'].numpy().astype(bool)
+    mask = batch['mesh_mask'].cpu().numpy().astype(bool)
 
     if config['use_skinning']:
         shape = batch['pose_shape'][:, 72:]
-        gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32)
+        gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long)
-        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])])
+        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()
 
         garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
-        garment_unposed = [garment_unposed[i] + shape_offsets.numpy()[i, mask[i], :] for i in range(mask.shape[0])]
+        garment_unposed = [garment_unposed[i] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])]
-        gt = [mesh_orig[i].numpy()[mask[i], :] + shape_offsets.numpy()[i, mask[i], :] for i in range(pred.shape[0])]
+        gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(pred.shape[0])]
     
         for i in range(mesh_orig.shape[0]):
-            mesh_pred[i, mask[i], :] += shape_offsets.numpy()[i, mask[i], :]
+            mesh_pred[i, mask[i], :] += shape_offsets[i, mask[i], :]
-        mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred).numpy()
+        mesh_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(mesh_pred, device=config['device']))[0].cpu().numpy()
     else:
-        mesh_posed = mesh_pred
+        mesh_posed = mesh_pred.cpu().numpy()
-        gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
+        gt = [mesh_orig[i][mask[i], :] for i in range(pred.shape[0])]
-        garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
+        garment_unposed, faces = maskFacesBatch(mesh_pred.cpu().numpy(), F, mask)
 
-    gt_posed = [batch['mesh_posed'].numpy()[i, mask[i], :] for i in range(mask.shape[0])]
+    gt_posed = [batch['mesh_posed'].cpu().numpy()[i, mask[i], :] for i in range(mask.shape[0])]
 
 
-    body = batch['mesh_body_posed'].numpy()
+    mesh_posed_fixed = fix_collision(torch.tensor(mesh_posed, device=config['device']), batch['mesh_body_posed'], torch.tensor(mask, device=config['device'])).cpu().numpy()
-    mesh_posed_fixed = fix_collision(mesh_posed, body, mask).numpy()
+    body = batch['mesh_body_posed'].cpu().numpy()
 
     garment_posed = [mesh_posed[i, mask[i], :] for i in range(body.shape[0])]
     collision = [np.concatenate((body[i], garment_posed[i]), axis=0) for i in range(len(garment_posed))]
@@ -289,8 +237,8 @@ def plot_everything(batch: dict, type: str):
     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))
+    mean_hist = wandb.Histogram(sequence=mean.cpu().numpy().mean(axis=0))
-    logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0))
+    logvar_hist = wandb.Histogram(sequence=logvar.cpu().numpy().mean(axis=0))
 
     return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
 
@@ -414,6 +362,7 @@ def sample(folder):
         print()
 
 
+
 def test():
     str_split = config['name'].split('_')
     test_idx = str_split.index('test')
@@ -462,108 +411,71 @@ def test():
 
 
 
-if __name__ == '__main__':
+def train():
-    # init_wandb()
+    valid_iterator = iter(valid_dataloader)
-    parser = argparse.ArgumentParser(description='')
-    parser.add_argument('--name', type=str)
-    args = vars(parser.parse_args())
 
-    smpl = SMPL(orig_smpl=config['is_cape'])
+    step = 0
+    for batch in train_dataloader:
+        train_loss = train_step(batch)
+        train_accumulator.update(train_loss)
+
+        if step % 25 == 0:
+            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)) } }
+
+            wandb.log(to_log, step=step)
+            train_accumulator.reset()
+            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 balancing_activated_step == 0:
+                balancing_activated_step = step
+            g_balancing_coeff = g_balancing_coeff + 1 / 10000 
+
+        if step % 10000 == 0:
+            ckpt_saver(model, step, optimizer)
+
+        step += 1
+
+
+if __name__ == '__main__':
+    init_wandb()
+    # parser = argparse.ArgumentParser(description='')
+    # parser.add_argument('--name', type=str)
+    # parser.add_argument('--debug', action='store_true')
+    # args = vars(parser.parse_args())
+
+    smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
     skirt_modifier = '_skirt' if config['is_skirt'] else ''
 
-    factory = DatasetFactory()
+    dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'])
-
+    dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'])
-    dataset_train = factory.get_dataset(folder=config['train_dir'],
+    train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, )
-                                        batch_size=config['batch_size'], 
+    valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=True)
-                                        signature=config['signature_dynamic'],
-                                        resolutions=[config['resolution']], 
-                                        in_memory=config['dataset_in_memory'],
-                                        use_one_hot=config['use_one_hot'],
-                                        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'],
-                                         signature=config['signature_static'], 
-                                         resolutions=[config['resolution']], 
-                                         in_memory=True, 
-                                        is_cape=config['is_cape'])
-
-    dataset_valid = factory.get_dataset(folder=config['valid_dir'],
-                                        batch_size=config['batch_size'], 
-                                        signature=config['signature_dynamic'], 
-                                        resolutions=[config['resolution']], 
-                                        in_memory=config['dataset_in_memory'], 
-                                        use_one_hot=config['use_one_hot'],
-                                        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'],
-                                         signature=config['signature_static'], 
-                                         resolutions=[config['resolution']], 
-                                         in_memory=True, 
-                                        is_cape=config['is_cape'])
-
     train_accumulator = Accumulator()
     valid_accumulator = Accumulator()
 
     model = CVAE(config)
 
-    optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
+    optimizer = optim.Adam(model.parameters(), lr=config['lr'])
+    _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
     balancing_activated_step = 0
     g_balancing_coeff = config['starting_balancing_coeff']
 
-    # sample('checkpoints/cvae_13')
+    ckpt_saver = CheckpointSaver('checkpoints/iccv/' + config['name'], top_n=5)
-    # test()
-
-    ckpt = tf.train.Checkpoint(model=model)
-    manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
 
     if config['pretrained_model'] != '':
         load_model(model, config['pretrained_model'])
 
-    # load_model(model, 'checkpoints/' + config['name'])
+    train()
- 
-    valid_iterator = iter(dataset_valid)
-    step = 0
-    for batch in dataset_train:
-        batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
-
-        train_loss = train_step(batch)
-        train_accumulator.update(train_loss)
-
-        data_valid = valid_iterator.get_next()
-        data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic']))
-        valid_loss = valid_step(data_valid)
-        valid_accumulator.update(valid_loss)
-
-
-        if train_accumulator.get()['train/euclid_error'] < (config['balancing_activation_limit'] if 'balancing_activation_limit' in config.keys() else 0.017):
-            if balancing_activated_step == 0:
-                balancing_activated_step = step
-            g_balancing_coeff = g_balancing_coeff + 1 / 10000     
-
-
-        if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
-            to_log = { **train_accumulator.get(), **valid_accumulator.get(), **{ '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)) } }
-
-            to_log = { **to_log, **{ 'train/balancing_coeff': g_balancing_coeff } }
-        
-            wandb.log(to_log, step = step)
-            train_accumulator.reset()
-            valid_accumulator.reset()
-            
-        if step % 5000 == 0:
-            manager.save(checkpoint_number=step)
-
-        print(step)
-
-        step += 1
-