380 lines
17 KiB
Python
380 lines
17 KiB
Python
import os
|
|
from configs.config_cvae import config
|
|
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)
|
|
|
|
import time
|
|
import argparse
|
|
import wandb
|
|
import random
|
|
import numpy as np
|
|
import scipy as sp
|
|
from custom_utils.custom_utils import UV2Mesh, maskFacesBatch, _maskFaces
|
|
import plotly.graph_objects as go
|
|
import plotly.express as ex
|
|
from PIL import Image
|
|
|
|
from utils import str_to_bool
|
|
from tf_utils import check_tf_version, allow_memory_growth, split_gpu_for_testing
|
|
from load_models import load_generator, load_discriminator
|
|
from losses import d_logistic, d_logistic_r1_reg, g_logistic_non_saturating, g_logistic_ns_pathreg, edge_loss, uv_mask_loss, bend_loss
|
|
# from losses import collision_penalty as collision_penalty
|
|
from losses import collision_loss as collision_penalty
|
|
from custom_utils.custom_utils import batch_to_dict, load_model, plot_3d
|
|
from dataset import DatasetFactory, StaticDataset
|
|
from custom_utils.smpl import SMPL
|
|
from models.cvae_model import CVAE
|
|
|
|
|
|
def init_wandb():
|
|
run = wandb.init(project='vae', name=config['name'],
|
|
notes=config['notes'])
|
|
artifact = wandb.Artifact('code', type='code')
|
|
artifact.add_file('cvae.py')
|
|
artifact.add_file('models/cvae_model.py')
|
|
artifact.add_file('losses.py')
|
|
artifact.add_file('configs/config_base.py')
|
|
artifact.add_file('configs/config_cvae.py')
|
|
artifact.add_file('models/base.py')
|
|
artifact.add_file('models/cond_encoder.py')
|
|
artifact.add_file('dataset.py')
|
|
artifact.add_file('convnext/models/convnext_tf.py')
|
|
run.log_artifact(artifact)
|
|
|
|
uv2mesh = UV2Mesh(res=256)
|
|
|
|
|
|
def log_normal_pdf(sample, mean, logvar, raxis=1):
|
|
log2pi = tf.math.log(2. * np.pi)
|
|
res = tf.reduce_sum(-.5 * ((sample - mean) ** 2. * tf.exp(-logvar) + logvar + log2pi), axis=raxis)
|
|
return res
|
|
|
|
|
|
def kl_loss(mean, logvar):
|
|
kl_loss = 1 + logvar - tf.square(mean) - tf.exp(logvar)
|
|
kl_loss = tf.reduce_mean(kl_loss)
|
|
kl_loss *= -0.5
|
|
return kl_loss
|
|
|
|
|
|
@tf.function
|
|
def train_step(batch):
|
|
|
|
with tf.GradientTape() as tape:
|
|
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
|
|
|
|
pred, mean, logvar, z = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], uv_curvature, batch['uv_mask']],
|
|
training=True, use_mask=True)
|
|
|
|
mesh_pred = uv2mesh(pred)
|
|
mesh_orig = batch['mesh_unposed']
|
|
|
|
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)
|
|
|
|
e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
|
c_loss = tf.reduce_mean(collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
|
|
l1_loss = tf.reduce_sum(tf.reduce_sum((tf.math.abs(batch['uv_unposed'] - pred)), axis=-1) * batch['uv_mask'], axis=[1, 2])
|
|
l2_loss = 1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - pred) ** 2), axis=-1) * batch['uv_mask'], axis=[1, 2])
|
|
# ms_ssim = tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) + 1, tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1, max_val=2)
|
|
ms_ssim = tf.image.ssim_multiscale(pred + 1, batch['uv_unposed'] + 1, max_val=3, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))
|
|
# ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale((tf.transpose(pred, [0,2,3,1]) + 1) * batch['uv_mask'][:,:,:,tf.newaxis], (tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1) * batch['uv_mask'][:,:,:,tf.newaxis], max_val=2))
|
|
|
|
reconstr_loss = l2_loss
|
|
reconstr_loss = tf.reduce_mean(reconstr_loss)
|
|
kl = kl_loss(mean, logvar)
|
|
loss = reconstr_loss + balancing_coeff * kl
|
|
ms_ssim = tf.reduce_mean(ms_ssim)
|
|
l1_loss = tf.reduce_mean(l1_loss)
|
|
l2_loss = tf.reduce_mean(l2_loss)
|
|
mean = tf.reduce_mean(mean)
|
|
logvar = tf.reduce_mean(logvar)
|
|
|
|
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
|
gradients = tape.gradient(loss, model.trainable_variables)
|
|
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
|
|
return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/l1_loss': l1_loss, 'train/euclid_error': metric, 'train/ms_ssim': ms_ssim,
|
|
'train/reconstr_loss': reconstr_loss,
|
|
'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/reconst_loss_norm': reconstr_loss / (2 * (gamma ** 2)), 'train/var': np.e ** logvar,
|
|
'train/reg_coeff': reg_coeff, 'train/l2_loss': l2_loss }
|
|
|
|
|
|
|
|
@tf.function
|
|
def valid_step(batch):
|
|
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
|
|
pred, mean, logvar, z = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], uv_curvature, batch['uv_mask'], batch['uv_shaped_body']])
|
|
|
|
mesh_pred = uv2mesh(pred)
|
|
mesh_orig = batch['mesh_unposed']
|
|
e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
|
c_loss = 1e-2 * tf.reduce_mean(collision_penalty(mesh_pred, batch['mesh_body_posed'], batch['mesh_mask']))
|
|
l1_loss = tf.reduce_sum(tf.reduce_sum((tf.math.abs(tf.transpose(batch['uv_unposed'], [0,2,3,1]) - pred)), axis=-1) * batch['uv_mask'], axis=[1, 2])
|
|
b_loss = 0 #1e-3 * bend_loss(mesh_pred, smpl_faces, laplacian_loss, batch['mesh_mask'])
|
|
# ms_ssim = tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) + 1, tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1, max_val=2)
|
|
ms_ssim = tf.image.ssim_multiscale(pred + 1, tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1, max_val=3)
|
|
fft_loss = 0 #tf.reduce_sum(tf.math.abs(tf.signal.fft3d(tf.complex(pred, tf.zeros_like(pred))) - tf.signal.fft3d(tf.complex(tf.transpose(batch['uv_unposed'], [0,2,3,1]), tf.zeros_like(tf.transpose(batch['uv_unposed'], [0,2,3,1]))))), axis=[1,2,3])
|
|
# mesh_orig_2 = uv2mesh(batch['uv_unposed'])
|
|
metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
|
metric_2 = 0 #tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig_2 - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
|
|
|
reconstr_loss = l1_loss
|
|
kl = kl_loss(mean, logvar)
|
|
# loss = reconstr_loss / (2 * (gamma ** 2)) + kl
|
|
loss = reconstr_loss + balancing_coeff * kl
|
|
ms_ssim = tf.reduce_mean(ms_ssim)
|
|
l1_loss = tf.reduce_mean(l1_loss)
|
|
fft_loss = tf.reduce_mean(fft_loss)
|
|
b_loss = tf.reduce_mean(b_loss)
|
|
reconstr_loss = tf.reduce_mean(reconstr_loss)
|
|
mean = tf.reduce_mean(mean)
|
|
logvar = tf.reduce_mean(logvar)
|
|
|
|
return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/l1_loss': l1_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim,
|
|
'valid/fft_loss': fft_loss, 'valid/euclid_error_reconst': metric_2, 'train/bend_loss': b_loss, 'train/reconstr_loss': reconstr_loss,
|
|
'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar }
|
|
|
|
|
|
def plot_everything(batch: dict, type: str):
|
|
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
|
|
pred, mean, logvar, z = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], uv_curvature, batch['uv_mask']], training=False, use_mask=True)
|
|
|
|
mesh_pred = uv2mesh(pred).numpy()
|
|
mesh_orig = batch['mesh_unposed']
|
|
|
|
orig_img = batch['uv_unposed']
|
|
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)]
|
|
|
|
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])])
|
|
|
|
F = np.load("custom_utils/smpl_faces.npy")
|
|
mask = batch['mesh_mask'].numpy().astype(bool)
|
|
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])]
|
|
|
|
body = batch['mesh_body_posed'].numpy()
|
|
for i in range(body.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()
|
|
|
|
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))]
|
|
collision_faces = [np.concatenate((F, faces[i] + 14475), axis=0) for i in range(len(garment_posed))]
|
|
collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(garment_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(garment_posed))]
|
|
|
|
figs = { type + "/garment_" + str(i): plot_3d(gt[i], garment_unposed[i], faces[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
|
|
|
|
mean_hist = wandb.Histogram(sequence=mean.numpy().mean(axis=0), num_bins=model.latent_dim)
|
|
logvar_hist = wandb.Histogram(sequence=logvar.numpy().mean(axis=0), num_bins=model.latent_dim)
|
|
|
|
return { **figs, **{ 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, signature_dynamic))
|
|
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
|
|
nr_of_samples=2
|
|
|
|
pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples)
|
|
pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:]
|
|
pose, shape = 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((14475, 3)), F, mask)
|
|
|
|
pred_zero = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[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()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
init_wandb()
|
|
allow_memory_growth()
|
|
parser = argparse.ArgumentParser(description='')
|
|
parser.add_argument('--name', type=str)
|
|
args = vars(parser.parse_args())
|
|
|
|
batch_size = config['batch_size']
|
|
|
|
smpl = SMPL()
|
|
|
|
factory = DatasetFactory()
|
|
|
|
dataset_train = factory.get_dataset(folder=config['train_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']])
|
|
static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']])
|
|
dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'])
|
|
static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['signature_static'])
|
|
|
|
model = CVAE(config)
|
|
|
|
optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
|
|
balancing_coeff = config['starting_balancing_coeff']
|
|
reg_coeff = 1
|
|
valid_iterator = iter(dataset_valid)
|
|
gamma = 1
|
|
balancing_activated_step = 0
|
|
|
|
# sample('checkpoints/cvae_13')
|
|
|
|
ckpt = tf.train.Checkpoint(model=model)
|
|
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=3)
|
|
|
|
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)
|
|
|
|
# data_valid = valid_iterator.get_next()
|
|
# data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, signature_dynamic))
|
|
# valid_loss = valid_step(data_valid)
|
|
valid_loss = {}
|
|
|
|
to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
|
|
if step % 2500 == 0:
|
|
train_figs = plot_everything(batch, 'train')
|
|
# valid_figs = plot_everything(data_valid, 'valid')
|
|
valid_figs = {}
|
|
to_log = { **to_log, **train_figs, **valid_figs }
|
|
|
|
if step % 10000 == 0:
|
|
manager.save(checkpoint_number=step)
|
|
|
|
if train_loss['train/euclid_error'] < 0.01:
|
|
if balancing_activated_step == 0:
|
|
balancing_activated_step = step
|
|
balancing_coeff = balancing_coeff + 1 / 15000
|
|
|
|
to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
|
|
|
|
wandb.log(to_log, step = step)
|
|
|
|
print(step)
|
|
|
|
step += 1 |