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

pyramid pipeline ready

Browse Source
This commit is contained in:
luni
2023-05-22 00:13:39 +02:00
parent 8e0d061104
commit 52e461ca47
6 changed files with 938 additions and 793 deletions
Download Patch File Download Diff File Expand all files Collapse all files
configs/pyr_32.py
+296
View File
@@ -0,0 +1,296 @@
from utils.convnext_utils import CNBlockConfig
config = dict()
config['gpu'] = '5'
config['name'] = 'pyr_torch_32'
config['notes'] = ''
config['tags'] = ['pyr', 'iccv', 'torch']
config['script'] = 'scripts/cvae_pyramid.py'
config['batch_size'] = 4
config['is_skirt'] = False
config['is_cape'] = False
config['device'] = 'cuda'
config['use_skinning'] = True # and deshaping
config['remove_global_orientation'] = True
config['use_extra_losses'] = True # edge, collision, 3d mesh
config['use_offsets'] = False
config['use_norm_loss'] = True
config['use_curvature'] = True
config['pretrained_model'] = ''
config['pretrained_model_iteration'] = ''
config['pyramid'] = dict()
config['pyramid']['resolutions'] = [32]
config['pyramid']['pretrained_pyramid'] = ''
config['pyramid']['pretrained_pyramid_iteration'] = ''
config['pyramid']['final_upscale_enhancer'] = ''
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['dataset_in_memory'] = False
config['resolution'] = None
config['smpl_res'] = 14475
if config['is_cape']:
config['smpl_res'] = 3638
config['lr'] = 0.0001
config['starting_balancing_coeff'] = 0.001
config['balancing_activation_limit'] = 0.015
config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
config['avg_garment_path'] = ''
config['bottleneck_scale'] = 2
config['signature']: set = { 'id',
'frame_nr',
'pose_shape',
'uv_body_posed',
'mesh_body_posed',
'mesh_posed',
'mesh_unposed',
'uv_unposed',
'uv_curvature',
'uv_static',
'mesh_mask',
'uv_mask',
}
config['pyramid']['is_label'] = False
# config['pyramid']['add_noise'] = False
# config['pyramid']['noise_amount'] = 0.0
config['pyramid']['loss_weights'] = [1,1,1,1,1]
for res in config['pyramid']['resolutions']:
if res != 512:
res_modifier = '_' + str(res)
config['signature'].add('uv_body_posed' + res_modifier)
config['signature'].add('uv_unposed' + res_modifier)
config['signature'].add('uv_curvature' + res_modifier)
config['signature'].add('uv_static' + res_modifier)
config['signature'].add('uv_mask' + res_modifier)
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['freeze_encoders'] = True
config['pyramid']['levels'] = []
for res in config['pyramid']['resolutions']:
if res == 512:
level = dict()
level['resolution'] = 512
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['kernel_size'] = 7
level['upscale_enhancer'] = ''
level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
block_setting = [
CNBlockConfig(16, 32, 3),
CNBlockConfig(32, 64, 3),
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 64, 9),
CNBlockConfig(64, 32, 3),
CNBlockConfig(32, 16, 3),
CNBlockConfig(16, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 256:
level = dict()
level['resolution'] = 256
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_256'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 3),
CNBlockConfig(128, 128, 3),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 3),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 3),
CNBlockConfig(128, 128, 9),
CNBlockConfig(128, 65, 3),
CNBlockConfig(64, 3, 3),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 128:
level = dict()
level['resolution'] = 128
level['kernel_size'] = 5
level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_128'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
block_setting = [
CNBlockConfig(64, 128, 9),
CNBlockConfig(128, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 128, 9),
CNBlockConfig(128, 128, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 64:
level = dict()
level['resolution'] = 64
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_64'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
block_setting = [
CNBlockConfig(64, level['bottleneck_size'], 9),
CNBlockConfig(level['bottleneck_size'], None, 9),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 64, 9),
CNBlockConfig(64, 3, 9),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
elif res == 32:
level = dict()
level['resolution'] = 32
level['kernel_size'] = 3
level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_32'
level['upscale_enhancer_freeze'] = True
level['bottleneck_size'] = 64 * config['bottleneck_scale']
level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3
block_setting = [
CNBlockConfig(level['bottleneck_size'], None, 16),
]
block_setting_reverse = [
CNBlockConfig(level['bottleneck_size'] * 2, 3, 16),
]
level['encoder_block_settings'] = block_setting
level['decoder_block_settings'] = block_setting_reverse
config['pyramid']['levels'].append(level)
else:
raise NotImplementedError
####################### 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/pyramid_level.py
+117 -125
View File
@@ -1,176 +1,168 @@
import os import os
import time import time
import random import random
import tensorflow as tf import torch
from torch import nn
import numpy as np import numpy as np
import scipy as sp import scipy as sp
# import plotly.graph_objects as go # import plotly.graph_objects as go
# import plotly.express as ex # 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, VariationalEncoderNew, DecoderNew from models.base import AEEncoder, VariationalEncoder, Decoder
from models.upscaler import UpscalerBasic, UpscalerBasicConv, UpscalerBasicNew from models.upscaler import Upscaler
class PyramidLevel(tf.keras.Model):
# class PyramidLevel(nn.Module):
# def __init__(self, config):
# super(PyramidLevel, self).__init__()
# self.latent_dim = config['latent_dim']
# self.size = config['resolution']
# self.encoder: VariationalEncoder = VariationalEncoder(config['encoder_block_settings'], config['input_features'], kernel_size=config['kernel_size'])
# self.decoder: Decoder = Decoder(config['decoder_block_settings'], config['kernel_size'])
# self.upscale_enhancer = None
# if config['upscale_enhancer'] != '':
# k_size = config['upscale_enhancer_kernel_size']
# self.upscale_enhancer = Upscaler(config['resolution'], kernel_size=k_size)
# load_model(self.upscale_enhancer, config['upscale_enhancer'])
# for param in self.upscale_enhancer.parameters(): param.requires_grad = False
# if config['avg_garment_path'] != '':
# self.avg_garment = np.load(config['avg_garment_path'])
# else:
# self.avg_garment = None
# def enhance(self, low, mask, training=None):
# x = self.upscale_enhancer([low, mask], training=training)
# return x
# def sample(self, z_cond, uv_mask, noise=None):
# if noise is None:
# eps = torch.normal(shape=(uv_mask.shape[0], self.latent_dim))
# else:
# eps = noise
# z = torch.concat([eps, z_cond], dim=-1)
# x = self.decoder(z)
# if self.avg_garment is not None:
# x = x + self.avg_garment[None,:,:,:]
# x = x * uv_mask[:,None,:,:]
# return x
# def reparameterize(self, mean, logvar, training, fix_noise=False):
# if training == True:
# if not fix_noise:
# eps = torch.normal(mean=0.0, std=1.0, size=mean.shape)
# else:
# eps = torch.normal(mean=0.0, std=1.0, size=mean.shape)
# eps = torch.tile(eps, [mean.shape[0],1])
# out = eps * torch.exp(logvar * .5) + mean
# else:
# out = torch.exp(logvar * .5) + mean
# return out
# def call(self, inputs, z_cond, training=None):
# uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs
# x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1)
# mean, logvar = self.encoder(x, training=training)
# z = self.reparameterize(mean, logvar, training)
# z = torch.concat([z, z_cond], dim=-1)
# x = self.decoder(z, training=training)
# if self.avg_garment is not None:
# x = x + self.avg_garment[None,:,:,:]
# x = x * uv_mask[:,None,:,:]
# # if self.upscale_enhancer is not None:
# # pred_low = self.enhance(x, uv_mask, training=training)
# # x = tf.image.resize(pred_low, (512, 256), tf.image.ResizeMethod.LANCZOS5)
# # x = x * uv_mask_high[:,:,:,tf.newaxis]
# return x, mean, logvar
class PyramidLevel(nn.Module):
def __init__(self, config): def __init__(self, config):
super(PyramidLevel, self).__init__() super(PyramidLevel, self).__init__()
self.latent_dim = config['latent_dim']
self.size = config['resolution'] self.size = config['resolution']
self.encoder = VariationalEncoder(config['latent_dim'], config['encoder_depths'], config['encoder_dims'], kernel_size=config['kernel_size']) self.encoder: VariationalEncoder = VariationalEncoder(config['encoder_block_settings'], input_features=config['input_features'], kernel_size=config['kernel_size'])
self.decoder = Decoder(config['decoder_input'], config['decoder_depths'], config['decoder_dims'], config['kernel_size']) self.decoder: Decoder = Decoder(config['decoder_block_settings'], config['kernel_size'])
self.upscale_enhancer = None self.upscale_enhancer = None
if config['upscale_enhancer'] != '': if config['upscale_enhancer'] != '':
k_size = config['upscale_enhancer_kernel_size'] if 'upscale_enhancer_kernel_size' in config.keys() else ((3 if config['resolution'] <= 64 else 5)) k_size = config['kernel_size']
self.upscale_enhancer = UpscalerBasicConv(config['resolution'], kernel_size=k_size) self.upscale_enhancer = Upscaler(config['resolution'], kernel_size=k_size).to('cuda')
load_model(self.upscale_enhancer, config['upscale_enhancer']) load_model(self.upscale_enhancer, config['upscale_enhancer'])
self.upscale_enhancer.trainable = not config['upscale_enhancer_freeze'] for param in self.upscale_enhancer.parameters(): param.requires_grad = False
if config['avg_garment_path'] != '':
self.avg_garment = np.load(config['avg_garment_path'])
else:
self.avg_garment = None
def enhance(self, low, mask, training=None): def enhance(self, low, mask):
x = self.upscale_enhancer([low, mask], training=training) x = self.upscale_enhancer([low, mask])
return x return x
def sample(self, z_cond, uv_mask, noise=None): def sample(self, z_cond, uv_mask, noise=None):
if noise is None: if noise is None:
eps = tf.random.normal(shape=(uv_mask.shape[0], self.latent_dim)) eps = torch.normal(shape=(uv_mask.shape[0], self.latent_dim))
else: else:
eps = noise eps = noise
z = tf.concat([eps, z_cond], axis=-1) z = torch.concat([eps, z_cond], dim=-1)
x = self.decoder(z) x = self.decoder(z)
if self.avg_garment is not None: if self.avg_garment is not None:
x = x + self.avg_garment[tf.newaxis,:,:,:] x = x + self.avg_garment[None,:,:,:]
x = x * uv_mask[:,:,:,tf.newaxis] x = x * uv_mask[:,None:,:]
return x return x
def reparameterize(self, mean, logvar, training, fix_noise=False): def reparameterize(self, mean, logvar, fix_noise=False):
if training == True: if self.training == True:
if not fix_noise: if not fix_noise:
eps = tf.random.normal(shape=mean.shape) eps = torch.normal(mean=0.0, std=1.0, size=mean.shape).to(mean.device)
else: else:
eps = tf.random.normal(shape=(1, mean.shape[1])) eps = torch.normal(mean=0.0, std=1.0, size=mean.shape).to(mean.device)
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 * .5) + mean
else: else:
out = tf.exp(logvar * .5) + mean out = torch.exp(logvar * .5) + mean
return out return out
def call(self, inputs, z_cond, training=None): 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_curv, uv_mask, uv_mask_high = inputs
x = tf.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], axis=-1) x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1)
mean, logvar = self.encoder(x, training=training) mean, logvar = self.encoder(x)
z = self.reparameterize(mean, logvar, training) z = self.reparameterize(mean, logvar)
z = torch.reshape(z, (mean.shape[0], -1, 8, 4))
z = tf.concat([z, z_cond], axis=-1) z = torch.concat([z, z_cond], dim=1)
x = self.decoder(z, training=training) x = self.decoder(z)
if self.avg_garment is not None: x = x * uv_mask[:,None,:,:]
x = x + self.avg_garment[tf.newaxis,:,:,:]
x = x * uv_mask[:,:,:,tf.newaxis]
# if self.upscale_enhancer is not None:
# pred_low = self.enhance(x, uv_mask, training=training)
# x = tf.image.resize(pred_low, (512, 256), tf.image.ResizeMethod.LANCZOS5)
# x = x * uv_mask_high[:,:,:,tf.newaxis]
return x, mean, logvar
class PyramidLevelNew(tf.keras.Model):
def __init__(self, config):
super(PyramidLevelNew, self).__init__()
self.size = config['resolution']
self.encoder = VariationalEncoderNew(config['encoder_depths'], config['encoder_dims'], kernel_size=config['kernel_size'])
self.decoder = DecoderNew(config['decoder_depths'], config['decoder_dims'], config['kernel_size'])
self.upscale_enhancer = None
if config['upscale_enhancer'] != '':
k_size = config['upscale_enhancer_kernel_size'] if 'upscale_enhancer_kernel_size' in config.keys() else ((3 if config['resolution'] <= 64 else 5))
self.upscale_enhancer = UpscalerBasicConv(config['resolution'], kernel_size=k_size)
load_model(self.upscale_enhancer, config['upscale_enhancer'])
self.upscale_enhancer.trainable = not config['upscale_enhancer_freeze']
if config['avg_garment_path'] != '':
self.avg_garment = np.load(config['avg_garment_path'])
else:
self.avg_garment = None
self.reshape = tf.keras.layers.Reshape((8, 4, 64))
def enhance(self, low, mask, training=None):
x = self.upscale_enhancer([low, mask], training=training)
return x
def sample(self, z_cond, uv_mask, noise=None):
if noise is None:
eps = tf.random.normal(shape=(uv_mask.shape[0], self.latent_dim))
else:
eps = noise
z = tf.concat([eps, z_cond], axis=-1)
x = self.decoder(z)
if self.avg_garment is not None:
x = x + self.avg_garment[tf.newaxis,:,:,:]
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 call(self, inputs, z_cond, training=None):
uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs
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 = 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 * uv_mask[:,:,:,tf.newaxis]
# if self.upscale_enhancer is not None: # if self.upscale_enhancer is not None:
# pred_low = self.enhance(x, uv_mask, training=training) # pred_low = self.enhance(x, uv_mask, training=training)
models/pyramid_model.py
+246
View File
@@ -0,0 +1,246 @@
import os
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
from models.pyramid_level import PyramidLevel
# 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):
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['static_model'] != '':
load_model(self.static_enc, config['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['body_model'] != '':
load_model(self.body_enc, config['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'], is_label=True, nr_of_labels=7)
if config['curvature_model'] != '':
load_model(self.curv_enc, config['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] }) for i in range(len(config['pyramid']['levels']))]
# 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_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 forward(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], training=training)
pred = self.levels[0].enhance(pred, levels_input[0][-2]) # levels_input[i][-2]=uv_mask_res
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)):
input = levels_input[i]
# 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])
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:
# 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 = 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])
return out_levels
models/pyramid_model_optimized.py
-365
View File
@@ -1,365 +0,0 @@
import os
import time
import random
import tensorflow as tf
import numpy as np
# import plotly.graph_objects as go
# import plotly.express as ex
from custom_utils.custom_utils import load_model
from models.base import AEEncoder, AEEncoderNew
from models.pyramid_level import PyramidLevel, PyramidLevelNew
from models.upscaler import UpscalerBasic, UpscalerBasicConv, UpscalerBasicNew
class Pyramid(tf.keras.Model):
def __init__(self, config):
super(Pyramid, self).__init__()
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'])
if config['pyramid']['static_model'] != '':
load_model(self.static_enc, config['pyramid']['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'])
if config['pyramid']['body_model'] != '':
load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
if config['pyramid']['curvature_model'] != '':
load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
if config['pyramid']['freeze_encoders']:
self.static_enc.trainable = False
self.body_enc.trainable = False
self.curv_enc.trainable = False
self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(256, activation='relu'),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(config['pyramid']['latent_dim'], activation='tanh'),])
self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae': config['cond_ae']} }) 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, training):
x = self.upscale_enhancer([low, mask], training=training)
return x
def encode_conds(self, uv_template, uv_body_posed, uv_curv, training):
z_static = self.static_enc(uv_template, training)
z_body = self.body_enc(uv_body_posed, training)
z_curv = self.curv_enc(uv_curv, training)
z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
z_cond = self.cond_encoder(z_cond, training=training)
return z_cond
def call(self, inputs, training):
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, training)
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, training=training)
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], training=training) # levels_input[i][-2]=uv_mask_res
pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
out_levels.append([pred, mean, logvar])
pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
else:
pred = self.enhance(pred, levels_input[0][-2], training=training)
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # 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, training=training)
pred = pred + pred_level
if i != len(self.levels) - 1:
pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
out_levels.append([pred, mean, logvar])
pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
else:
if self.upscale_enhancer is not None:
pred = self.enhance(pred, levels_input[-1][-2], training=training)
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
out_levels.append([pred, mean, logvar])
return out_levels
# # 32
# pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training)
# pred_0 = self.enhance(pred_0, levels_input[0][-2], training=training)
# pred_0 = tf.image.resize(pred_0, (512, 256), tf.image.ResizeMethod.LANCZOS5)
# pred_0 = pred_0 * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
# return [ [pred_0, mean_0, logvar_0] ]
# # 32 64
# pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training)
# pred_0 = self.levels[0].enhance(pred_0, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res
# pred_0 = tf.image.resize(pred_0, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
# pred = pred_0 * levels_input[1][-2][:,:,:,tf.newaxis]
# pred_1, mean_1, logvar_1 = self.levels[1](levels_input[1], z_cond, training=training)
# pred_1 = pred + pred_1
# pred_1 = self.enhance(pred_1, levels_input[-1][-2], training=training)
# pred_1 = tf.image.resize(pred_1, (512, 256), tf.image.ResizeMethod.LANCZOS5)
# pred_1 = pred_1 * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
# return [ [pred_0, mean_0, logvar_0], [pred_1, mean_1, logvar_1] ]
# class Pyramid(tf.keras.Model):
# def __init__(self, config):
# super(Pyramid, self).__init__()
# 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'])
# if config['pyramid']['static_model'] != '':
# load_model(self.static_enc, config['pyramid']['static_model'] + '_enc')
# self.body_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
# if config['pyramid']['body_model'] != '':
# load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
# self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size'])
# if config['pyramid']['curvature_model'] != '':
# load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
# if config['pyramid']['freeze_encoders']:
# self.static_enc.trainable = False
# self.body_enc.trainable = False
# self.curv_enc.trainable = False
# self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'),
# tf.keras.layers.Dense(256, activation='relu'),
# tf.keras.layers.Dense(128, activation='relu'),
# tf.keras.layers.Dense(config['pyramid']['latent_dim']),])
# self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae': config['cond_ae']} }) for i in range(len(config['pyramid']['levels']))]
# self.upscale_enhancer = None
# if config['pyramid']['final_upscale_enhancer'] != '':
# self.upscale_enhancer = UpscalerBasicNew(low_res=config['pyramid']['resolutions'][-1])
# 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_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 = tf.concat([z_static, z_body, z_curv], axis=-1)
# z_cond = self.cond_encoder(z_cond)
# return z_cond
# def call(self, inputs, training):
# 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)
# out_levels = []
# pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training)
# pred_0 = self.levels[0].enhance(pred_0, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res
# # pred_0 = self.enhance(pred_0, levels_input[0][-2], training=training)
# ##################
# # if more than 1 level
# # x = tf.image.resize(pred_0, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5)
# # x = x * levels_input[1][-2][:,:,:,tf.newaxis]
# # if only 1 level
# pred_0 = tf.image.resize(pred_0, (512, 256), tf.image.ResizeMethod.LANCZOS5)
# ##################
# # pred_1, mean_1, logvar_1 = self.levels[1](levels_input[1], z_cond, training=training)
# # pred_1 = pred_0 + pred_1
# # pred_1 = self.levels[1].enhance(pred, levels_input[1][-2], training=training)
# # for i in range(1, len(self.levels)):
# # pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training)
# # pred = pred + pred_level
# # if i != len(self.levels) - 1:
# # pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training)
# # out_levels.append([pred, mean, logvar])
# # pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5)
# # pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
# # else:
# # if self.upscale_enhancer is not None:
# # pred = self.enhance(pred, levels_input[-1][-2], training=training)
# # pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5)
# # out_levels.append([pred, mean, logvar])
# # pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
# out_levels = [
# [pred_0, mean_0, logvar_0]
# ]
# return out_levels
class PyramidNew(tf.keras.Model):
def __init__(self, config):
super(PyramidNew, self).__init__()
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['pyramid']['static_model'] != '':
load_model(self.static_enc, config['pyramid']['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['pyramid']['body_model'] != '':
load_model(self.body_enc, config['pyramid']['body_model'] + '_enc')
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['pyramid']['curvature_model'] != '':
load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc')
if config['pyramid']['freeze_encoders']:
self.static_enc.trainable = False
self.body_enc.trainable = False
self.curv_enc.trainable = False
self.levels = [PyramidLevelNew({ **config['pyramid']['levels'][i] }) for i in range(len(config['pyramid']['levels']))]
# 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_curv, training):
z_static = self.static_enc(uv_template, training)
z_body = self.body_enc(uv_body_posed, training)
z_curv = self.curv_enc(uv_curv, training)
z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
return z_cond
def call(self, inputs, training):
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, training)
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, training=training)
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], training=training) # levels_input[i][-2]=uv_mask_res
pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR)
out_levels.append([pred, mean, logvar])
pred = pred * levels_input[1][-2][:,:,:,tf.newaxis]
else:
# pred = self.enhance(pred, levels_input[0][-2], training=training)
pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
out_levels.append([pred, mean, logvar])
for i in range(1, len(self.levels)):
input = levels_input[i]
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, training=training)
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], training=training)
out_levels.append([pred, mean, logvar])
pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.BILINEAR)
pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis]
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], training=training)
pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR)
pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask
out_levels.append([pred, mean, logvar])
return out_levels
scripts/cvae_pyramid.py
+221 -244
View File
@@ -1,65 +1,67 @@
import os import os
import sys import sys
from configs.config_abl_pyr_32_skirt 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)
parser.add_argument('--debug', action='store_true')
args = vars(parser.parse_args())
config_module = importlib.import_module(args['config'])
config = config_module.config
if args['debug']:
from configs.pyr_32 import config
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
import tensorflow as tf if args['debug']:
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 time
import tqdm
import argparse import argparse
import wandb import wandb
import tqdm
import random import random
import numpy as np import numpy as np
import scipy as sp
from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, get_summary_str, plot_3d_collision, group_inputs_for_levels
import plotly.graph_objects as go import plotly.graph_objects as go
import plotly.express as ex import plotly.express as ex
from plotly.subplots import make_subplots
from PIL import Image from PIL import Image
if config['is_skirt']: if config['is_skirt']:
from losses import edge_loss_skirt as edge_loss from losses.losses import edge_loss_skirt as edge_loss
else: else:
from losses import edge_loss from losses.losses import edge_loss
from losses import uv_mask_loss, bend_loss, kl_loss, collision_ratio, normal_loss import torch
# from losses import collision_penalty as collision_penalty import torch.nn as nn
from losses import collision_loss as collision_penalty import torch.optim as optim
from custom_utils.custom_utils import batch_to_dict, load_model import torch.nn.functional as F
from dataset import DatasetFactory, StaticDataset from data.dataset import Dataset
from custom_utils.smpl import SMPL from utils.checkpoints import CheckpointSaver, load_model
from models.pyramid_model_optimized import Pyramid from utils.utils import InfiniteDataLoader as DataLoader
from postprocessing import fix_collision from utils.postprocess import fix_collision
from losses.losses import collision_loss, normal_loss, kl_loss
from pytorch_msssim import MS_SSIM
from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels
from smpl.smpl_torch import SMPL
from plotly.subplots import make_subplots
from models.pyramid_model import Pyramid
def init_wandb(): 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='/data-local/127/temp', tags=config['tags'])
artifact = wandb.Artifact('code', type='code') artifact = wandb.Artifact('code', type='code')
artifact.add_file('cvae_pyramid.py') artifact.add_file('scripts/cvae_pyramid.py')
artifact.add_file('models/cvae_model.py') artifact.add_file('losses/losses.py')
artifact.add_file('models/pyramid_model_optimized.py')
artifact.add_file('models/pyramid_level.py')
artifact.add_file('models/upscaler.py')
artifact.add_file('losses.py')
artifact.add_file('models/base.py') artifact.add_file('models/base.py')
artifact.add_file('models/cond_encoder.py') artifact.add_file('models/cond_encoder.py')
artifact.add_file('dataset.py') artifact.add_file('models/convnext.py')
artifact.add_file('convnext/models/convnext_tf.py') artifact.add_file('models/pyramid_model.py')
config_file_names = [key for key in sys.modules.keys() if key.startswith('configs')] artifact.add_file('models/pyramid_level.py')
artifact.add_file('data/dataset.py')
config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')]
for config_file_name in config_file_names: for config_file_name in config_file_names:
file_name = '/'.join(config_file_name.split('.')) + '.py' file_name = '/'.join(config_file_name.split('.')) + '.py'
if os.path.exists(file_name): if os.path.exists(file_name):
@@ -210,12 +212,12 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col
return fig return fig
# @tf.function
def train_step(batch): def train_step(batch):
model.train()
# with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp):
levels_input, conds = group_inputs_for_levels(batch, config) levels_input, conds = group_inputs_for_levels(batch, config)
with tf.GradientTape() as tape: out_levels = model([levels_input, conds])
out_levels = model([levels_input, conds], training=True)
if config['use_skinning']: if config['use_skinning']:
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
@@ -236,24 +238,24 @@ def train_step(batch):
if config['use_skinning']: if config['use_skinning']:
shape = batch['pose_shape'][:, 72:] 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(dtype=torch.int64)
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])])
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
else: else:
mesh_pred_posed = mesh_pred mesh_pred_posed = mesh_pred
# is the output already masked? # 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 = tf.reduce_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_penalty(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 = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2])) l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2]))
# 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))) 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))
# ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) 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 = 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'])
kl = kl_loss(mean, logvar) kl = kl_loss(mean, logvar)
if config['use_extra_losses']: if config['use_extra_losses']:
@@ -263,33 +265,44 @@ def train_step(batch):
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: if config['use_norm_loss'] and step > 2000:
# reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] 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
mean = tf.reduce_mean(mean) # scaler.scale(loss).backward()
logvar = tf.reduce_mean(logvar) # scaler.step(optimizer)
# scaler.update()
# optimizer.zero_grad()
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']) optimizer.zero_grad()
loss.backward()
optimizer.step()
model.eval()
with torch.inference_mode():
mean = torch.mean(mean)
logvar = torch.mean(logvar)
ms_ssim = torch.mean(_MSSSIM(pred + 1, 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, 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, } } #
loss = reconstr_loss_total + balancing_coeff * kl_total
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
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 }
@tf.function
def valid_step(batch): def valid_step(batch):
model.eval()
with torch.inference_mode():
levels_input, conds = group_inputs_for_levels(batch, config) levels_input, conds = group_inputs_for_levels(batch, config)
out_levels = model([levels_input, conds], training=False)
out_levels = model([levels_input, conds])
if config['use_skinning']: if config['use_skinning']:
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
@@ -310,23 +323,24 @@ def valid_step(batch):
if config['use_skinning']: if config['use_skinning']:
shape = batch['pose_shape'][:, 72:] 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(dtype=torch.int64)
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])])
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
else: else:
mesh_pred_posed = mesh_pred mesh_pred_posed = mesh_pred
# is the output already masked?
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) # is the output already masked?
c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) # 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)))
c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
# 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))) e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
# ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
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)) 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']) 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']:
@@ -336,34 +350,35 @@ def valid_step(batch):
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: if config['use_norm_loss'] and step > 2000:
# reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] 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
mean = tf.reduce_mean(mean) mean = torch.mean(mean)
logvar = tf.reduce_mean(logvar) logvar = torch.mean(logvar)
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']) 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, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric,
'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl, 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl,
'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss, 'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss,
'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim, 'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/ms_ssim' + res_modifier: ms_ssim, } } #
loss = reconstr_loss_total + balancing_coeff * kl_total
return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output } return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output }
@tf.function
def test_step(batch): def test_step(batch):
levels_input, conds = group_inputs_for_levels(batch, config) levels_input, conds = group_inputs_for_levels(batch, config)
out_levels = model([levels_input, conds], training=False) out_levels = model([levels_input, conds], training=False)
shape = batch['pose_shape'][:, 72:] shape = batch['pose_shape'][:, 72:]
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) 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])]) shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, dim=0) for i in range(shape.shape[0])])
mesh_orig = batch['mesh_unposed'] mesh_orig = batch['mesh_unposed']
output = dict() output = dict()
@@ -377,18 +392,18 @@ def test_step(batch):
pred, mean, logvar = out_levels[i] pred, mean, logvar = out_levels[i]
mesh_pred = uv2mesh(pred) mesh_pred = uv2mesh(pred)
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
# is the output already masked? # is the output already masked?
e_loss = tf.reduce_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_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - pred) ** 2), axis=-1), axis=[1, 2])) l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_unposed'] - pred) ** 2), dim=-1), dim=[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)) l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1), dim=-1))
# 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))) # 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 = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3))
kl = kl_loss(mean, logvar) kl = kl_loss(mean, logvar)
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)
@@ -397,11 +412,11 @@ def test_step(batch):
# reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (e_loss + c_loss) * config['reg_loss_coeff']) # reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (e_loss + c_loss) * config['reg_loss_coeff'])
kl_total += kl kl_total += kl
mean = tf.reduce_mean(mean) mean = torch.mean(mean)
logvar = tf.reduce_mean(logvar) logvar = torch.mean(logvar)
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']) metric = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1))) / torch.sum(batch['mesh_mask'])
euclid_error_per_garment = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1)), axis=1) / tf.reduce_sum(batch['mesh_mask'], axis=1) euclid_error_per_garment = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1)), dim=1) / torch.sum(batch['mesh_mask'], dim=1)
output = { **output, **{ 'test/edge_loss' + res_modifier: e_loss, 'test/collision_loss' + res_modifier: c_loss,'test/euclid_error' + res_modifier: metric, output = { **output, **{ 'test/edge_loss' + res_modifier: e_loss, 'test/collision_loss' + res_modifier: c_loss,'test/euclid_error' + res_modifier: metric,
'test/mean' + res_modifier: mean, 'test/logvar' + res_modifier: logvar, 'test/kl_loss' + res_modifier: kl, 'test/mean' + res_modifier: mean, 'test/logvar' + res_modifier: logvar, 'test/kl_loss' + res_modifier: kl,
@@ -416,35 +431,38 @@ def test_step(batch):
def plot_everything(batch: dict, type: str): def plot_everything(batch: dict, type: str):
if config['use_skinning']: if config['use_skinning']:
mesh_orig, uv_orig = batch['mesh_unposed'].numpy(), batch['uv_unposed'].numpy() mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed']
else: else:
mesh_orig, uv_orig = batch['mesh_posed'].numpy(), batch['uv_posed'].numpy() mesh_orig, uv_orig = batch['mesh_posed'].cpu().numpy(), batch['uv_posed']
model.eval()
with torch.inference_mode():
levels_input = group_inputs_for_levels(batch, config) levels_input = group_inputs_for_levels(batch, config)
output_levels = model(levels_input, training=False) output_levels = model(levels_input)
mesh_pred_levels = [uv2mesh(output_levels[i][0]).numpy() for i in range(len(output_levels))] mesh_pred_levels = [uv2mesh(output_levels[i][0]).detach().cpu().numpy() for i in range(len(output_levels))]
mesh_orig_posed = batch['mesh_posed'].numpy() mesh_orig_posed = batch['mesh_posed'].cpu().numpy()
body = batch['mesh_body_posed'].numpy() body = batch['mesh_body_posed'].cpu().numpy()
orig_img = (uv_orig + 1) / 2 orig_img = (torch.permute(uv_orig, [0,2,3,1]) + 1) / 2
uv_static_img = (batch['uv_static'].numpy() + 1) / 2 uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2
uv_body_posed_img = (batch['uv_body_posed'].numpy() + 1) / 2 uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2
uv_curvature = (np.tile(batch['uv_curvature'].numpy().argmax(-1)[:,:,:,np.newaxis], [1,1,1,3]) / 6) uv_curvature = (torch.tile(torch.argmax(torch.permute(batch['uv_curvature'], [0,2,3,1]), dim=-1)[:,:,:,None], [1,1,1,3]) / 6)
pred_img = np.concatenate([tf.image.resize(output_levels[i][0], (512, 256), tf.image.ResizeMethod.LANCZOS5) for i in range(len(output_levels))], axis=2) pred_img = torch.concatenate([torch.permute(F.interpolate(output_levels[i][0], size=(512, 256), mode='bilinear'), [0,2,3,1]) for i in range(len(output_levels))], dim=3)
pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) # pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis])
img = tf.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2) pred_img = (pred_img - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) / (pred_img.flatten().reshape(pred_img.shape[0], -1).max(1)[0][:,None,None,None] - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None])
imgs = [wandb.Image(img[i]) for i in range(4)]
F = np.load("custom_utils/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy") img = torch.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2)
mask = batch['mesh_mask'].numpy().astype(bool) imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)]
_, faces = maskFacesBatch(np.ones_like(mesh_orig), F, mask)
_F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
mask = batch['mesh_mask'].cpu().numpy().astype(bool)
_, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask)
if config['use_skinning']: if config['use_skinning']:
shape = batch['pose_shape'][:, 72:] 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])]).numpy() shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]).cpu().numpy()
gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])] gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])]
@@ -458,8 +476,7 @@ def plot_everything(batch: dict, type: str):
mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32) mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32)
for i in range(mask.shape[0]): for i in range(mask.shape[0]):
mesh_unposed_shaped_full[i, mask[i], :] = mesh_unposed_shaped[i] mesh_unposed_shaped_full[i, mask[i], :] = mesh_unposed_shaped[i]
mesh_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(mesh_unposed_shaped_full, device=config['device']))[0].cpu().numpy()
mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_unposed_shaped_full).numpy()
else: else:
mesh_posed = mesh_pred_levels[-1] mesh_posed = mesh_pred_levels[-1]
gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])] gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])]
@@ -467,7 +484,7 @@ def plot_everything(batch: dict, type: str):
gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(mask.shape[0])] gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(mask.shape[0])]
mesh_posed_fixed = fix_collision(mesh_posed, body, mask).numpy() mesh_posed_fixed = fix_collision(torch.Tensor(mesh_posed).to('cuda'), torch.Tensor(body).to('cuda'), torch.Tensor(mask).to('cuda')).cpu().numpy()
mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])] mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])]
@@ -477,7 +494,7 @@ def plot_everything(batch: dict, type: str):
collision_color = [np.ones_like(mesh_posed[i], dtype=np.int32)*230 for i in range(len(mesh_posed))] collision_color = [np.ones_like(mesh_posed[i], dtype=np.int32)*230 for i in range(len(mesh_posed))]
else: else:
collision = [np.concatenate((body[i], mesh_posed[i]), axis=0) for i in range(len(mesh_posed))] collision = [np.concatenate((body[i], mesh_posed[i]), axis=0) for i in range(len(mesh_posed))]
collision_faces = [np.concatenate((F, faces[i] + config['smpl_res']), axis=0) for i in range(len(mesh_posed))] collision_faces = [np.concatenate((_F, faces[i] + config['smpl_res']), axis=0) for i in range(len(mesh_posed))]
collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(mesh_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(mesh_posed))] collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(mesh_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(mesh_posed))]
figs = { type + "/garment_" + str(i): plot_3d(gt[i], mesh_unposed_shaped_levels[i], faces[i], gt_posed[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) } figs = { type + "/garment_" + str(i): plot_3d(gt[i], mesh_unposed_shaped_levels[i], faces[i], gt_posed[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
@@ -487,7 +504,7 @@ def plot_everything(batch: dict, type: str):
else: else:
garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(body.shape[0])] garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(body.shape[0])]
collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(mesh_posed))] collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(mesh_posed))]
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])]
collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(gt_posed))] collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(gt_posed))]
figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i]) for i in range(4) } figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i]) for i in range(4) }
@@ -505,7 +522,7 @@ def sample(folder):
pred = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples) pred = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:] pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:]
pose, shape = tf.tile(pose[tf.newaxis,:], [nr_of_samples,1]), tf.tile(shape[tf.newaxis,:], [nr_of_samples,1]) pose, shape = tf.tile(pose[None,:], [nr_of_samples,1]), tf.tile(shape[None,:], [nr_of_samples,1])
mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2])) mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2]))
mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy() mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy()
@@ -706,13 +723,13 @@ def generate_results():
shape = batch['pose_shape'][:, 72:] shape = batch['pose_shape'][:, 72:]
gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) 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])]) shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])])
i = -1 i = -1
pred = out_levels[i][0] pred = out_levels[i][0]
mesh_pred = uv2mesh(pred) mesh_pred = uv2mesh(pred)
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
for i in range(batch['id'].shape[0]): for i in range(batch['id'].shape[0]):
@@ -725,157 +742,117 @@ def generate_results():
pass pass
@tf.function
def speed_step(levels_input, conds): def speed_step(levels_input, conds):
return model.sample([levels_input, conds], training=False) return model.sample([levels_input, conds], training=False)
def train():
global g_balancing_coeff
global step
valid_iterator = iter(valid_dataloader)
for batch in train_dataloader:
train_loss = train_step(batch)
train_accumulator.update(train_loss)
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)) } }
if not args['debug']:
wandb.log(to_log, step=step)
train_accumulator.reset()
valid_accumulator.reset()
print(step)
if train_loss['train/euclid_error'] < config['balancing_activation_limit']:
g_balancing_coeff += 1 / 10000
if step % 10000 == 0:
ckpt_saver(model, step, optimizer, None)
step += 1
if __name__ == '__main__': if __name__ == '__main__':
# init_wandb() if not args['debug']:
parser = argparse.ArgumentParser(description='') init_wandb()
parser.add_argument('--name', type=str, default='lhunor')
args = vars(parser.parse_args())
# config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')] use_amp = True
# assert len(config_file_names) == 1 smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
# config_file_name = config_file_names[0]
# # assert config_file_name.split('.')[1].endswith(args.name)
# assert config_file_name.split('.')[1].endswith(config['name'])
smpl = SMPL(orig_smpl=config['is_cape'])
skirt_modifier = '_skirt' if config['is_skirt'] else '' skirt_modifier = '_skirt' if config['is_skirt'] else ''
dataset_resolutions = config['pyramid']['resolutions'].copy() dataset_resolutions = config['pyramid']['resolutions'].copy()
if 512 not in dataset_resolutions: if 512 not in dataset_resolutions:
dataset_resolutions.append(512) dataset_resolutions.append(512)
factory = DatasetFactory() dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
dataset_train = factory.get_dataset(folder=config['train_dir'], dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape'])
batch_size=config['batch_size'], train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, )
# batch_size=1, valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=True)
signature=config['signature_dynamic'], train_accumulator = Accumulator()
resolutions=dataset_resolutions, valid_accumulator = Accumulator()
in_memory=config['dataset_in_memory'],
is_cape=config['is_cape'],
frames_file=config['frames_file'] if 'frames_file' in config.keys() else None)
static_dataset_train = StaticDataset(folder=config['train_dir'],
signature=config['signature_static'],
resolutions=dataset_resolutions,
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=dataset_resolutions,
in_memory=config['dataset_in_memory'],
is_cape=config['is_cape'],
frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None)
static_dataset_valid = StaticDataset(folder=config['valid_dir'],
signature=config['signature_static'],
resolutions=dataset_resolutions,
in_memory=True,
is_cape=config['is_cape'])
model: Pyramid = Pyramid(config) model: Pyramid = Pyramid(config)
optimizer = tf.optimizers.Adam(learning_rate=config['lr']) optimizer = optim.Adam(model.parameters(), lr=config['lr'])
balancing_coeff = config['starting_balancing_coeff'] _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
ckpt_saver = CheckpointSaver('checkpoints/iccv/torch/' + config['name'], top_n=5)
scaler = torch.cuda.amp.GradScaler(enabled=use_amp)
g_balancing_coeff = config['starting_balancing_coeff']
reg_coeff = 1 reg_coeff = 1
valid_iterator = iter(dataset_valid)
gamma = 1
balancing_activated_step = 0
# sample('checkpoints/cvae_13')
# test()
# generate_results()
ckpt = tf.train.Checkpoint(model=model)
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
# load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000')
step = 0
if config['pretrained_model'] != '': if config['pretrained_model'] != '':
# assert len(config['pyramid']['resolutions']) == 1 # assert len(config['pyramid']['resolutions']) == 1
load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration']) step = load_model(model, config['pretrained_model'], optimizer=optimizer, scaler=scaler, iteration=config['pretrained_model_iteration'])
if not args['debug']:
model = torch.compile(model)
wandb.watch(model, log='all', log_freq=1000, log_graph=True)
if len(config['pyramid']['resolutions']) == 1: if len(config['pyramid']['resolutions']) == 1:
model.static_enc.trainable = False for param in model.static_enc.parameters(): param.requires_grad = False
model.body_enc.trainable = False for param in model.body_enc.parameters(): param.requires_grad = False
model.curv_enc.trainable = False for param in model.curv_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'] if 'pretrained_pyramid_iteration' in config.keys() else ''))
model.static_enc.trainable = False for param in model.static_enc.parameters(): param.requires_grad = False
model.body_enc.trainable = False for param in model.body_enc.parameters(): param.requires_grad = False
model.curv_enc.trainable = False for param in model.curv_enc.parameters(): param.requires_grad = False
model.cond_encoder.trainable = 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
# for i in range(len(model.levels)-1):
# load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer'])
# model.levels[i].upscale_enhancer.trainable = False
# if config['pyramid']['resolutions'][-1] != 512:
# load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
# model.upscale_enhancer.trainable = False
for i in range(len(model.levels)-1): for i in range(len(model.levels)-1):
load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer']) for param in model.levels[i].parameters(): param.requires_grad = False
model.levels[i].upscale_enhancer.trainable = False
if config['pyramid']['resolutions'][-1] != 512:
load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer'])
model.upscale_enhancer.trainable = False
for i in range(len(model.levels)-1):
model.levels[i].trainable = False
# load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid']) # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid'])
# load_model(model.levels[0], config['pyramid']['pretrained_pyramid']) # load_model(model.levels[0], config['pyramid']['pretrained_pyramid'])
# load_model(model.levels[-1], 'checkpoints/cvae_19') # load_model(model.levels[-1], 'checkpoints/cvae_19')
if not args['debug']:
model = torch.compile(model)
wandb.watch(model, log='all', log_freq=1000, log_graph=True)
step = 0 train()
times = []
for batch in dataset_train:
batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
# levels_input, conds = group_inputs_for_levels(batch, config)
# start = time.perf_counter()
# out = speed_step(levels_input, conds)
# t = time.perf_counter() - start
# print(t)
# times.append(t)
# if step > 200:
# break
train_loss = train_step(batch)
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)
to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
train_figs = plot_everything(batch, 'train')
valid_figs = plot_everything(data_valid, 'valid')
to_log = { **to_log, **train_figs, **valid_figs }
if step % 5000 == 0:
manager.save(checkpoint_number=step)
if step == 0:
to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
if train_loss['train/euclid_error'] < 0.004:
if balancing_activated_step == 0:
balancing_activated_step = step
balancing_coeff = balancing_coeff + 1 / 20000
to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
wandb.log(to_log, step = step)
print(step)
step += 1
# print('mean:')
# print(np.mean(times[1:]))
utils/postprocess.py
+1 -2
View File
@@ -25,8 +25,7 @@ to_keep = sio.loadmat('smpl/keep_remove.mat')['keep'].reshape(-1)
F_fix_coll = torch.tensor(np.tile(np.load("smpl/smpl_faces.npy")[to_keep,:][None,:,:], [4,1,1]), device='cuda') F_fix_coll = torch.tensor(np.tile(np.load("smpl/smpl_faces.npy")[to_keep,:][None,:,:], [4,1,1]), device='cuda')
def fix_collision(V: torch.Tensor, B: torch.Tensor, mask: torch.Tensor, thr=.004):
def fix_collision(V, B, mask, thr=.004):
mesh = Meshes(B, F_fix_coll) mesh = Meshes(B, F_fix_coll)
B_vn = torch.stack(mesh.verts_normals_list()) B_vn = torch.stack(mesh.verts_normals_list())