287 lines
11 KiB
Python
287 lines
11 KiB
Python
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())
|
|
|
|
|
|
if args['debug']:
|
|
from configs.iccvw.cvae_norm_5 import config
|
|
else:
|
|
config_module = importlib.import_module(args['config'])
|
|
config = config_module.config
|
|
|
|
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
|
|
if args['debug']:
|
|
os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
|
|
|
|
import time
|
|
import argparse
|
|
import wandb
|
|
import tqdm
|
|
import random
|
|
import numpy as np
|
|
import kaleido
|
|
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():
|
|
wandb.login(host='https://wandb2.lnrweb.com', key='local-2a78b434e9bc51e9f12625f8321a9e3ee34af16d', relogin=True, force=True)
|
|
run = wandb.init(project='iccvw', 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 * 1.4
|
|
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 + 1.4, batch['uv_normals'] + 1.4))
|
|
kl = kl_loss(mean, logvar)
|
|
|
|
reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim)
|
|
loss: torch.Tensor = 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 * 1.4
|
|
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 + 1.4, batch['uv_static'] + 1.4))
|
|
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 * 1.4
|
|
# 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]) + 1.4) / 2.8
|
|
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 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 / 2000
|
|
|
|
if step % 20000 == 0:
|
|
ckpt_saver(model, step, optimizer, None)
|
|
|
|
step += 1
|
|
|
|
|
|
|
|
def sample():
|
|
model.eval()
|
|
load_model(model, f'checkpoints/iccvw/{config["name"]}')
|
|
count = 0
|
|
|
|
for batch in train_dataloader:
|
|
uv_static = batch['uv_static']
|
|
uv_body_posed = batch['uv_body_posed']
|
|
uv_mask = batch['uv_mask']
|
|
|
|
batch_size = uv_static.size(0)
|
|
|
|
for i in range(batch_size):
|
|
uv_static_tiled = uv_static[i][None,:,:,:].repeat(4, 1, 1, 1)
|
|
uv_body_posed_tiled = uv_body_posed[i][None,:,:,:].repeat(4, 1, 1, 1)
|
|
uv_mask_tiled = uv_mask[i][None,:,:].repeat(4, 1, 1)
|
|
|
|
with torch.inference_mode():
|
|
pred = model.sample(uv_static_tiled, uv_body_posed_tiled, uv_mask_tiled)
|
|
|
|
pred = pred * 1.4
|
|
|
|
pred = pred.cpu().numpy().transpose(0, 2, 3, 1)
|
|
pred = (pred + 1.4) / 2.8
|
|
pred = pred * uv_mask_tiled[:,:,:,None].cpu().numpy()
|
|
gt = (batch['uv_normals'][i].cpu().numpy().transpose(1, 2, 0) + 1.4) / 2.8 * uv_mask_tiled[0,:,:,None].cpu().numpy()
|
|
img = np.concatenate(pred, axis=1)
|
|
img = np.concatenate([gt, img], axis=1)
|
|
# flip image along its shorter edge
|
|
img = img[::-1,:,:]
|
|
|
|
fig = ex.imshow(img)
|
|
fig.update_layout(margin=dict(l=0, r=0, b=0, t=0, pad=0), width=img.shape[1], height=img.shape[0])
|
|
fig.update_xaxes(visible=False)
|
|
fig.update_yaxes(visible=False)
|
|
fig.write_image(f'temp/normals/{batch["id"][i]}_{batch["frame_nr"][i].cpu().numpy()}_{batch["garment"][i]}.png')
|
|
count += 1
|
|
|
|
if count > 100:
|
|
break
|
|
|
|
|
|
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)
|
|
|
|
sample()
|
|
exit()
|
|
|
|
|
|
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/iccvw/' + config['name'], top_n=25)
|
|
|
|
step = 0
|
|
if config['pretrained_model'] != '':
|
|
if 'ignore_saved_optimizer' in config.keys() and config['ignore_saved_optimizer']:
|
|
step = load_model(model, config['pretrained_model'])
|
|
else:
|
|
step = load_model(model, config['pretrained_model'], optimizer=optimizer)
|
|
|
|
if not args['debug']:
|
|
# model = torch.compile(model)
|
|
wandb.watch(model, log='all', log_freq=10000, log_graph=True)
|
|
|
|
train() |