add cvae training
This commit is contained in:
+193
-281
@@ -1,21 +1,20 @@
|
||||
import os
|
||||
import sys
|
||||
from configs.config_abl_all_post 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)
|
||||
args = vars(parser.parse_args())
|
||||
|
||||
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']
|
||||
import tensorflow as tf
|
||||
|
||||
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)
|
||||
# os.environ["CUDA_LAUNCH_BLOCKING"] = '1'
|
||||
|
||||
import time
|
||||
import argparse
|
||||
@@ -26,256 +25,205 @@ import numpy as np
|
||||
import plotly.graph_objects as go
|
||||
import plotly.express as ex
|
||||
from PIL import Image
|
||||
from utils.postprocess import fix_collision
|
||||
|
||||
if config['is_skirt']:
|
||||
from utils.losses import edge_loss_skirt as edge_loss
|
||||
from losses.losses import edge_loss_skirt as edge_loss
|
||||
else:
|
||||
from utils.losses import edge_loss
|
||||
from losses.losses import edge_loss
|
||||
|
||||
from utils.losses import collision_ratio, kl_loss, normal_loss, collision_loss
|
||||
from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d, UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
|
||||
from data.dataset import DatasetFactory, StaticDataset
|
||||
from custom_utils.smpl import SMPL
|
||||
from models.cvae_model import CVAENew as CVAE
|
||||
from utils.utils import Accumulator
|
||||
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_model import CVAE
|
||||
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='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags'])
|
||||
run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
|
||||
artifact = wandb.Artifact('code', type='code')
|
||||
config_file_names = [key for key in sys.modules.keys() if (key.startswith('configs.') or key.startswith('custom_utils.') or key.startswith('utils.') or key.startswith('data.') or key.startswith('models.') or key.startswith('scripts.'))]
|
||||
artifact.add_file('scripts/cvae.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_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_adaptive=False, is_smpl_orig=config['is_cape'])
|
||||
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape'])
|
||||
|
||||
|
||||
def kl_loss(mean, logvar):
|
||||
kl_loss = 1 + logvar - tf.square(mean) - tf.exp(logvar)
|
||||
kl_loss = tf.reduce_mean(kl_loss)
|
||||
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
|
||||
|
||||
|
||||
# 3d loss on posed !!!!!!!!!!!!
|
||||
|
||||
# @tf.function
|
||||
def train_step(batch):
|
||||
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']
|
||||
|
||||
with tf.GradientTape() as tape:
|
||||
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']
|
||||
model.train()
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
|
||||
mesh_pred = uv2mesh(pred)
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=True)
|
||||
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])])
|
||||
# shape_offsets = torch.stack([torch.matmul(shape[i, :10], smpl.shapedirs[gender[i]][:, smpl.to_keep]) for i in range(shape.shape[0])])
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
|
||||
mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
|
||||
if config['use_skinning']:
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
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])])
|
||||
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
||||
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
|
||||
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (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'], is_smpl_orig=config['is_cape'])
|
||||
kl = kl_loss(mean, logvar)
|
||||
|
||||
# is the output already masked?
|
||||
reconstr_loss = l2_loss
|
||||
if config['use_extra_losses']:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss + n_loss) * config['reg_loss_coeff']
|
||||
|
||||
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
||||
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_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_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'], is_smpl_orig=config['is_cape'])
|
||||
# conc_loss = concept_loss(pred, batch['uv_unposed'])
|
||||
kl = kl_loss(mean, logvar)
|
||||
loss = reconstr_loss + g_balancing_coeff * kl
|
||||
|
||||
reconstr_loss = l2_loss
|
||||
if config['use_extra_losses']:
|
||||
if 'block_collision_loss' in config.keys() and config['block_collision_loss'] == True:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss) * config['reg_loss_coeff']
|
||||
else:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
|
||||
if config['use_norm_loss'] and step > 2000:
|
||||
reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
|
||||
optimizer.zero_grad()
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
loss = reconstr_loss + g_balancing_coeff * kl
|
||||
|
||||
mean = tf.reduce_mean(mean)
|
||||
logvar = tf.reduce_mean(logvar)
|
||||
|
||||
# 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)))
|
||||
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'])
|
||||
gradients = tape.gradient(loss, model.trainable_variables)
|
||||
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
|
||||
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'])
|
||||
|
||||
return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
|
||||
'train/reconstr_loss': reconstr_loss, 'train/collision_ratio': c_ratio,
|
||||
'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/normal_loss': n_loss,
|
||||
# 'train/ms_ssim': ms_ssim,
|
||||
'train/ms_ssim': ms_ssim,
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
@tf.function
|
||||
def valid_step(batch):
|
||||
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']
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
model.eval()
|
||||
with torch.inference_mode():
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
|
||||
mesh_pred = uv2mesh(pred)
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
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])])
|
||||
# shape_offsets = torch.stack([torch.matmul(shape[i, :10], smpl.shapedirs[gender[i]][:, smpl.to_keep]) for i in range(shape.shape[0])])
|
||||
|
||||
if config['use_skinning']:
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
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])])
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None]
|
||||
mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0]
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
|
||||
# is the output already masked?
|
||||
e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
||||
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio)
|
||||
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (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'], is_smpl_orig=config['is_cape'])
|
||||
kl = kl_loss(mean, logvar)
|
||||
|
||||
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
||||
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_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_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'], is_smpl_orig=config['is_cape'])
|
||||
# conc_loss = concept_loss(pred, batch['uv_unposed'])
|
||||
kl = kl_loss(mean, logvar)
|
||||
reconstr_loss = l2_loss
|
||||
if config['use_extra_losses']:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss + n_loss) * config['reg_loss_coeff']
|
||||
|
||||
reconstr_loss = l2_loss
|
||||
if config['use_extra_losses']:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
|
||||
if config['use_norm_loss']:
|
||||
reconstr_loss = reconstr_loss + n_loss * config['reg_loss_coeff']
|
||||
loss = reconstr_loss + g_balancing_coeff * kl
|
||||
|
||||
loss = reconstr_loss + g_balancing_coeff * kl
|
||||
|
||||
mean = tf.reduce_mean(mean)
|
||||
logvar = tf.reduce_mean(logvar)
|
||||
|
||||
# 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)))
|
||||
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'])
|
||||
# c_ratio = tf.reduce_mean(collision_ratio(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
|
||||
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'])
|
||||
|
||||
|
||||
return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric,
|
||||
'valid/reconstr_loss': reconstr_loss, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/collision_ratio': c_ratio,
|
||||
'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
|
||||
'valid/normal_loss': n_loss,# 'valid/ms_ssim': ms_ssim,
|
||||
'valid/normal_loss': n_loss, 'valid/ms_ssim': ms_ssim,
|
||||
}
|
||||
|
||||
|
||||
@tf.function
|
||||
def test_step(batch):
|
||||
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']
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
|
||||
if config['use_skinning']:
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
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])])
|
||||
|
||||
mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)
|
||||
mesh_orig_shaped = mesh_orig + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
mesh_orig_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_orig_shaped)
|
||||
else:
|
||||
mesh_pred_posed = mesh_pred
|
||||
mesh_orig_posed = mesh_orig
|
||||
|
||||
mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
|
||||
|
||||
# is the output already masked?
|
||||
|
||||
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
||||
c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
|
||||
c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_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_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))
|
||||
# conc_loss = concept_loss(pred, batch['uv_unposed'])
|
||||
kl = kl_loss(mean, logvar)
|
||||
|
||||
reconstr_loss = l2_loss
|
||||
if config['use_extra_losses']:
|
||||
reconstr_loss = reconstr_loss + l2_mesh_loss + (e_loss + c_loss) * config['reg_loss_coeff']
|
||||
|
||||
loss = reconstr_loss + g_balancing_coeff * kl
|
||||
|
||||
mean = tf.reduce_mean(mean)
|
||||
logvar = tf.reduce_mean(logvar)
|
||||
|
||||
ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, uv_orig + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
|
||||
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'])
|
||||
euclid_posed = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_posed - mesh_pred_posed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
||||
euclid_posed_fixed = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_posed - mesh_pred_posed_fixed) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
||||
|
||||
return { 'test/loss': loss, 'test/edge_loss': e_loss, 'test/collision_loss': c_loss, 'test/euclid_error': metric, 'test/ms_ssim': ms_ssim,
|
||||
'test/reconstr_loss': reconstr_loss, 'test/collision_ratio': c_ratio, 'test/l2_mesh_loss': l2_mesh_loss,
|
||||
'test/mean': mean, 'test/logvar': logvar, 'test/kl_loss': kl, 'test/var': np.e ** logvar,
|
||||
'test/euclid_posed': euclid_posed, 'test/euclid_posed_fixed': euclid_posed_fixed }
|
||||
|
||||
|
||||
def plot_everything(batch: dict, type: str):
|
||||
if config['use_skinning']:
|
||||
mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed']
|
||||
mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed']
|
||||
else:
|
||||
mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed']
|
||||
mesh_orig, uv_orig = batch['mesh_posed'].cpu().numpy(), batch['uv_posed']
|
||||
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
|
||||
model.eval()
|
||||
with torch.inference_mode():
|
||||
pred, mean, logvar = model([uv_orig, batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']])
|
||||
|
||||
mesh_pred = uv2mesh(pred).numpy()
|
||||
mesh_pred = uv2mesh(pred).detach().cpu().numpy()
|
||||
|
||||
orig_img = uv_orig
|
||||
uv_static_img = batch['uv_static']
|
||||
uv_body_posed_img = batch['uv_body_posed']
|
||||
pred_img = pred
|
||||
img = tf.concat((uv_static_img, uv_body_posed_img, orig_img, pred_img), axis=2)
|
||||
imgs = [wandb.Image((img[i] + 1) / 2.0) for i in range(4)]
|
||||
orig_img = torch.permute(uv_orig, [0,2,3,1])
|
||||
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])
|
||||
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("custom_utils/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
|
||||
mask = batch['mesh_mask'].numpy().astype(bool)
|
||||
F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
|
||||
mask = batch['mesh_mask'].cpu().numpy().astype(bool)
|
||||
|
||||
if config['use_skinning']:
|
||||
shape = batch['pose_shape'][:, 72:]
|
||||
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])])
|
||||
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()
|
||||
|
||||
garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
|
||||
garment_unposed = [garment_unposed[i] + shape_offsets.numpy()[i, mask[i], :] for i in range(mask.shape[0])]
|
||||
gt = [mesh_orig[i].numpy()[mask[i], :] + shape_offsets.numpy()[i, mask[i], :] for i in range(pred.shape[0])]
|
||||
garment_unposed = [garment_unposed[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(pred.shape[0])]
|
||||
|
||||
for i in range(mesh_orig.shape[0]):
|
||||
mesh_pred[i, mask[i], :] += shape_offsets.numpy()[i, mask[i], :]
|
||||
mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred).numpy()
|
||||
mesh_pred[i, mask[i], :] += shape_offsets[i, mask[i], :]
|
||||
mesh_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(mesh_pred, device=config['device']))[0].cpu().numpy()
|
||||
else:
|
||||
mesh_posed = mesh_pred
|
||||
gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
|
||||
garment_unposed, faces = maskFacesBatch(mesh_pred, F, mask)
|
||||
mesh_posed = mesh_pred.cpu().numpy()
|
||||
gt = [mesh_orig[i][mask[i], :] for i in range(pred.shape[0])]
|
||||
garment_unposed, faces = maskFacesBatch(mesh_pred.cpu().numpy(), F, mask)
|
||||
|
||||
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])]
|
||||
|
||||
|
||||
body = batch['mesh_body_posed'].numpy()
|
||||
mesh_posed_fixed = fix_collision(mesh_posed, body, mask).numpy()
|
||||
mesh_posed_fixed = fix_collision(torch.tensor(mesh_posed, device=config['device']), batch['mesh_body_posed'], torch.tensor(mask, device=config['device'])).cpu().numpy()
|
||||
body = batch['mesh_body_posed'].cpu().numpy()
|
||||
|
||||
garment_posed = [mesh_posed[i, mask[i], :] for i in range(body.shape[0])]
|
||||
collision = [np.concatenate((body[i], garment_posed[i]), axis=0) for i in range(len(garment_posed))]
|
||||
@@ -289,8 +237,8 @@ def plot_everything(batch: dict, type: str):
|
||||
figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) 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], flip_xy=(not config['use_skinning'] and config['remove_global_orientation'])) for i in range(4) }
|
||||
|
||||
mean_hist = wandb.Histogram(sequence=mean.numpy().mean(axis=0))
|
||||
logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0))
|
||||
mean_hist = wandb.Histogram(sequence=mean.cpu().numpy().mean(axis=0))
|
||||
logvar_hist = wandb.Histogram(sequence=logvar.cpu().numpy().mean(axis=0))
|
||||
|
||||
return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
|
||||
|
||||
@@ -414,6 +362,7 @@ def sample(folder):
|
||||
print()
|
||||
|
||||
|
||||
|
||||
def test():
|
||||
str_split = config['name'].split('_')
|
||||
test_idx = str_split.index('test')
|
||||
@@ -462,108 +411,71 @@ def test():
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# init_wandb()
|
||||
parser = argparse.ArgumentParser(description='')
|
||||
parser.add_argument('--name', type=str)
|
||||
args = vars(parser.parse_args())
|
||||
def train():
|
||||
valid_iterator = iter(valid_dataloader)
|
||||
|
||||
smpl = SMPL(orig_smpl=config['is_cape'])
|
||||
step = 0
|
||||
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)) } }
|
||||
|
||||
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):
|
||||
if balancing_activated_step == 0:
|
||||
balancing_activated_step = step
|
||||
g_balancing_coeff = g_balancing_coeff + 1 / 10000
|
||||
|
||||
if step % 10000 == 0:
|
||||
ckpt_saver(model, step, optimizer)
|
||||
|
||||
step += 1
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
init_wandb()
|
||||
# parser = argparse.ArgumentParser(description='')
|
||||
# parser.add_argument('--name', type=str)
|
||||
# parser.add_argument('--debug', action='store_true')
|
||||
# args = vars(parser.parse_args())
|
||||
|
||||
smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
|
||||
skirt_modifier = '_skirt' if config['is_skirt'] else ''
|
||||
|
||||
factory = DatasetFactory()
|
||||
|
||||
dataset_train = factory.get_dataset(folder=config['train_dir'],
|
||||
batch_size=config['batch_size'],
|
||||
signature=config['signature_dynamic'],
|
||||
resolutions=[config['resolution']],
|
||||
in_memory=config['dataset_in_memory'],
|
||||
use_one_hot=config['use_one_hot'],
|
||||
use_no_orient=config['remove_global_orientation'],
|
||||
frames_file=config['frames_file'] if 'frames_file' in config.keys() else None,
|
||||
is_cape=config['is_cape'])
|
||||
static_dataset_train = StaticDataset(folder=config['train_dir'],
|
||||
signature=config['signature_static'],
|
||||
resolutions=[config['resolution']],
|
||||
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=[config['resolution']],
|
||||
in_memory=config['dataset_in_memory'],
|
||||
use_one_hot=config['use_one_hot'],
|
||||
use_no_orient=config['remove_global_orientation'],
|
||||
frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None,
|
||||
is_cape=config['is_cape'])
|
||||
static_dataset_valid = StaticDataset(folder=config['valid_dir'],
|
||||
signature=config['signature_static'],
|
||||
resolutions=[config['resolution']],
|
||||
in_memory=True,
|
||||
is_cape=config['is_cape'])
|
||||
|
||||
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 = CVAE(config)
|
||||
|
||||
optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
|
||||
optimizer = optim.Adam(model.parameters(), lr=config['lr'])
|
||||
_MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
|
||||
balancing_activated_step = 0
|
||||
g_balancing_coeff = config['starting_balancing_coeff']
|
||||
|
||||
# sample('checkpoints/cvae_13')
|
||||
# test()
|
||||
|
||||
ckpt = tf.train.Checkpoint(model=model)
|
||||
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/post/' + config['name'], max_to_keep=20)
|
||||
ckpt_saver = CheckpointSaver('checkpoints/iccv/' + config['name'], top_n=5)
|
||||
|
||||
if config['pretrained_model'] != '':
|
||||
load_model(model, config['pretrained_model'])
|
||||
|
||||
# load_model(model, 'checkpoints/' + config['name'])
|
||||
|
||||
valid_iterator = iter(dataset_valid)
|
||||
step = 0
|
||||
for batch in dataset_train:
|
||||
batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
|
||||
|
||||
train_loss = train_step(batch)
|
||||
train_accumulator.update(train_loss)
|
||||
|
||||
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)
|
||||
valid_accumulator.update(valid_loss)
|
||||
|
||||
|
||||
if train_accumulator.get()['train/euclid_error'] < (config['balancing_activation_limit'] if 'balancing_activation_limit' in config.keys() else 0.017):
|
||||
if balancing_activated_step == 0:
|
||||
balancing_activated_step = step
|
||||
g_balancing_coeff = g_balancing_coeff + 1 / 10000
|
||||
|
||||
|
||||
if step % 1000 == 0 or (step < 1000 and step % 100 == 0):
|
||||
to_log = { **train_accumulator.get(), **valid_accumulator.get(), **{ '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)) } }
|
||||
|
||||
to_log = { **to_log, **{ 'train/balancing_coeff': g_balancing_coeff } }
|
||||
|
||||
wandb.log(to_log, step = step)
|
||||
train_accumulator.reset()
|
||||
valid_accumulator.reset()
|
||||
|
||||
if step % 5000 == 0:
|
||||
manager.save(checkpoint_number=step)
|
||||
|
||||
print(step)
|
||||
|
||||
step += 1
|
||||
|
||||
train()
|
||||
Reference in New Issue
Block a user