cvae norm training
This commit is contained in:
@@ -0,0 +1,172 @@
|
|||||||
|
from utils.convnext_utils import CNBlockConfig
|
||||||
|
|
||||||
|
config = dict()
|
||||||
|
|
||||||
|
config['gpu'] = '0'
|
||||||
|
config['name'] = 'cvae_norm_1'
|
||||||
|
config['notes'] = ''
|
||||||
|
config['tags'] = ['iccv', 'cvae_norm', 'torch']
|
||||||
|
config['script'] = 'scripts/cvae_norm.py'
|
||||||
|
|
||||||
|
config['pretrained_model'] = ''
|
||||||
|
|
||||||
|
|
||||||
|
config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision
|
||||||
|
|
||||||
|
config['batch_size'] = 4
|
||||||
|
config['resolution'] = 512
|
||||||
|
config['is_skirt'] = False
|
||||||
|
config['dataset_in_memory'] = False
|
||||||
|
config['is_cape'] = False
|
||||||
|
config['device'] = 'cuda'
|
||||||
|
|
||||||
|
config['train_dir'] = '/data-local/127/train'
|
||||||
|
config['valid_dir'] = '/data-local/127/valid'
|
||||||
|
config['test_dir'] = '/data-net/dataset/test_ready'
|
||||||
|
config['train_frames'] = None
|
||||||
|
config['valid_frames'] = None
|
||||||
|
|
||||||
|
config['static_model'] = 'checkpoints/iccv/static_torch_orig_2'
|
||||||
|
config['body_model'] = 'checkpoints/iccv/body_torch_1'
|
||||||
|
|
||||||
|
config['smpl_res'] = 14475
|
||||||
|
if config['is_cape']:
|
||||||
|
config['smpl_res'] = 3638
|
||||||
|
|
||||||
|
config['latent_dim'] = 128
|
||||||
|
|
||||||
|
###############
|
||||||
|
config['lr'] = 0.0001# 0.0001
|
||||||
|
###############
|
||||||
|
config['starting_balancing_coeff'] = 0.0001
|
||||||
|
|
||||||
|
config['signature']: set = { 'id',
|
||||||
|
'frame_nr',
|
||||||
|
'pose_shape',
|
||||||
|
'uv_body_posed',
|
||||||
|
'uv_normals',
|
||||||
|
'uv_static',
|
||||||
|
'mesh_mask',
|
||||||
|
'uv_mask',
|
||||||
|
'mesh_normals',
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
config['upscale_enhancer'] = ''
|
||||||
|
config['freeze_encoders'] = True
|
||||||
|
config['use_one_hot'] = False
|
||||||
|
config['bottleneck_scale'] = 2
|
||||||
|
|
||||||
|
config['cvae'] = dict()
|
||||||
|
config['cvae']['device'] = config['device']
|
||||||
|
config['cvae']['is_label'] = False
|
||||||
|
config['cvae']['input_features'] = 3+3+3
|
||||||
|
config['cvae']['kernel_size'] = 7
|
||||||
|
config['cvae']['bottleneck_size'] = 64 * config['bottleneck_scale']
|
||||||
|
config['cvae']['latent_dim'] = config['cvae']['bottleneck_size']
|
||||||
|
|
||||||
|
block_setting = [
|
||||||
|
CNBlockConfig(32, 64, 3),
|
||||||
|
CNBlockConfig(64, 128, 3),
|
||||||
|
CNBlockConfig(128, 256, 3),
|
||||||
|
CNBlockConfig(256, config['cvae']['bottleneck_size'], 9),
|
||||||
|
CNBlockConfig(config['cvae']['bottleneck_size'], None, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
block_setting_reverse = [
|
||||||
|
CNBlockConfig(176, 256, 3),
|
||||||
|
CNBlockConfig(256, 128, 9),
|
||||||
|
CNBlockConfig(128, 64, 9),
|
||||||
|
CNBlockConfig(64, 32, 3),
|
||||||
|
CNBlockConfig(32, 3, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
config['cvae']['encoder_block_settings'] = block_setting
|
||||||
|
config['cvae']['decoder_block_settings'] = block_setting_reverse
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
####################### cond_ae_curv ############################
|
||||||
|
config['cond_ae_curv'] = dict()
|
||||||
|
config['cond_ae_curv']['device'] = config['device']
|
||||||
|
config['cond_ae_curv']['is_label'] = True
|
||||||
|
config['cond_ae_curv']['latent_dim'] = config['latent_dim']
|
||||||
|
config['cond_ae_curv']['kernel_size'] = 7
|
||||||
|
config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale']
|
||||||
|
|
||||||
|
block_setting = [
|
||||||
|
CNBlockConfig(16, 32, 3),
|
||||||
|
CNBlockConfig(32, 64, 3),
|
||||||
|
CNBlockConfig(64, 128, 9),
|
||||||
|
CNBlockConfig(128, config['cond_ae_curv']['bottleneck_size'], 9),
|
||||||
|
CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], None, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
block_setting_reverse = [
|
||||||
|
CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], 128, 3),
|
||||||
|
CNBlockConfig(128, 64, 9),
|
||||||
|
CNBlockConfig(64, 32, 9),
|
||||||
|
CNBlockConfig(32, 16, 3),
|
||||||
|
CNBlockConfig(16, 3, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
config['cond_ae_curv']['encoder_block_settings'] = block_setting
|
||||||
|
config['cond_ae_curv']['decoder_block_settings'] = block_setting_reverse
|
||||||
|
config['cond_ae_curv']['activation'] = 'tanh'
|
||||||
|
|
||||||
|
####################### cond_ae_body ############################
|
||||||
|
config['cond_ae_body'] = dict()
|
||||||
|
config['cond_ae_body']['device'] = config['device']
|
||||||
|
config['cond_ae_body']['is_label'] = False
|
||||||
|
config['cond_ae_body']['latent_dim'] = config['latent_dim']
|
||||||
|
config['cond_ae_body']['kernel_size'] = 7
|
||||||
|
config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale']
|
||||||
|
|
||||||
|
block_setting = [
|
||||||
|
CNBlockConfig(16, 32, 3),
|
||||||
|
CNBlockConfig(32, 64, 3),
|
||||||
|
CNBlockConfig(64, 128, 9),
|
||||||
|
CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9),
|
||||||
|
CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
block_setting_reverse = [
|
||||||
|
CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3),
|
||||||
|
CNBlockConfig(128, 64, 9),
|
||||||
|
CNBlockConfig(64, 32, 9),
|
||||||
|
CNBlockConfig(32, 16, 3),
|
||||||
|
CNBlockConfig(16, 3, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
config['cond_ae_body']['encoder_block_settings'] = block_setting
|
||||||
|
config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse
|
||||||
|
config['cond_ae_body']['activation'] = 'tanh'
|
||||||
|
|
||||||
|
####################### cond_ae_static ############################
|
||||||
|
config['cond_ae_static'] = dict()
|
||||||
|
config['cond_ae_static']['device'] = config['device']
|
||||||
|
config['cond_ae_static']['is_label'] = False
|
||||||
|
config['cond_ae_static']['latent_dim'] = config['latent_dim']
|
||||||
|
config['cond_ae_static']['kernel_size'] = 7
|
||||||
|
config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale']
|
||||||
|
|
||||||
|
block_setting = [
|
||||||
|
CNBlockConfig(8, 16, 3),
|
||||||
|
CNBlockConfig(16, 32, 3),
|
||||||
|
CNBlockConfig(32, 64, 3),
|
||||||
|
CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9),
|
||||||
|
CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
block_setting_reverse = [
|
||||||
|
CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3),
|
||||||
|
CNBlockConfig(64, 32, 9),
|
||||||
|
CNBlockConfig(32, 16, 3),
|
||||||
|
CNBlockConfig(16, 8, 3),
|
||||||
|
CNBlockConfig(8, 3, 3),
|
||||||
|
]
|
||||||
|
|
||||||
|
config['cond_ae_static']['encoder_block_settings'] = block_setting
|
||||||
|
config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse
|
||||||
|
config['cond_ae_static']['activation'] = 'tanh'
|
||||||
@@ -0,0 +1,97 @@
|
|||||||
|
import os
|
||||||
|
import time
|
||||||
|
import random
|
||||||
|
import torch
|
||||||
|
from torch import nn
|
||||||
|
import numpy as np
|
||||||
|
import scipy as sp
|
||||||
|
# import plotly.graph_objects as go
|
||||||
|
# import plotly.express as ex
|
||||||
|
|
||||||
|
from utils.checkpoints import load_model
|
||||||
|
from models.base import AEEncoder, VariationalEncoder, Decoder
|
||||||
|
|
||||||
|
|
||||||
|
class CVAENorm(nn.Module):
|
||||||
|
|
||||||
|
def __init__(self, config):
|
||||||
|
super(CVAENorm, self).__init__()
|
||||||
|
self.size = config['resolution']
|
||||||
|
|
||||||
|
self.static_enc : AEEncoder = AEEncoder(config['cond_ae_static']['encoder_block_settings'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation'], device=config['device'])
|
||||||
|
if config['static_model'] != '':
|
||||||
|
load_model(self.static_enc, config['static_model'] + '_enc')
|
||||||
|
|
||||||
|
self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['encoder_block_settings'], config['cond_ae_body']['kernel_size'], config['cond_ae_body']['activation'], device=config['device'])
|
||||||
|
if config['body_model'] != '':
|
||||||
|
load_model(self.body_enc, config['body_model'] + '_enc')
|
||||||
|
|
||||||
|
if config['freeze_encoders']:
|
||||||
|
for param in self.static_enc.parameters(): param.requires_grad = False
|
||||||
|
for param in self.body_enc.parameters(): param.requires_grad = False
|
||||||
|
|
||||||
|
self.encoder = VariationalEncoder(config['cvae']['encoder_block_settings'], config['cvae']['kernel_size'], config['cvae']['input_features'], device=config['device'])
|
||||||
|
self.decoder : Decoder = Decoder(config['cvae']['decoder_block_settings'], kernel_size=config['cvae']['kernel_size'], device=config['device'])
|
||||||
|
|
||||||
|
self.latent_shape = (config['cvae']['latent_dim'], 8, 4)
|
||||||
|
|
||||||
|
|
||||||
|
def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, noise=None, add_noise=False):
|
||||||
|
if noise is None:
|
||||||
|
eps = tf.random.normal(shape=(uv_template.shape[0], 8, 4, self.latent_dim))
|
||||||
|
else:
|
||||||
|
eps = noise
|
||||||
|
|
||||||
|
z_cond = self.encode_conds(uv_template, uv_body_posed, uv_curv, training=False)
|
||||||
|
if add_noise:
|
||||||
|
z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount)
|
||||||
|
|
||||||
|
z = tf.concat([eps, z_cond], axis=-1)
|
||||||
|
|
||||||
|
x = self.decoder(z, training=False)
|
||||||
|
|
||||||
|
if self.avg_garment is not None:
|
||||||
|
x = x + self.avg_garment[tf.newaxis,:,:,:]
|
||||||
|
|
||||||
|
if self.use_offsets_over_body:
|
||||||
|
x = x + uv_body_posed
|
||||||
|
|
||||||
|
x = x * uv_mask[:,:,:,tf.newaxis]
|
||||||
|
|
||||||
|
return x
|
||||||
|
|
||||||
|
|
||||||
|
def reparameterize(self, mean: torch.Tensor, logvar: torch.Tensor, training: bool = True, fix_noise: bool = False):
|
||||||
|
if training == True:
|
||||||
|
if not fix_noise:
|
||||||
|
eps = torch.randn(size=mean.shape).to(mean.device)
|
||||||
|
else:
|
||||||
|
eps = torch.randn(size=(1, mean.shape[1]))
|
||||||
|
eps = torch.tile(eps, [mean.shape[0],1])
|
||||||
|
out = eps * torch.exp(logvar * 0.5) + mean
|
||||||
|
else:
|
||||||
|
out = torch.exp(logvar * 0.5) + mean
|
||||||
|
return out
|
||||||
|
|
||||||
|
|
||||||
|
def encode_conds(self, uv_template, uv_body_posed):
|
||||||
|
z_body = self.body_enc(uv_body_posed)
|
||||||
|
z_static = self.static_enc(uv_template)
|
||||||
|
z_cond = torch.concat([z_static, z_body], dim=1)
|
||||||
|
return z_cond
|
||||||
|
|
||||||
|
|
||||||
|
def forward(self, inputs):
|
||||||
|
uv_unposed, uv_template, uv_body_posed, uv_mask = inputs
|
||||||
|
x = torch.concat([uv_unposed, uv_template, uv_body_posed], dim=1)
|
||||||
|
|
||||||
|
mean, logvar = self.encoder(x)
|
||||||
|
z: torch.Tensor = self.reparameterize(mean, logvar)
|
||||||
|
z = z.view((mean.shape[0], *self.latent_shape))
|
||||||
|
z_cond = self.encode_conds(uv_template, uv_body_posed)
|
||||||
|
|
||||||
|
z = torch.concat([z, z_cond], dim=1)
|
||||||
|
x = self.decoder(z)
|
||||||
|
x = x * uv_mask[:,None,:,:]
|
||||||
|
|
||||||
|
return x, mean, logvar
|
||||||
@@ -1,6 +1,6 @@
|
|||||||
import os
|
import os
|
||||||
import sys
|
import sys
|
||||||
from configs.abl_norm import config
|
from configs.cvae_norm_1 import config
|
||||||
import argparse
|
import argparse
|
||||||
|
|
||||||
# parser = argparse.ArgumentParser(description='')
|
# parser = argparse.ArgumentParser(description='')
|
||||||
|
|||||||
+1
-1
@@ -51,7 +51,7 @@ from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary
|
|||||||
|
|
||||||
|
|
||||||
def init_wandb():
|
def init_wandb():
|
||||||
run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/tmp', 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('scripts/cvae.py')
|
artifact.add_file('scripts/cvae.py')
|
||||||
artifact.add_file('losses/losses.py')
|
artifact.add_file('losses/losses.py')
|
||||||
|
|||||||
@@ -0,0 +1,400 @@
|
|||||||
|
import os
|
||||||
|
import sys
|
||||||
|
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
|
||||||
|
|
||||||
|
import importlib
|
||||||
|
import argparse
|
||||||
|
parser = argparse.ArgumentParser(description='')
|
||||||
|
parser.add_argument('--name', type=str)
|
||||||
|
parser.add_argument('--config', type=str)
|
||||||
|
parser.add_argument('--debug', action='store_true')
|
||||||
|
args = vars(parser.parse_args())
|
||||||
|
|
||||||
|
config_module = importlib.import_module(args['config'])
|
||||||
|
config = config_module.config
|
||||||
|
if args['debug']:
|
||||||
|
from configs.cvae_norm_1 import config
|
||||||
|
|
||||||
|
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
|
||||||
|
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
|
||||||
|
if args['debug']:
|
||||||
|
os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
|
||||||
|
|
||||||
|
import time
|
||||||
|
import argparse
|
||||||
|
import wandb
|
||||||
|
import tqdm
|
||||||
|
import random
|
||||||
|
import numpy as np
|
||||||
|
import plotly.graph_objects as go
|
||||||
|
import plotly.express as ex
|
||||||
|
from PIL import Image
|
||||||
|
|
||||||
|
if config['is_skirt']:
|
||||||
|
from losses.losses import edge_loss_skirt as edge_loss
|
||||||
|
else:
|
||||||
|
from losses.losses import edge_loss
|
||||||
|
|
||||||
|
import torch
|
||||||
|
import torch.nn as nn
|
||||||
|
import torch.optim as optim
|
||||||
|
from data.dataset import Dataset
|
||||||
|
from models.cond_encoder import AutoEncoder
|
||||||
|
from utils.checkpoints import CheckpointSaver, load_model
|
||||||
|
from utils.utils import InfiniteDataLoader as DataLoader
|
||||||
|
from utils.postprocess import fix_collision
|
||||||
|
from losses.losses import collision_loss, normal_loss
|
||||||
|
from pytorch_msssim import MS_SSIM
|
||||||
|
from models.cvae_norm_model import CVAENorm
|
||||||
|
from smpl.smpl_torch import SMPL
|
||||||
|
from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision
|
||||||
|
|
||||||
|
|
||||||
|
def init_wandb():
|
||||||
|
run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags'])
|
||||||
|
artifact = wandb.Artifact('code', type='code')
|
||||||
|
artifact.add_file('scripts/cvae_norm.py')
|
||||||
|
artifact.add_file('losses/losses.py')
|
||||||
|
artifact.add_file('models/base.py')
|
||||||
|
artifact.add_file('models/cond_encoder.py')
|
||||||
|
artifact.add_file('models/convnext.py')
|
||||||
|
artifact.add_file('models/cvae_norm_model.py')
|
||||||
|
artifact.add_file('data/dataset.py')
|
||||||
|
config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')]
|
||||||
|
for config_file_name in config_file_names:
|
||||||
|
file_name = '/'.join(config_file_name.split('.')) + '.py'
|
||||||
|
if os.path.exists(file_name):
|
||||||
|
artifact.add_file(file_name)
|
||||||
|
run.log_artifact(artifact)
|
||||||
|
|
||||||
|
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
||||||
|
|
||||||
|
|
||||||
|
def kl_loss(mean: torch.Tensor, logvar: torch.Tensor) -> torch.Tensor:
|
||||||
|
kl_loss = 1 + logvar - torch.square(mean) - torch.exp(logvar)
|
||||||
|
kl_loss = torch.mean(kl_loss)
|
||||||
|
kl_loss *= -0.5
|
||||||
|
return kl_loss
|
||||||
|
|
||||||
|
|
||||||
|
def train_step(batch):
|
||||||
|
model.train()
|
||||||
|
pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
|
||||||
|
pred = pred * 1.1
|
||||||
|
mesh_pred = uv2mesh(pred)
|
||||||
|
|
||||||
|
|
||||||
|
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_normals'] - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||||
|
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_normals'] - mesh_pred) ** 2, axis=-1), axis=-1))
|
||||||
|
ms_ssim = torch.mean(_MSSSIM(pred + 1.1, batch['uv_normals'] + 1.1))
|
||||||
|
kl = kl_loss(mean, logvar)
|
||||||
|
|
||||||
|
reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim)
|
||||||
|
loss = reconstr_loss + g_balancing_coeff * kl
|
||||||
|
|
||||||
|
optimizer.zero_grad()
|
||||||
|
loss.backward()
|
||||||
|
optimizer.step()
|
||||||
|
|
||||||
|
model.eval()
|
||||||
|
with torch.inference_mode():
|
||||||
|
mean = torch.mean(mean)
|
||||||
|
logvar = torch.mean(logvar)
|
||||||
|
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_normals'] - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
|
||||||
|
|
||||||
|
return { 'train/loss': loss, 'train/euclid_error': metric,
|
||||||
|
'train/reconstr_loss': reconstr_loss,
|
||||||
|
'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
|
||||||
|
'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss,
|
||||||
|
'train/ms_ssim': ms_ssim,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def valid_step(batch):
|
||||||
|
model.eval()
|
||||||
|
with torch.inference_mode():
|
||||||
|
pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
|
||||||
|
pred = pred * 1.1
|
||||||
|
mesh_pred = uv2mesh(pred)
|
||||||
|
|
||||||
|
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_normals'] - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||||
|
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_pred - batch['mesh_normals']) ** 2, axis=-1), axis=-1))
|
||||||
|
ms_ssim = torch.mean(_MSSSIM(pred + 1.1, batch['uv_static'] + 1.1))
|
||||||
|
kl = kl_loss(mean, logvar)
|
||||||
|
|
||||||
|
reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim)
|
||||||
|
loss = reconstr_loss + g_balancing_coeff * kl
|
||||||
|
|
||||||
|
mean = torch.mean(mean)
|
||||||
|
logvar = torch.mean(logvar)
|
||||||
|
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_normals'] - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
|
||||||
|
|
||||||
|
|
||||||
|
return { 'valid/loss': loss, 'valid/euclid_error': metric,
|
||||||
|
'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss,
|
||||||
|
'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
|
||||||
|
'valid/ms_ssim': ms_ssim,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def plot_everything(batch: dict, type: str):
|
||||||
|
model.eval()
|
||||||
|
with torch.inference_mode():
|
||||||
|
pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
|
||||||
|
|
||||||
|
pred = pred * 1.1
|
||||||
|
# mesh_pred = uv2mesh(pred).detach().cpu().numpy()
|
||||||
|
|
||||||
|
uv_static_img = torch.permute(batch['uv_static'], [0,2,3,1])
|
||||||
|
uv_body_posed_img = torch.permute(batch['uv_body_posed'], [0,2,3,1])
|
||||||
|
orig_img = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.1) / 2.2
|
||||||
|
pred_img = torch.permute(pred, [0,2,3,1])
|
||||||
|
img = torch.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img), axis=2)
|
||||||
|
imgs = [wandb.Image((img[i].cpu().numpy() + 1) / 2.0) for i in range(4)]
|
||||||
|
|
||||||
|
# F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
|
||||||
|
# mask = batch['mesh_mask'].cpu().numpy().astype(bool)
|
||||||
|
|
||||||
|
mean_hist = wandb.Histogram(sequence=mean.cpu().numpy().mean(axis=0))
|
||||||
|
logvar_hist = wandb.Histogram(sequence=logvar.cpu().numpy().mean(axis=0))
|
||||||
|
|
||||||
|
return { **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
|
||||||
|
|
||||||
|
|
||||||
|
def sample(folder):
|
||||||
|
# run = wandb.init(project='vae_plots', name=folder.split('/')[-1])
|
||||||
|
load_model(model,folder)
|
||||||
|
count = 0
|
||||||
|
for batch in dataset_train:
|
||||||
|
batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
|
||||||
|
uv_normals = tf.one_hot(batch['uv_normals'], 7)
|
||||||
|
nr_of_samples=2
|
||||||
|
|
||||||
|
pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[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 = tf.tile(pose[tf.newaxis,:], [nr_of_samples,1]), tf.tile(shape[tf.newaxis,:], [nr_of_samples,1])
|
||||||
|
|
||||||
|
mesh_pred = uv2mesh(pred)
|
||||||
|
mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy()
|
||||||
|
mesh_orig = batch['mesh_posed'][0].numpy()
|
||||||
|
mesh_orig_reposed = smpl.run_garment(pose[:1], shape[:1], batch['mesh_unposed'][:1]).numpy()[0]
|
||||||
|
|
||||||
|
body = batch['mesh_body_posed'][0].numpy()
|
||||||
|
body_color = np.ones_like(body, dtype=np.int32)*100
|
||||||
|
|
||||||
|
F = np.load("custom_utils/smpl_faces.npy")
|
||||||
|
mask = batch['mesh_mask'].numpy().astype(bool)[0]
|
||||||
|
_, faces = _maskFaces(np.ones((config['smpl_res'], 3)), F, mask)
|
||||||
|
|
||||||
|
pred_zero = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples, zero_latent=True)
|
||||||
|
mesh_pred_zero = uv2mesh(pred_zero)
|
||||||
|
mesh_posed_zero = smpl.run_garment(pose, shape, mesh_pred_zero).numpy()
|
||||||
|
|
||||||
|
|
||||||
|
meshes = []
|
||||||
|
meshes.append(go.Mesh3d(
|
||||||
|
# 8 vertices of a cube
|
||||||
|
x=mesh_orig_reposed[mask,0],
|
||||||
|
y=mesh_orig_reposed[mask,2],
|
||||||
|
z=mesh_orig_reposed[mask,1],
|
||||||
|
# i, j and k give the vertices of triangles
|
||||||
|
i = faces[:,0],
|
||||||
|
j = faces[:,1],
|
||||||
|
k = faces[:,2]
|
||||||
|
))
|
||||||
|
|
||||||
|
for i in range(nr_of_samples):
|
||||||
|
x = mesh_posed[i][mask, :].copy()
|
||||||
|
# x[:, 2] += 1 * (i + 1)
|
||||||
|
x[:, 2] += 1
|
||||||
|
meshes.append(go.Mesh3d(
|
||||||
|
# 8 vertices of a cube
|
||||||
|
x=x[:,0],
|
||||||
|
y=x[:,2],
|
||||||
|
z=x[:,1],
|
||||||
|
# i, j and k give the vertices of triangles
|
||||||
|
i = faces[:,0],
|
||||||
|
j = faces[:,1],
|
||||||
|
k = faces[:,2]
|
||||||
|
))
|
||||||
|
|
||||||
|
|
||||||
|
for i in range(nr_of_samples):
|
||||||
|
x = mesh_posed_zero[i][mask, :].copy()
|
||||||
|
# x[:, 2] += 1 * (i + 1)
|
||||||
|
x[:, 2] += 2
|
||||||
|
meshes.append(go.Mesh3d(
|
||||||
|
# 8 vertices of a cube
|
||||||
|
x=x[:,0],
|
||||||
|
y=x[:,2],
|
||||||
|
z=x[:,1],
|
||||||
|
# i, j and k give the vertices of triangles
|
||||||
|
i = faces[:,0],
|
||||||
|
j = faces[:,1],
|
||||||
|
k = faces[:,2]
|
||||||
|
))
|
||||||
|
|
||||||
|
# for i in range(5):
|
||||||
|
# x = body.copy()
|
||||||
|
# x[:, 2] += 1 * i
|
||||||
|
# meshes.append(go.Mesh3d(
|
||||||
|
# # 8 vertices of a cube
|
||||||
|
# x=x[:,0],
|
||||||
|
# y=x[:,2],
|
||||||
|
# z=x[:,1],
|
||||||
|
# # i, j and k give the vertices of triangles
|
||||||
|
# i = F[:,0],
|
||||||
|
# j = F[:,1],
|
||||||
|
# k = F[:,2],
|
||||||
|
# vertexcolor=body_color
|
||||||
|
# ))
|
||||||
|
|
||||||
|
|
||||||
|
fig = go.Figure(data=meshes)
|
||||||
|
|
||||||
|
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=2, z=1))
|
||||||
|
# fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=nr_of_samples-1, z=1))
|
||||||
|
fig.update_layout(
|
||||||
|
scene = dict(
|
||||||
|
xaxis = dict(nticks=4, range=[-1,1],),
|
||||||
|
# yaxis = dict(nticks=4, range=[-1,nr_of_samples+1],),
|
||||||
|
yaxis = dict(nticks=4, range=[-1,3],),
|
||||||
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
||||||
|
)
|
||||||
|
|
||||||
|
# wandb.log({'plot_' + str(count): fig})
|
||||||
|
fig.show()
|
||||||
|
|
||||||
|
pred = pred.numpy()
|
||||||
|
frames = [Image.fromarray(((pred[i] + 1) * 128).astype(np.int8), mode='RGB') for i in range(pred.shape[0])]
|
||||||
|
frames[0].save("temp/garment_1.gif", format="GIF", append_images=frames[1:],
|
||||||
|
save_all=True, duration=500, loop=0)
|
||||||
|
|
||||||
|
|
||||||
|
if count > 10:
|
||||||
|
break
|
||||||
|
|
||||||
|
print(count)
|
||||||
|
count += 1
|
||||||
|
|
||||||
|
print()
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
def test():
|
||||||
|
str_split = config['name'].split('_')
|
||||||
|
test_idx = str_split.index('test')
|
||||||
|
checkpoint_name = '_'.join(str_split[:test_idx])
|
||||||
|
load_model(model, 'checkpoints/' + checkpoint_name)
|
||||||
|
|
||||||
|
dataset_test = factory.get_dataset(folder=config['test_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False, do_repeat=False)
|
||||||
|
static_dataset_test = StaticDataset(folder=config['test_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False)
|
||||||
|
|
||||||
|
step = 0
|
||||||
|
losses = []
|
||||||
|
|
||||||
|
for batch in tqdm.tqdm(dataset_test):
|
||||||
|
batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
|
||||||
|
|
||||||
|
test_loss = test_step(batch)
|
||||||
|
losses.append(test_loss)
|
||||||
|
|
||||||
|
to_log = { **{ 'current_step': step }, **test_loss }
|
||||||
|
if step % 1000 == 0:
|
||||||
|
figs = plot_everything(batch, 'test')
|
||||||
|
to_log = { **to_log, **figs }
|
||||||
|
|
||||||
|
wandb.log(to_log, step = step)
|
||||||
|
|
||||||
|
# print(step)
|
||||||
|
step += 1
|
||||||
|
|
||||||
|
# averages = dict()
|
||||||
|
path_to_plotly_html = "temp/plotly_figure.html"
|
||||||
|
|
||||||
|
histograms = dict()
|
||||||
|
for key in test_loss.keys():
|
||||||
|
accumulated = [losses[i][key].numpy() for i in range(len(losses))]
|
||||||
|
fig = ex.histogram(accumulated, title='Average: ' + str(np.asarray(accumulated).mean()))
|
||||||
|
fig.write_html(path_to_plotly_html, auto_play = False)
|
||||||
|
|
||||||
|
histograms['all/' + key.split('/')[-1] + '_hist'] = wandb.Html(path_to_plotly_html)
|
||||||
|
# averages['all/' + key.split('/')[-1] + '_avg'] = np.asarray(accumulated).mean()
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
wandb.log({ **histograms }, step = step)
|
||||||
|
wandb.finish()
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
def train():
|
||||||
|
global g_balancing_coeff
|
||||||
|
global step
|
||||||
|
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'] if 'balancing_activation_limit' in config.keys() else 0.017):
|
||||||
|
g_balancing_coeff += 1 / 10000
|
||||||
|
|
||||||
|
if step % 10000 == 0:
|
||||||
|
ckpt_saver(model, step, optimizer, None)
|
||||||
|
|
||||||
|
step += 1
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
if not args['debug']:
|
||||||
|
init_wandb()
|
||||||
|
|
||||||
|
smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
|
||||||
|
skirt_modifier = '_skirt' if config['is_skirt'] else ''
|
||||||
|
|
||||||
|
dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'])
|
||||||
|
dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'])
|
||||||
|
train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, )
|
||||||
|
valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=True)
|
||||||
|
train_accumulator = Accumulator()
|
||||||
|
valid_accumulator = Accumulator()
|
||||||
|
|
||||||
|
model = CVAENorm(config)
|
||||||
|
|
||||||
|
optimizer = optim.Adam(model.parameters(), lr=config['lr'])
|
||||||
|
_MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
|
||||||
|
g_balancing_coeff = config['starting_balancing_coeff']
|
||||||
|
|
||||||
|
ckpt_saver = CheckpointSaver('checkpoints/iccv/' + config['name'], top_n=5)
|
||||||
|
|
||||||
|
step = 0
|
||||||
|
if config['pretrained_model'] != '':
|
||||||
|
step = load_model(model, config['pretrained_model'])
|
||||||
|
|
||||||
|
if not args['debug']:
|
||||||
|
# model = torch.compile(model)
|
||||||
|
wandb.watch(model, log='all', log_freq=10000, log_graph=True)
|
||||||
|
|
||||||
|
train()
|
||||||
Reference in New Issue
Block a user