luni/cvpr_2023
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update pyramid for ablation

Browse Source
This commit is contained in:
luni
2023-07-04 18:22:20 +02:00
parent c42b32ac14
commit 84b5af96cc
3 changed files with 74 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/pyramid_level.py
+8 -3
View File
@@ -100,7 +100,7 @@ from models.upscaler import Upscaler
class PyramidLevel(nn.Module): class PyramidLevel(nn.Module):
def __init__(self, config): def __init__(self, config, use_normals=True):
super(PyramidLevel, self).__init__() super(PyramidLevel, self).__init__()
self.size = config['resolution'] self.size = config['resolution']
@@ -114,6 +114,7 @@ class PyramidLevel(nn.Module):
load_model(self.upscale_enhancer, config['upscale_enhancer']) load_model(self.upscale_enhancer, config['upscale_enhancer'])
for param in self.upscale_enhancer.parameters(): param.requires_grad = False for param in self.upscale_enhancer.parameters(): param.requires_grad = False
self.use_normals = use_normals
def enhance(self, low, mask): def enhance(self, low, mask):
x = self.upscale_enhancer([low, mask]) x = self.upscale_enhancer([low, mask])
@@ -152,9 +153,13 @@ class PyramidLevel(nn.Module):
def forward(self, inputs, z_cond): 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
x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1) 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)
mean, logvar = self.encoder(x) mean, logvar = self.encoder(x)
z = self.reparameterize(mean, logvar) z = self.reparameterize(mean, logvar)
z = torch.reshape(z, (mean.shape[0], -1, 8, 4)) z = torch.reshape(z, (mean.shape[0], -1, 8, 4))
models/pyramid_model.py
+14 -170
View File
@@ -3,11 +3,6 @@ import time
import random import random
import torch import torch
from torch import nn 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 utils.checkpoints import load_model
from models.base import AEEncoder from models.base import AEEncoder
@@ -15,123 +10,6 @@ from models.pyramid_level import PyramidLevel
from torchvision.transforms import Resize from torchvision.transforms import Resize
from torchvision.transforms.functional import InterpolationMode 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): class Pyramid(nn.Module):
@@ -146,57 +24,33 @@ class Pyramid(nn.Module):
if config['body_model'] != '': if config['body_model'] != '':
load_model(self.body_enc, config['body_model'] + '_enc') load_model(self.body_enc, config['body_model'] + '_enc')
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['use_normals']:
if config['normals_model'] != '': 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'])
load_model(self.norm_enc, config['normals_model'] + '_enc') if config['normals_model'] != '':
load_model(self.norm_enc, config['normals_model'] + '_enc')
if config['freeze_encoders']: if config['freeze_encoders']:
for param in self.static_enc.parameters(): param.requires_grad = False 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.body_enc.parameters(): param.requires_grad = False
for param in self.norm_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 = { 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.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): def encode_conds(self, uv_template, uv_body_posed, uv_norm):
z_static = self.static_enc(uv_template) z_static = self.static_enc(uv_template)
z_body = self.body_enc(uv_body_posed) z_body = self.body_enc(uv_body_posed)
z_norm = self.norm_enc(uv_norm)
z_cond = torch.concat([z_static, z_body, z_norm], dim=1) 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 return z_cond
@@ -206,9 +60,6 @@ class Pyramid(nn.Module):
z_cond = self.encode_conds(uv_static, uv_body, uv_norm) 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 = [] out_levels = []
pred, mean, logvar = self.levels[0](levels_input[0], z_cond) pred, mean, logvar = self.levels[0](levels_input[0], z_cond)
# if self.use_offsets: # if self.use_offsets:
@@ -219,7 +70,6 @@ class Pyramid(nn.Module):
out_levels.append([pred, mean, logvar]) out_levels.append([pred, mean, logvar])
pred = pred * levels_input[1][-2][:,None,:,:] pred = pred * levels_input[1][-2][:,None,:,:]
else: 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.levels[0].enhance(pred, levels_input[0][-2]) # levels_input[i][-2]=uv_mask_res
pred = self.resizers[512](pred) pred = self.resizers[512](pred)
pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask 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)): for i in range(1, len(self.levels)):
input = levels_input[i] 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, 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 pred = pred + pred_level
if i != len(self.levels) - 1: if i != len(self.levels) - 1:
pred = self.levels[i].enhance(pred, levels_input[i][-2]) 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 = self.resizers[self.levels[i+1].size](pred)
pred = pred * levels_input[i+1][-2][:,None,:,:] pred = pred * levels_input[i+1][-2][:,None,:,:]
else: 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.levels[-1].enhance(pred, levels_input[-1][-2])
pred = self.resizers[512](pred) pred = self.resizers[512](pred)
pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask
scripts/cvae_pyramid.py
+52 -65
View File
@@ -11,7 +11,7 @@ parser.add_argument('--debug', action='store_true')
args = vars(parser.parse_args()) args = vars(parser.parse_args())
if args['debug']: if args['debug']:
from configs.iccvw.pyr_64_cape_m import config from configs.iccvw.pyr_64_reg import config
else: else:
config_module = importlib.import_module(args['config']) config_module = importlib.import_module(args['config'])
config = config_module.config config = config_module.config
@@ -238,72 +238,41 @@ def train_step(batch):
res_modifier = '_' + str(res) if res != 512 else '' res_modifier = '_' + str(res) if res != 512 else ''
pred, mean, logvar = out_levels[i] 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
# 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_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) kl = kl_loss(mean, logvar)
if config['use_extra_losses']: if 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)
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['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_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) reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
if not config['is_cape']: if not config['is_cape']:
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 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: else:
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) 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 kl_total += kl
loss: torch.Tensor = reconstr_loss_total + g_balancing_coeff * kl_total 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() optimizer.zero_grad()
loss.backward() loss.backward()
optimizer.step() optimizer.step()
@@ -313,13 +282,33 @@ def train_step(batch):
mean = torch.mean(mean) mean = torch.mean(mean)
logvar = torch.mean(logvar) 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)) 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']) 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, 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/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/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 } return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
@@ -359,28 +348,24 @@ def valid_step(batch):
else: else:
mesh_pred_posed = mesh_pred 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'])) 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 = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) 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_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)) 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']) 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) kl = kl_loss(mean, logvar)
if config['use_extra_losses']: if config['use_extra_losses']:
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
if not config['is_cape']: if not config['is_cape']:
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] 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: else:
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) 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 kl_total += kl
loss = reconstr_loss_total + g_balancing_coeff * kl_total loss = reconstr_loss_total + g_balancing_coeff * kl_total
@@ -825,9 +810,9 @@ def train():
print(step) print(step)
if train_loss['train/euclid_error'] < config['balancing_activation_limit']: 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) ckpt_saver(model, step, optimizer, None)
step += 1 step += 1
@@ -874,12 +859,14 @@ if __name__ == '__main__':
if len(config['pyramid']['resolutions']) == 1: if len(config['pyramid']['resolutions']) == 1:
for param in model.static_enc.parameters(): param.requires_grad = False 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.body_enc.parameters(): param.requires_grad = False
for param in model.norm_enc.parameters(): param.requires_grad = False if config['use_normals']:
for param in model.norm_enc.parameters(): param.requires_grad = False
else: 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.static_enc.parameters(): param.requires_grad = False
for param in model.body_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 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']) # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer'])
# model.levels[0].upscale_enhancer.trainable = False # model.levels[0].upscale_enhancer.trainable = False