539 lines
24 KiB
Python
539 lines
24 KiB
Python
import os
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
|
|
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
|
|
from tensorboardX import SummaryWriter
|
|
import plotly.graph_objects as go
|
|
import plotly.express as ex
|
|
|
|
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 convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block
|
|
from stylegan2_ae.generator import Generator
|
|
from custom_utils.graph_utils import Reconstructor_V4_Decoder as GNNDecoder, sparse_to_tensor
|
|
from custom_utils.graph_utils import Reconstructor_v2 as SimpleReconstructor
|
|
from dataset import DatasetFactory, StaticDataset
|
|
from custom_utils.custom_utils import batch_to_dict, plot_3d
|
|
from custom_utils.smpl import SMPL
|
|
from auto_encoder_body import AutoEncoder as BodyAE
|
|
from auto_encoder_curv import AutoEncoder as CurvatureAE
|
|
from auto_encoder_static import AutoEncoder as StaticAE
|
|
from cvae_curv import CVAE as CurvatureVAE
|
|
|
|
|
|
name='cvae_vae_1'
|
|
def init_wandb():
|
|
run = wandb.init(project='vae', name=name,
|
|
notes='learn offsets. smaller flattened latent vectors. with 25-85k pretraining. smaller batchsize. fixed balancing of reconst and kl loss for baseline.\
|
|
new implementation for kl loss. no lr schedule. 25 jumpsuits, average reconst_loss before calculation, linearly increasing balancing, up to 1000 from 250.\
|
|
offsets over average unposed garment. gamma balancing. remove global orientation (in posed body input and in pose_shape parameters. \
|
|
rebalanced l1 loss. retrained body encoder with deoriented bodies \
|
|
')
|
|
artifact = wandb.Artifact('code', type='code')
|
|
artifact.add_file('cvae.py')
|
|
artifact.add_file('dataset.py')
|
|
artifact.add_file('losses.py')
|
|
artifact.add_file('convnext/models/convnext_tf.py')
|
|
run.log_artifact(artifact)
|
|
|
|
uv2mesh = UV2Mesh(res=256)
|
|
|
|
|
|
|
|
class Bottleneck(tf.keras.Model):
|
|
|
|
def __init__(self, dim):
|
|
super(Bottleneck, self).__init__()
|
|
|
|
self.bottleneck = tf.keras.Sequential(
|
|
[Block(dim=dim, drop_path=0,
|
|
layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
|
|
)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.bottleneck(x, training=training)
|
|
|
|
return x
|
|
|
|
|
|
class Encoder(tf.keras.Model):
|
|
|
|
def __init__(self, latent_dim):
|
|
super(Encoder, self).__init__()
|
|
|
|
self.encoder = ConvNeXt(depths=[3, 3, 9, 3], dims=[32, 64, 128, 256], include_top=False)
|
|
self.flatten = tf.keras.layers.Flatten()
|
|
self.mean = tf.keras.layers.Dense(latent_dim)
|
|
self.log_var = tf.keras.layers.Dense(latent_dim)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.encoder(x)
|
|
x = self.flatten(x)
|
|
mean = self.mean(x)
|
|
log_var = self.log_var(x)
|
|
|
|
return mean, log_var
|
|
|
|
|
|
class Decoder(tf.keras.Model):
|
|
|
|
def __init__(self):
|
|
super(Decoder, self).__init__()
|
|
|
|
self.dense = tf.keras.layers.Dense(16 * 8 * 80)
|
|
self.reshape = tf.keras.layers.Reshape((16, 8, 80))
|
|
self.decoder = ConvNeXtReverse(depths=list(reversed([3, 3, 9, 3])), dims=list(reversed([256, 128, 64, 16])))
|
|
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.dense(x)
|
|
x = self.reshape(x)
|
|
x = self.decoder(x)
|
|
|
|
return x
|
|
|
|
|
|
class CVAE(tf.keras.Model):
|
|
|
|
def __init__(self, latent_dim=128):
|
|
super(CVAE, self).__init__()
|
|
self.latent_dim = latent_dim
|
|
|
|
model : StaticAE = StaticAE()
|
|
load_model(model, 'checkpoints/ae_static_3')
|
|
self.static_enc = tf.keras.Sequential([model.encoder, model.bottleneck])
|
|
self.static_enc.trainable = False
|
|
|
|
model : BodyAE = BodyAE()
|
|
load_model(model, 'checpoints/ae_body_5')
|
|
self.body_enc = tf.keras.Sequential([model.encoder, model.bottleneck])
|
|
self.body_enc.trainable = False
|
|
|
|
model : CurvatureAE = CurvatureVAE()
|
|
load_model(model, 'checpoints/cvae_curv_1_3')
|
|
self.curv_gen = model
|
|
self.curv_gen.trainable = False
|
|
|
|
self.encoder = Encoder(latent_dim)
|
|
self.decoder = Decoder()
|
|
|
|
|
|
# @tf.function
|
|
def sample(self, uv_template, uv_body_posed, uv_curv, uv_mask, eps=None):
|
|
if eps is None:
|
|
eps = tf.random.normal(shape=(4, self.latent_dim))
|
|
|
|
uv_template = tf.tile(tf.transpose(uv_template, [1,2,0])[tf.newaxis,:,:,:], [4,1,1,1])
|
|
uv_body_posed = tf.tile(tf.transpose(uv_body_posed, [1,2,0])[tf.newaxis,:,:,:], [4,1,1,1])
|
|
uv_curv = tf.tile(uv_curv[tf.newaxis,:,:,:], [4,1,1,1])
|
|
uv_mask = tf.tile(uv_mask[tf.newaxis,:,:], [4,1,1])
|
|
|
|
# uv_template, uv_body_posed = tf.transpose(uv_template, [0,2,3,1]), tf.transpose(uv_body_posed, [0,2,3,1])
|
|
z_static = self.static_enc(uv_template)
|
|
z_body = self.body_enc(uv_body_posed)
|
|
z_curv = self.curv_gen(uv_curv)
|
|
|
|
z_cond = tf.concat([z_static, z_body, z_curv], axis=-1)
|
|
z = tf.concat([eps, z_cond], axis=-1)
|
|
|
|
x = self.decoder(z)
|
|
x = x + avg_jumpsuit[tf.newaxis,:,:,:]
|
|
x = x * uv_mask[:,:,:,tf.newaxis]
|
|
|
|
return x
|
|
|
|
|
|
def reparameterize(self, mean, logvar):
|
|
eps = tf.random.normal(shape=mean.shape)
|
|
return eps * tf.exp(logvar * .5) + mean
|
|
|
|
|
|
def decode(self, z, apply_sigmoid=False):
|
|
logits = self.decoder(z)
|
|
if apply_sigmoid:
|
|
probs = tf.sigmoid(logits)
|
|
return probs
|
|
return logits
|
|
|
|
|
|
def call(self, inputs, training=None):
|
|
uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_shaped_body = inputs
|
|
uv_unposed, uv_template, uv_body_posed = tf.transpose(uv_unposed, [0,2,3,1]), tf.transpose(uv_template, [0,2,3,1]), tf.transpose(uv_body_posed, [0,2,3,1])
|
|
z_static = self.static_enc(uv_template)
|
|
z_body = self.body_enc(uv_body_posed)
|
|
z_curv = self.curv_gen.sample(uv_template, uv_body_posed, uv_mask)
|
|
|
|
x = tf.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], axis=-1)
|
|
|
|
mean, logvar = self.encoder(x)
|
|
z = self.reparameterize(mean, logvar)
|
|
z = tf.concat([z, z_static, z_body, z_curv], axis=-1)
|
|
x = self.decoder(z)
|
|
|
|
|
|
# x = tf.transpose(x, [0,3,1,2])
|
|
# x = x * uv_mask[:,tf.newaxis,:,:]
|
|
# x = tf.image.resize(x, (512, 256), tf.image.ResizeMethod.LANCZOS5)
|
|
# x = x + tf.transpose(uv_shaped_body, [0,2,3,1])
|
|
x = x + avg_jumpsuit[tf.newaxis,:,:,:]
|
|
x = x * uv_mask[:,:,:,tf.newaxis]
|
|
|
|
return x, mean, logvar, z
|
|
|
|
|
|
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'], batch['uv_shaped_body']])
|
|
|
|
mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2]))
|
|
mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred)
|
|
mesh_orig = batch['mesh_unposed']
|
|
|
|
|
|
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(tf.transpose(batch['uv_unposed'], [0,2,3,1]) - pred)), 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, tf.transpose(batch['uv_unposed'], [0,2,3,1]) + 1, max_val=3)
|
|
# 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))
|
|
rfft_loss = 0 #tf.reduce_mean(tf.reduce_sum(tf.math.abs(tf.signal.rfft3d(pred) - tf.signal.rfft3d(batch['uv_unposed'])), axis=[1,2,3]))
|
|
fft_loss = 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])
|
|
fft_loss_pc, fft_loss_pc_low, fft_loss_pc_high = 0,0,0 #fft_loss_per_channel(pred, batch['uv_unposed'])
|
|
tv_loss = tf.image.total_variation(pred)
|
|
|
|
reconstr_loss = l1_loss / 4
|
|
reconstr_loss = tf.reduce_mean(reconstr_loss) + reg_coeff *(e_loss + c_loss)
|
|
# logpx_z = -reconstr_loss
|
|
# logpz = log_normal_pdf(z[:,:model.latent_dim], 0., 0.)
|
|
# logqz_x = log_normal_pdf(z[:,:model.latent_dim], mean, logvar)
|
|
# loss = -tf.reduce_mean(logpx_z + balancing_coeff * (logpz - logqz_x))
|
|
kl = kl_loss(mean, logvar)
|
|
loss = reconstr_loss / (2 * (gamma ** 2)) + balancing_coeff * 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)
|
|
tv_loss = tf.reduce_mean(tv_loss)
|
|
mean = tf.reduce_mean(mean)
|
|
logvar = tf.reduce_mean(logvar)
|
|
|
|
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 = 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'])
|
|
euclid_posed = 0 # tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_skinned - batch['mesh_posed']) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask'])
|
|
gradients = tape.gradient(loss, model.trainable_variables)
|
|
# gradients = [tf.clip_by_norm(g, 1.0) for g in gradients]
|
|
# gradients = [tf.clip_by_value(g, -1.0, 1.0) for g in gradients]
|
|
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/fft_loss': fft_loss, 'train/euclid_error_reconst': metric_2, 'train/rfft_loss': rfft_loss, 'train/fft_oc_low': fft_loss_pc_low, 'train/fft_pc_high': fft_loss_pc_high,
|
|
'train/fft_loss_per_channel': fft_loss_pc, 'train/euclid_error_posed': euclid_posed, 'train/reconstr_loss': reconstr_loss, 'train/tv_loss': tv_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 }
|
|
|
|
|
|
|
|
@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(tf.transpose(pred, [0,3,1,2]))
|
|
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
|
|
# logpx_z = -reconstr_loss
|
|
# logpz = log_normal_pdf(z[:,:model.latent_dim], 0., 0.)
|
|
# logqz_x = log_normal_pdf(z[:,:model.latent_dim], mean, logvar)
|
|
# loss = -tf.reduce_mean(logpx_z + balancing_coeff * (logpz - logqz_x))
|
|
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'], batch['uv_shaped_body']])
|
|
|
|
mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2]))
|
|
mesh_orig = batch['mesh_unposed']
|
|
|
|
orig_img = tf.transpose(batch['uv_unposed'], [0,2,3,1])
|
|
uv_static_img = tf.transpose(batch['uv_static'], [0,2,3,1])
|
|
uv_body_posed_img = tf.transpose(batch['uv_body_posed'], [0,2,3,1])
|
|
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)]
|
|
|
|
F = np.load("custom_utils/smpl_faces.npy")
|
|
mask = batch['mesh_mask'].numpy().astype(bool)
|
|
garment_unposed, faces = maskFacesBatch(mesh_pred.numpy(), F, mask)
|
|
gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
|
|
|
|
body = batch['mesh_body_posed'].numpy()
|
|
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 load_model(model, checkpoint):
|
|
ckpt = tf.train.Checkpoint(model=model)
|
|
manager = tf.train.CheckpointManager(ckpt, checkpoint, max_to_keep=1)
|
|
ckpt.restore(manager.latest_checkpoint)
|
|
|
|
|
|
def sample(folder):
|
|
load_model(model,folder)
|
|
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)
|
|
|
|
pred = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0])
|
|
pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:]
|
|
pose, shape = tf.tile(pose[tf.newaxis,:], [4,1]), tf.tile(shape[tf.newaxis,:], [4,1])
|
|
|
|
mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2]))
|
|
mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy()
|
|
mesh_orig = batch['mesh_posed'][0].numpy()
|
|
|
|
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)
|
|
|
|
batch = 0
|
|
|
|
meshes = []
|
|
meshes.append(go.Mesh3d(
|
|
# 8 vertices of a cube
|
|
x=mesh_orig[mask,0],
|
|
y=mesh_orig[mask,1],
|
|
z=mesh_orig[mask,2],
|
|
# i, j and k give the vertices of triangles
|
|
i = faces[:,0],
|
|
j = faces[:,1],
|
|
k = faces[:,2]
|
|
))
|
|
|
|
for i in range(4):
|
|
x = mesh_posed[i][mask, :].copy()
|
|
x[:, 1] += 1 * (i + 1)
|
|
meshes.append(go.Mesh3d(
|
|
# 8 vertices of a cube
|
|
x=x[:,0],
|
|
y=x[:,1],
|
|
z=x[:,2],
|
|
# 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[:, 1] += 1 * i
|
|
meshes.append(go.Mesh3d(
|
|
# 8 vertices of a cube
|
|
x=x[:,0],
|
|
y=x[:,1],
|
|
z=x[:,2],
|
|
# 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=3, z=1))
|
|
fig.update_layout(
|
|
scene = dict(
|
|
xaxis = dict(nticks=4, range=[-1,1],),
|
|
yaxis = dict(nticks=4, range=[-1,5],),
|
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
|
)
|
|
|
|
fig.show()
|
|
|
|
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 = 12
|
|
|
|
smpl = SMPL()
|
|
|
|
factory = DatasetFactory()
|
|
signature_dynamic = { 'id': (),
|
|
'pose_shape': (72 + 11,),
|
|
# 'uv_posed': (3, 512, 256,),
|
|
'uv_body_posed': (3, 512, 256,),
|
|
'mesh_body_posed': (14475, 3,),
|
|
'mesh_posed': (14475, 3,),
|
|
'mesh_unposed': (14475, 3,),
|
|
'uv_unposed': (3, 512, 256,),
|
|
'uv_curvature': (512, 256),
|
|
}
|
|
signature_static = { 'uv_static': (3, 512, 256,),
|
|
# 'mesh_static': (14475, 3,),
|
|
'mesh_mask': (14475,),
|
|
'uv_mask': (512, 256,),
|
|
'uv_shaped_body': (3, 512, 256,),
|
|
}
|
|
|
|
dataset_train = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/train', batch_size=batch_size, signature=signature_dynamic)
|
|
static_dataset_train = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/train', signature=signature_static)
|
|
dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/valid', batch_size=batch_size, signature=signature_dynamic)
|
|
static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/valid', signature=signature_static)
|
|
|
|
|
|
model = CVAE()
|
|
|
|
|
|
# lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(0.0001, decay_steps=30000, decay_rate=0.1, staircase=False)
|
|
optimizer = tf.optimizers.Adam(learning_rate=0.0001)
|
|
balancing_coeff = 250
|
|
reg_coeff = 1
|
|
folder = 'models/ae_logs/'
|
|
valid_iterator = iter(dataset_valid)
|
|
gamma = 1
|
|
balancing_activated_step = 0
|
|
avg_jumpsuit = np.load('custom_data/jumpsuit_20_avg_uv.npy')
|
|
|
|
|
|
sample('checkpoints/cvae_10')
|
|
|
|
|
|
ckpt = tf.train.Checkpoint(model=model)
|
|
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + name, max_to_keep=3)
|
|
|
|
step = 0
|
|
for batch in dataset_train:
|
|
batch = static_dataset_train.expand_batch(batch_to_dict(batch, 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 + 1000 / 30000
|
|
if train_loss['train/euclid_error'] < 0.015:
|
|
reg_coeff = reg_coeff + 100 / 15000
|
|
# if step > 15000 and balancing_coeff <= 1e-3:
|
|
# balancing_coeff = 1e-2
|
|
# if step > 20000 and balancing_coeff <= 1e-3:
|
|
# balancing_coeff = 1e-2
|
|
# if step > 25000 and balancing_coeff <= 1e-2:
|
|
# balancing_coeff = 1e-1
|
|
# if step > 30000 and balancing_coeff <= 1e-1:
|
|
# balancing_coeff = 1
|
|
|
|
# gamma = 0.99 * gamma + 0.01 * train_loss['train/reconstr_loss']
|
|
|
|
to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } }
|
|
|
|
wandb.log(to_log, step = step)
|
|
|
|
print(step)
|
|
|
|
step += 1 |