557 lines
28 KiB
Python
557 lines
28 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.pyr_64_128_256_512_cape_f 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 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
|
|
import torch.nn.functional as F
|
|
from data.dataset import Dataset
|
|
from utils.checkpoints import CheckpointSaver, load_model
|
|
from utils.utils import InfiniteDataLoader as DataLoader
|
|
from utils.utils import text_to_html
|
|
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():
|
|
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_pyramid.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/pyramid_model.py')
|
|
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:
|
|
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 plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, collision_faces, collision_color):
|
|
fig = make_subplots(rows=1, cols=1+len(mesh_pred_unposed_levels)+1+1, start_cell="top-left", specs = [ [{ 'type': 'scene' } for _ in range(1+len(mesh_pred_unposed_levels)+1+1)] ])
|
|
|
|
fig.add_trace(go.Mesh3d(
|
|
x=mesh_gt[:,0],
|
|
y=mesh_gt[:,2],
|
|
z=mesh_gt[:,1],
|
|
i = faces[:,0],
|
|
j = faces[:,1],
|
|
k = faces[:,2],
|
|
text="Ground Truth"
|
|
),
|
|
row=1, col=1)
|
|
|
|
for i, mesh in enumerate(mesh_pred_unposed_levels):
|
|
fig.add_trace(go.Mesh3d(
|
|
x=mesh[:,0],
|
|
y=mesh[:,2],
|
|
z=mesh[:,1],
|
|
i = faces[:,0],
|
|
j = faces[:,1],
|
|
k = faces[:,2],
|
|
text='Unposed level_' + str(i)
|
|
),
|
|
row=1, col=i+2)
|
|
|
|
fig.add_trace(go.Mesh3d(
|
|
x=mesh_posed[:,0],
|
|
y=mesh_posed[:,2],
|
|
z=mesh_posed[:,1],
|
|
i = faces[:,0],
|
|
j = faces[:,1],
|
|
k = faces[:,2],
|
|
text='Posed GT'
|
|
),
|
|
row=1, col=1+len(mesh_pred_unposed_levels)+1)
|
|
|
|
fig.add_trace(go.Mesh3d(
|
|
x=collision[:,0],
|
|
y=collision[:,2],
|
|
z=collision[:,1],
|
|
i = collision_faces[:,0],
|
|
j = collision_faces[:,1],
|
|
k = collision_faces[:,2],
|
|
vertexcolor=collision_color,
|
|
text='Posed output on body'
|
|
),
|
|
row=1, col=1+len(mesh_pred_unposed_levels)+1+1)
|
|
|
|
if len(mesh_pred_unposed_levels) == 1:
|
|
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
|
|
scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
|
|
scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
|
|
scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
|
|
)
|
|
helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
|
|
yaxis = dict(nticks=4, range=[-1,1],),
|
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
|
fig.update_layout(scene = helper,
|
|
scene2 = helper,
|
|
scene3 = helper,
|
|
scene4 = helper,
|
|
)
|
|
if len(mesh_pred_unposed_levels) == 2:
|
|
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
|
|
scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
|
|
scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
|
|
scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
|
|
scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
|
|
)
|
|
helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
|
|
yaxis = dict(nticks=4, range=[-1,1],),
|
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
|
fig.update_layout(scene = helper,
|
|
scene2 = helper,
|
|
scene3 = helper,
|
|
scene4 = helper,
|
|
scene5 = helper,
|
|
)
|
|
if len(mesh_pred_unposed_levels) == 3:
|
|
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
|
|
scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
|
|
scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
|
|
scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
|
|
scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
|
|
scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,)
|
|
)
|
|
helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
|
|
yaxis = dict(nticks=4, range=[-1,1],),
|
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
|
fig.update_layout(scene = helper,
|
|
scene2 = helper,
|
|
scene3 = helper,
|
|
scene4 = helper,
|
|
scene5 = helper,
|
|
scene6 = helper,
|
|
)
|
|
if len(mesh_pred_unposed_levels) == 4:
|
|
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
|
|
scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
|
|
scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
|
|
scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
|
|
scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
|
|
scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,),
|
|
scene7_aspectmode='manual', scene7_aspectratio=dict(x=1, y=1, z=1,),
|
|
)
|
|
helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
|
|
yaxis = dict(nticks=4, range=[-1,1],),
|
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
|
fig.update_layout(scene = helper,
|
|
scene2 = helper,
|
|
scene3 = helper,
|
|
scene4 = helper,
|
|
scene5 = helper,
|
|
scene6 = helper,
|
|
scene7 = helper,
|
|
)
|
|
if len(mesh_pred_unposed_levels) == 5:
|
|
fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1),
|
|
scene2_aspectmode='manual', scene2_aspectratio=dict(x=1, y=1, z=1),
|
|
scene3_aspectmode='manual', scene3_aspectratio=dict(x=1, y=1, z=1),
|
|
scene4_aspectmode='manual', scene4_aspectratio=dict(x=1, y=1, z=1),
|
|
scene5_aspectmode='manual', scene5_aspectratio=dict(x=1, y=1, z=1),
|
|
scene6_aspectmode='manual', scene6_aspectratio=dict(x=1, y=1, z=1,),
|
|
scene7_aspectmode='manual', scene7_aspectratio=dict(x=1, y=1, z=1,),
|
|
scene8_aspectmode='manual', scene8_aspectratio=dict(x=1, y=1, z=1,),
|
|
)
|
|
helper = dict(xaxis = dict(nticks=4, range=[-1,1],),
|
|
yaxis = dict(nticks=4, range=[-1,1],),
|
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
|
fig.update_layout(scene = helper,
|
|
scene2 = helper,
|
|
scene3 = helper,
|
|
scene4 = helper,
|
|
scene5 = helper,
|
|
scene6 = helper,
|
|
scene7 = helper,
|
|
scene8 = helper,
|
|
)
|
|
return fig
|
|
|
|
|
|
def train_step(batch):
|
|
if config['is_cape']:
|
|
batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
|
|
|
|
model.train()
|
|
# with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp):
|
|
levels_input, conds = group_inputs_for_levels(batch, config)
|
|
|
|
out_levels = model([levels_input, conds])
|
|
|
|
if config['use_skinning']:
|
|
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
|
|
else:
|
|
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
|
|
|
output = dict()
|
|
reconstr_loss_total = 0
|
|
kl_total = 0
|
|
posed_or_not = 'unposed' if config['use_skinning'] else 'posed'
|
|
|
|
for i, res in enumerate(config['pyramid']['resolutions']):
|
|
# i = -1
|
|
res = config['pyramid']['resolutions'][i]
|
|
res_modifier = '_' + str(res) if res != 512 else ''
|
|
pred, mean, logvar = out_levels[i]
|
|
|
|
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((levels_input[i][0] - pred) ** 2), dim=-1), dim=[1, 2])) # levels_input[i][0] = uv_orig
|
|
kl = kl_loss(mean, logvar)
|
|
|
|
mesh_pred = uv2mesh(pred)
|
|
|
|
if config['use_skinning']:
|
|
shape = batch['pose_shape'][:, 72:]
|
|
gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
|
|
shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
|
|
|
|
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None]
|
|
mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
|
|
else:
|
|
mesh_pred_posed = mesh_pred
|
|
|
|
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask']))
|
|
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask'])
|
|
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
|
|
n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
|
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1))
|
|
|
|
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
|
|
if not config['is_cape']:
|
|
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff']
|
|
if config['use_norm_loss'] and step > 2000:
|
|
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * n_loss * config['reg_loss_coeff']
|
|
|
|
kl_total += kl
|
|
loss: torch.Tensor = reconstr_loss_total + g_balancing_coeff * kl_total
|
|
|
|
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, levels_input[i][0] + 1))
|
|
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask'])
|
|
|
|
output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric,
|
|
'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl,
|
|
'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss,
|
|
'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss, 'train/ms_ssim' + res_modifier: ms_ssim,
|
|
'train/collision_ratio': c_ratio } } #
|
|
|
|
|
|
return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output }
|
|
|
|
|
|
def valid_step(batch):
|
|
if config['is_cape']:
|
|
batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
|
|
|
|
model.eval()
|
|
with torch.inference_mode():
|
|
levels_input, conds = group_inputs_for_levels(batch, config)
|
|
|
|
out_levels = model([levels_input, conds])
|
|
|
|
if config['use_skinning']:
|
|
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
|
|
else:
|
|
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
|
|
|
output = dict()
|
|
reconstr_loss_total = 0
|
|
kl_total = 0
|
|
|
|
for i, res in enumerate(config['pyramid']['resolutions']):
|
|
# i = -1
|
|
res = config['pyramid']['resolutions'][i]
|
|
res_modifier = '_' + str(res) if res != 512 else ''
|
|
pred, mean, logvar = out_levels[i]
|
|
|
|
mesh_pred = uv2mesh(pred)
|
|
|
|
if config['use_skinning']:
|
|
shape = batch['pose_shape'][:, 72:]
|
|
gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64)
|
|
shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])])
|
|
|
|
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_fix']['mesh_mask'][:,:,None]
|
|
mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
|
|
else:
|
|
mesh_pred_posed = mesh_pred
|
|
|
|
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_fix']['mesh_mask']))
|
|
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_fix']['mesh_mask'])
|
|
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
|
|
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_fix']['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_fix']['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
|
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((levels_input[i][0] - pred) ** 2), dim=-1), dim=[1, 2]))
|
|
|
|
kl = kl_loss(mean, logvar)
|
|
|
|
if config['use_extra_losses']:
|
|
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss)
|
|
if not config['is_cape']:
|
|
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff']
|
|
if config['use_norm_loss'] and step > 2000:
|
|
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * n_loss * config['reg_loss_coeff']
|
|
else:
|
|
reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss)
|
|
|
|
kl_total += kl
|
|
loss = reconstr_loss_total + g_balancing_coeff * kl_total
|
|
|
|
mean = torch.mean(mean)
|
|
logvar = torch.mean(logvar)
|
|
|
|
ms_ssim = torch.mean(_MSSSIM(pred + 1, levels_input[i][0] + 1))
|
|
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_fix']['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / torch.sum(batch['mesh_fix']['mesh_mask'])
|
|
|
|
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/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, } } #
|
|
|
|
|
|
|
|
return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output }
|
|
|
|
|
|
def plot_everything(batch: dict, type: str):
|
|
if config['is_cape']:
|
|
batch['mesh_fix'] = {'mesh_mask': batch['mesh_mask']}
|
|
|
|
if config['use_skinning']:
|
|
mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed']
|
|
else:
|
|
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)
|
|
output_levels = model(levels_input)
|
|
|
|
mesh_pred_levels = [uv2mesh(output_levels[i][0]).cpu() for i in range(len(output_levels))]
|
|
mesh_orig_posed = batch['mesh_posed'].cpu()
|
|
body = batch['mesh_body_posed'].cpu().numpy()
|
|
|
|
# mesh_pred = torch.cat((mesh_pred[:, :, 0:1], -mesh_pred[:, :, 2:3], mesh_pred[:, :, 1:2]), dim=2)
|
|
# mesh_pred_levels = [torch.cat((mesh_pred_levels[i][:, :, 0:1], -mesh_pred_levels[i][:, :, 2:3], mesh_pred_levels[i][:, :, 1:2]), dim=2).numpy() for i in range(len(mesh_pred_levels))]
|
|
# mesh_orig_posed = torch.cat((mesh_orig_posed[:, :, 0:1], -mesh_orig_posed[:, :, 2:3], mesh_orig_posed[:, :, 1:2]), dim=2).numpy()
|
|
|
|
orig_img = (torch.permute(uv_orig, [0,2,3,1]) + 1) / 2
|
|
uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2
|
|
uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2
|
|
uv_normals = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.4) / 2.8
|
|
pred_img = torch.concatenate([torch.permute(model.resizers[512](output_levels[i][0]), [0,2,3,1]) for i in range(len(output_levels))], dim=2)
|
|
# 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.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])
|
|
|
|
img = torch.concat((uv_static_img, uv_body_posed_img, uv_normals, orig_img, pred_img), dim=2)
|
|
imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)]
|
|
|
|
_F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
|
|
mask = batch['mesh_fix']['mesh_mask'].cpu().numpy().astype(bool)
|
|
if 'mesh_fix' in batch and not config['is_cape']:
|
|
faces = [np.load( (dataset_train if type == 'train' else dataset_valid).folder + "/mesh_fixed/" + batch['id'][i] + '_' + batch['garment'][i] + ".npz" )['faces'] for i in range(len(batch['id']))]
|
|
else:
|
|
_, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask)
|
|
|
|
if config['use_skinning']:
|
|
shape = batch['pose_shape'][:, 72:]
|
|
gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long)
|
|
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])]
|
|
|
|
mesh_unposed_shaped_levels = [[] for _ in range(mask.shape[0])]
|
|
for i in range(len(output_levels)):
|
|
mesh_unposed_shaped = [mesh_pred_levels[i][j, mask[j], :] + shape_offsets[j, mask[j]] for j in range(mask.shape[0])]
|
|
for k in range(mask.shape[0]):
|
|
mesh_unposed_shaped_levels[k].append(mesh_unposed_shaped[k])
|
|
|
|
# full res version
|
|
mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32)
|
|
for i in range(mask.shape[0]):
|
|
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()
|
|
|
|
# rotate gt 180 degrees along z axis
|
|
# gt = [np.matmul(gt[i], np.array([[np.cos(np.pi), -np.sin(np.pi), 0], [np.sin(np.pi), np.cos(np.pi), 0], [0, 0, 1]])) for i in range(mask.shape[0])]
|
|
|
|
# gt_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32)
|
|
# for i in range(mask.shape[0]):
|
|
# gt_full[i, mask[i], :] = gt[i]
|
|
# mesh_orig_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(np.stack(gt_full, axis=0), device=config['device'], dtype=torch.float32))[0].cpu().numpy()
|
|
else:
|
|
mesh_posed = mesh_pred_levels[-1]
|
|
gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])]
|
|
mesh_unposed_shaped_levels = [[mesh_pred_levels[i][j, mask[j], :] for i in range(len(output_levels))] for j 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(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])]
|
|
|
|
if config['is_cape']:
|
|
collision = mesh_posed
|
|
collision_faces = faces
|
|
collision_color = [np.ones_like(mesh_posed[i], dtype=np.int32)*230 for i in range(len(mesh_posed))]
|
|
else:
|
|
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_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) }
|
|
|
|
if config['is_cape']:
|
|
figs_coll = dict()
|
|
else:
|
|
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))]
|
|
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))]
|
|
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) }
|
|
|
|
batch_id = batch['id']
|
|
batch_frame_nr = batch['frame_nr']
|
|
batch_garment = batch['garment']
|
|
batch_info = [f'batch_info: id: {batch_id[i]}, frame_nr: {batch_frame_nr[i]}, garment: {batch_garment[i]}' for i in range(len(batch_id))]
|
|
batch_info = text_to_html(batch_info)
|
|
batch_info = wandb.Html(batch_info)
|
|
|
|
return { **figs, **figs_coll, **{ type + '/images': imgs, }, **{ f'{type}/batch_info': batch_info }, }
|
|
|
|
|
|
def speed_step(levels_input, conds):
|
|
|
|
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)
|
|
|
|
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 / 50000
|
|
|
|
if step % 10000 == 0 and not args['debug']:
|
|
ckpt_saver(model, step, optimizer, None)
|
|
|
|
step += 1
|
|
|
|
|
|
if __name__ == '__main__':
|
|
if not args['debug']:
|
|
init_wandb()
|
|
|
|
use_amp = True
|
|
smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
|
|
skirt_modifier = '_skirt' if config['is_skirt'] else ''
|
|
dataset_resolutions = config['pyramid']['resolutions'].copy()
|
|
if 512 not in dataset_resolutions:
|
|
dataset_resolutions.append(512)
|
|
|
|
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_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'])
|
|
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: Pyramid = Pyramid(config)
|
|
|
|
optimizer = optim.Adam(model.parameters(), lr=config['lr'] * 0.05)
|
|
_MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
|
|
ckpt_saver = CheckpointSaver('checkpoints/iccvw/' + config['name'] + '_fine_2', top_n=50)
|
|
scaler = torch.cuda.amp.GradScaler(enabled=use_amp)
|
|
|
|
g_balancing_coeff = config['starting_balancing_coeff']
|
|
config['pyramid']['loss_weights'] = [1,3,5,10,25]
|
|
|
|
step = load_model(model, f'checkpoints/iccvw/{config["name"]}', iteration='25000')
|
|
|
|
for param in model.static_enc.parameters(): param.requires_grad = False
|
|
for param in model.body_enc.parameters(): param.requires_grad = False
|
|
for param in model.norm_enc.parameters(): param.requires_grad = False
|
|
for i in range(len(model.levels)-1):
|
|
for param in model.levels[i].upscale_enhancer.parameters(): param.requires_grad = False
|
|
|
|
train() |