update pyramid for ablation

models/pyramid_level.py

@@ -100,7 +100,7 @@ from models.upscaler import Upscaler
 
 class PyramidLevel(nn.Module):
     
-    def __init__(self, config):
+    def __init__(self, config, use_normals=True):
         super(PyramidLevel, self).__init__()
         self.size = config['resolution']
 
@@ -114,6 +114,7 @@ class PyramidLevel(nn.Module):
             load_model(self.upscale_enhancer, config['upscale_enhancer'])
             for param in self.upscale_enhancer.parameters(): param.requires_grad = False
 
+        self.use_normals = use_normals
 
     def enhance(self, low, mask):
         x = self.upscale_enhancer([low, mask])
@@ -152,9 +153,13 @@ class PyramidLevel(nn.Module):
 
 
     def forward(self, inputs, z_cond):
-        uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs
+        uv_unposed, uv_template, uv_body_posed, uv_normals, uv_mask, uv_mask_high = inputs
+
+        if self.use_normals:
+            x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_normals], dim=1)
+        else:   
+            x = torch.concat([uv_unposed, uv_template, uv_body_posed], dim=1)
             
-        x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1)
         mean, logvar = self.encoder(x)
         z = self.reparameterize(mean, logvar)
         z = torch.reshape(z, (mean.shape[0], -1, 8, 4))

models/pyramid_model.py

@@ -3,11 +3,6 @@ import time
 import random
 import torch
 from torch import nn
-import torch.nn.functional as F
-# import numpy as np
-# import scipy as sp
-# import plotly.graph_objects as go
-# import plotly.express as ex
 
 from utils.checkpoints import load_model
 from models.base import AEEncoder
@@ -15,123 +10,6 @@ from models.pyramid_level import PyramidLevel
 from torchvision.transforms import Resize
 from torchvision.transforms.functional import InterpolationMode
 
-# class Pyramid(nn.Module):
-    
-#     def __init__(self, config):
-#         super(Pyramid, self).__init__()
-
-#         self.static_enc : AEEncoder = AEEncoder(config['cond_ae_static']['encoder_block_settings'], kernel_size=config['cond_ae_static']['kernel_size'], activation=config['cond_ae_static']['activation'])
-#         if config['pyramid']['static_model'] != '':
-#             load_model(self.static_enc, config['pyramid']['static_model'] + '_enc')
-
-#         self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['encoder_block_settings'], kernel_size=config['cond_ae_body']['kernel_size'], activation=config['cond_ae_body']['activation'])
-#         if config['pyramid']['body_model'] != '':
-#             load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
-
-#         self.curv_enc : AEEncoder = AEEncoder(config['cond_ae_curv']['encoder_block_settings'], kernel_size=config['cond_ae_curv']['kernel_size'], activation=config['cond_ae_curv']['activation'])
-#         if config['pyramid']['curvature_model'] != '':
-#             load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
-
-#         if config['freeze_encoders']:
-#             for param in self.static_enc.parameters(): param.requires_grad = False
-#             for param in self.body_enc.parameters(): param.requires_grad = False
-#             for param in self.curv_enc.parameters(): param.requires_grad = False
-
-
-#         self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae_static': config['cond_ae_static'], 'cond_ae_body': config['cond_ae_body'], 'cond_ae_curv': config['cond_ae_curv'], } }) for i in range(len(config['pyramid']['levels']))]
-
-#         # if config['is_cape']:
-#         #     if len(config['pyramid']['resolutions']) == 2:
-#         #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #     if len(config['pyramid']['resolutions']) == 3:
-#         #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #         self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #     if len(config['pyramid']['resolutions']) == 4:
-#         #         self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #         self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         #         self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # else:
-
-#         # if len(config['pyramid']['resolutions']) == 2:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # if len(config['pyramid']['resolutions']) == 3:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-#         #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # if len(config['pyramid']['resolutions']) == 4:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-#         #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-#         #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-#         # if len(config['pyramid']['resolutions']) == 5:
-#         #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)])
-#         #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-#         #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-#         #     self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-
-#         # self.add_noise = config['pyramid']['add_noise']
-#         # self.noise_amount = config['pyramid']['noise_amount']
-#         self.use_offsets = config['use_offsets']
- 
-#         # self.upscale_enhancer = None
-#         # if config['pyramid']['final_upscale_enhancer'] != '':
-#         #     k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-#         #     self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
-#         #     load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-#         #     self.upscale_enhancer.trainable = False
-
-#     def enhance(self, low, mask):
-#         x = self.upscale_enhancer([low, mask])
-#         return x
-
-#     def encode_conds(self, uv_template, uv_body_posed, uv_curv):
-#         z_static = self.static_enc(uv_template)
-#         z_body = self.body_enc(uv_body_posed)
-#         z_curv = self.curv_enc(uv_curv)
-
-#         z_cond = torch.concat([z_static, z_body, z_curv], dim=-1)
-
-#         return z_cond
-
-#     def call(self, inputs):
-#         levels_input, conds = inputs
-#         uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2]
-
-#         z_cond = self.encode_conds(uv_static, uv_body, uv_curv)
-
-#         # if self.add_noise == True and training == True:
-#         #     z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
-
-#         out_levels = []
-#         pred, mean, logvar = self.levels[0](levels_input[0], z_cond)
-#         if self.use_offsets:
-#             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 = F.interpolate(pred, size=(self.levels[1].size, self.levels[1].size//2), mode='bilinear')
-#             out_levels.append([pred, mean, logvar])
-#             pred = pred * levels_input[1][-2][:,None,:,:]
-#         else:
-#             pred = self.enhance(pred, levels_input[0][-2])
-#             pred = F.interpolate(pred, size=(512, 256), mode='bilinear')
-#             pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
-#             out_levels.append([pred, mean, logvar])
-
-#         for i in range(1, len(self.levels)):
-#             pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond)
-#             pred = pred + pred_level
-#             if i != len(self.levels) - 1:
-#                 pred = self.levels[i].enhance(pred, levels_input[i][-2])
-#                 out_levels.append([pred, mean, logvar])
-#                 pred = F.interpolate(pred, size=(self.levels[i+1].size, self.levels[i+1].size//2), mode='bilinear')
-#                 pred = pred * levels_input[i+1][-2][:,None,:,:]
-#             else:
-#                 pred = self.enhance(pred, levels_input[i][-1])
-#                 pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
-#                 pred = F.interpolate(pred, size=(512, 256), mode='bilinear')
-#                 out_levels.append([pred, mean, logvar])
-
-#         return out_levels
-
-
 
 class Pyramid(nn.Module):
     
@@ -146,6 +24,7 @@ class Pyramid(nn.Module):
         if config['body_model'] != '':
             load_model(self.body_enc, config['body_model'] + '_enc')
 
+        if config['use_normals']:
             self.norm_enc : AEEncoder = AEEncoder(config['cond_ae_norm']['encoder_block_settings'], config['cond_ae_norm']['kernel_size'], config['cond_ae_norm']['activation'], device=config['device'])
             if config['normals_model'] != '':
                 load_model(self.norm_enc, config['normals_model'] + '_enc')
@@ -153,50 +32,25 @@ class Pyramid(nn.Module):
         if config['freeze_encoders']:
             for param in self.static_enc.parameters(): param.requires_grad = False
             for param in self.body_enc.parameters(): param.requires_grad = False
+            if config['use_normals']:
                 for param in self.norm_enc.parameters(): param.requires_grad = False
 
-        self.levels = nn.ModuleList([PyramidLevel({ **config['pyramid']['levels'][i] }) for i in range(len(config['pyramid']['levels']))])
+        self.levels = nn.ModuleList([PyramidLevel({ **config['pyramid']['levels'][i] }, use_normals=config['use_normals']) for i in range(len(config['pyramid']['levels']))])
 
         self.resizers = { res: Resize(size=(res, int(res/2)), interpolation=InterpolationMode.BILINEAR).to(config['device']) for res in config['pyramid']['resolutions'] }
         self.resizers[512] = Resize(size=(512, 256), interpolation=InterpolationMode.BILINEAR).to(config['device'])
 
-
+        self.use_normals = config['use_normals']
-        # if len(config['pyramid']['resolutions']) == 2:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 3:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 4:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-        # if len(config['pyramid']['resolutions']) == 5:
-        #     self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)])
-        #     self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)])
-        #     self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)])
-        #     self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)])
-
-        # self.add_noise = config['pyramid']['add_noise']
-        # self.noise_amount = config['pyramid']['noise_amount']
-        # self.use_offsets = config['use_offsets']
- 
-        # self.upscale_enhancer = None
-        # if config['pyramid']['final_upscale_enhancer'] != '':
-        #     k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5))
-        #     self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size)
-        #     load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
-        #     self.upscale_enhancer.trainable = False
-
-    # def enhance(self, low, mask, training):
-    #     x = self.upscale_enhancer([low, mask], training=training)
-    #     return x
 
     def encode_conds(self, uv_template, uv_body_posed, uv_norm):
         z_static = self.static_enc(uv_template)
         z_body = self.body_enc(uv_body_posed)
-        z_norm = self.norm_enc(uv_norm)
 
+        if self.use_normals:
+            z_norm = self.norm_enc(uv_norm)
             z_cond = torch.concat([z_static, z_body, z_norm], dim=1)
+        else:
+            z_cond = torch.concat([z_static, z_body], dim=1)
 
         return z_cond
 
@@ -206,9 +60,6 @@ class Pyramid(nn.Module):
 
         z_cond = self.encode_conds(uv_static, uv_body, uv_norm)
 
-        # if self.add_noise == True and training == True:
-        #     z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
-
         out_levels = []
         pred, mean, logvar = self.levels[0](levels_input[0], z_cond)
         # if self.use_offsets:
@@ -219,7 +70,6 @@ class Pyramid(nn.Module):
             out_levels.append([pred, mean, logvar])
             pred = pred * levels_input[1][-2][:,None,:,:]
         else:
-            # pred = self.enhance(pred, levels_input[0][-2], training=training)
             pred = self.levels[0].enhance(pred, levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
             pred = self.resizers[512](pred)
             pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
@@ -227,12 +77,8 @@ class Pyramid(nn.Module):
 
         for i in range(1, len(self.levels)):
             input = levels_input[i]
-            # input[0] = input[0] - pred
+            input[0] = input[0] - pred
-            # input_min, input_max = tf.reduce_min(input[0], axis=[1,2,3]), tf.reduce_max(input[0], axis=[1,2,3])
-            # input[0] = (input[0] - input_min[:,None,None,None]) / (input_max - input_min)[:,None,None,None]
-            # input[0] = input[0] * input[-2][:,None,:,:] # uv_mask_res
             pred_level, mean, logvar = self.levels[i](input, z_cond)
-            # pred_level = ( (pred_level * (input_max - input_min)[:,None,None,None]) + input_min[:,None,None,None] ) * input[-2][:,:,:,None] # uv_mask_res
             pred = pred + pred_level
             if i != len(self.levels) - 1:
                 pred = self.levels[i].enhance(pred, levels_input[i][-2])
@@ -240,8 +86,6 @@ class Pyramid(nn.Module):
                 pred = self.resizers[self.levels[i+1].size](pred)
                 pred = pred * levels_input[i+1][-2][:,None,:,:]
             else:
-                # if self.upscale_enhancer is not None:
-                    # pred = self.enhance(pred, levels_input[-1][-2], training=training)
                 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

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_cape_m import config
+    from configs.iccvw.pyr_64_reg import config
 else:
     config_module = importlib.import_module(args['config'])
     config = config_module.config
@@ -238,6 +238,12 @@ def train_step(batch):
     res_modifier = '_' + str(res) if res != 512 else ''
     pred, mean, logvar = out_levels[i]
 
+
+
+    l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2]))
+    kl = kl_loss(mean, logvar)
+
+    if config['use_extra_losses']:
         mesh_pred = uv2mesh(pred)
 
         if config['use_skinning']:
@@ -250,60 +256,23 @@ def train_step(batch):
         else:
             mesh_pred_posed = mesh_pred
 
-    # is the output already masked?
-    # ms_ssim = torch.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)))
-    # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-
         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), dim=-1), dim=[1, 2]))
-    l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['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_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
-    kl = kl_loss(mean, logvar)
+        l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
         
-    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 + n_loss * config['reg_loss_coeff']
     else:
         reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
     
-    if config['use_norm_loss'] and step > 2000:
-        reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
-    
     kl_total += kl
     loss: torch.Tensor = reconstr_loss_total + g_balancing_coeff * kl_total
 
-    # scaler.scale(loss).backward()
-    # scaler.step(optimizer)
-    # scaler.update()
-    # optimizer.zero_grad()
-
-    # b = 0
-    # from custom_utils.custom_utils import _maskFaces
-    # mesh_mask = batch['mesh_mask'][b].cpu().numpy()
-    # faces = np.load('smpl/smpl_faces_skirt.npy') if batch['garment'][b] in ['Skirt', 'Dress'] else np.load('smpl/smpl_faces.npy')
-    # faces_body = np.load('smpl/smpl_faces.npy')
-    # _, faces = _maskFaces(np.zeros((14475, 3)), faces, mesh_mask)
-
-    # # fig = go.Figure(data=[go.Mesh3d(x=batch['mesh_posed'].cpu().numpy()[0,mesh_mask,0], y=batch['mesh_posed'].cpu().numpy()[0,mesh_mask,2], z=batch['mesh_posed'].cpu().numpy()[0,mesh_mask,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=1),
-    # #                         go.Mesh3d(x=batch['mesh_body_posed'].cpu().numpy()[0,:,0], y=batch['mesh_body_posed'].cpu().numpy()[0,:,2], z=batch['mesh_body_posed'].cpu().numpy()[0,:,1], i=faces_body[:,0], j=faces_body[:,1], k=faces_body[:,2], color='lightblue', opacity=1),
-    # # ])
-    
-    # fig = go.Figure(data=[go.Mesh3d(x=mesh_orig.cpu().numpy()[0,mesh_mask,0], y=mesh_orig.cpu().numpy()[0,mesh_mask,2], z=mesh_orig.cpu().numpy()[0,mesh_mask,1], i=faces[:,0], j=faces[:,1], k=faces[:,2], color='lightpink', opacity=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()
-
-    # ex.imshow((uv_orig[b].cpu().numpy().transpose(1,2,0) + 1) / 2).show()
-    # upscaled = model.levels[0].enhance(levels_input[0][0], levels_input[0][-2])  # levels_input[i][-2]=uv_mask_res
-    # upscaled = model.resizers[512](upscaled)
-    # ex.imshow((levels_input[0][0][b].cpu().numpy().transpose(1,2,0) + 1) / 2).show()
-    # ex.imshow((upscaled[b].cpu().numpy().transpose(1,2,0) + 1) / 2).show()
-
-
     optimizer.zero_grad()
     loss.backward()
     optimizer.step()
@@ -313,13 +282,33 @@ def train_step(batch):
         mean = torch.mean(mean)
         logvar = torch.mean(logvar)
 
+        if not config['use_extra_losses']:
+            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
+                
+            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_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['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_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+        
         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'])
 
     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/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 }
@@ -359,27 +348,23 @@ def valid_step(batch):
         else:
             mesh_pred_posed = mesh_pred
 
-        # is the output already masked?
-        # ms_ssim = torch.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)))
-        # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
-
         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), dim=-1), dim=[1, 2]))
         l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['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_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
+       
         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'] 
-        else:
-            reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
-
                 if config['use_norm_loss'] and step > 2000:
                     reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff']
+        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
@@ -825,9 +810,9 @@ def train():
             print(step)
 
         if train_loss['train/euclid_error'] < config['balancing_activation_limit']:
-            g_balancing_coeff += 1 / 10000 
+            g_balancing_coeff += 1 / 50000 
 
-        if step % 25000 == 0:
+        if step % 25000 == 0 and not args['debug']:
             ckpt_saver(model, step, optimizer, None)
 
         step += 1
@@ -874,11 +859,13 @@ if __name__ == '__main__':
     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
+        if config['use_normals']:
             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'] if 'pretrained_pyramid_iteration' in config.keys() 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
+        if config['use_normals']:
             for param in model.norm_enc.parameters(): param.requires_grad = False
 
     # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])