luni/cvpr
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update main script

Browse Source
This commit is contained in:
luni
2022-10-29 20:08:38 +00:00
parent 89fca608a6
commit 7a783803ef
3 changed files with 247 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cvae.py
+127 -70
View File
@@ -1,5 +1,7 @@
import os
from configs.config_cvae import config
import sys
from configs.config_cvae_test import config
os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu']
import tensorflow as tf
@@ -18,23 +20,23 @@ if gpus:
import time
import argparse
import wandb
import tqdm
import random
import numpy as np
import scipy as sp
from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces
import plotly.graph_objects as go
import plotly.express as ex
from PIL import Image
from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, plot_3d_collision
from postprocessing import fix_collision
if config['is_skirt']:
from losses import edge_loss_skirt as edge_loss
else:
from losses import edge_loss
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 uv_mask_loss, bend_loss, kl_loss
from losses import collision_ratio, kl_loss #, concept_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
@@ -44,7 +46,7 @@ from models.cvae_model import CVAE
def init_wandb():
run = wandb.init(project='cvae', name=config['name'], notes=config['notes'])
run = wandb.init(project='cvae', name=config['name'], notes=config['notes'], dir='/home/workspace/local-data/temp')
artifact = wandb.Artifact('code', type='code')
artifact.add_file('cvae.py')
artifact.add_file('models/cvae_model.py')
@@ -55,15 +57,12 @@ def init_wandb():
artifact.add_file('models/cond_encoder.py')
artifact.add_file('dataset.py')
artifact.add_file('convnext/models/convnext_tf.py')
config_file_name = [key for key in sys.modules.keys() if key.startswith('configs.')]
assert len(config_file_name) == 1
artifact.add_file('/'.join(config_file_name[0].split('.')) + '.py')
run.log_artifact(artifact)
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'])
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
uv2mesh = UV2Mesh(res=256, is_skirt=config['is_skirt'], is_adaptive=False)
def kl_loss(mean, logvar):
@@ -94,23 +93,27 @@ def train_step(batch):
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']))
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - 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 + (e_loss + c_loss) * config['reg_loss_coeff']
reconstr_loss = (l2_loss + l2_mesh_loss) * config['l2_coeff'] + (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, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1)))
# 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']))
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/euclid_error': metric, 'train/ms_ssim': ms_ssim,
'train/reconstr_loss': reconstr_loss,
return { 'train/loss': loss, 'train/edge_loss': e_loss, 'train/collision_loss': c_loss, 'train/euclid_error': metric,
'train/reconstr_loss': reconstr_loss,
'train/mean': mean, 'train/logvar': logvar, 'train/kl_loss': kl, 'train/var': np.e ** logvar,
'train/l2_loss': l2_loss }
'train/l2_loss': l2_loss, 'train/l2_mesh_loss': l2_mesh_loss
# 'train/ms_ssim': ms_ssim, 'train/collision_ratio': c_ratio,
}
@tf.function
@@ -132,9 +135,54 @@ def valid_step(batch):
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']))
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - 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 + (e_loss + c_loss) * config['reg_loss_coeff']
reconstr_loss = (l2_loss + l2_mesh_loss) * config['l2_coeff'] + (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, 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']))
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/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar,
# 'valid/ms_ssim': ms_ssim, 'valid/collision_ratio': c_ratio,
}
@tf.function
def test_step(batch):
pred, mean, logvar = model([batch['uv_unposed'], batch['uv_static'], batch['uv_body_posed'], batch['uv_curvature'], batch['uv_mask']], training=False)
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)
mesh_pred_posed_fixed = fix_collision(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask'])
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)
# is the output already masked?
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']))
l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - 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 + l2_mesh_loss) * config['l2_coeff'] + (e_loss + c_loss) * config['reg_loss_coeff']
loss = reconstr_loss + g_balancing_coeff * kl
mean = tf.reduce_mean(mean)
@@ -142,10 +190,14 @@ def valid_step(batch):
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'])
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'])
c_ratio = tf.reduce_mean(collision_ratio(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']))
return { 'valid/loss': loss, 'valid/edge_loss': e_loss, 'valid/collision_loss': c_loss, 'valid/euclid_error': metric, 'valid/ms_ssim': ms_ssim,
'train/reconstr_loss': reconstr_loss,
'valid/mean': mean, 'valid/logvar': logvar, 'valid/kl_loss': kl, 'valid/var': np.e ** logvar }
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):
@@ -175,18 +227,23 @@ def plot_everything(batch: dict, type: str):
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()
mesh_posed_fixed = fix_collision(mesh_posed, body, mask).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))]
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(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) }
figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision[i], collision_fixed[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 } }
return { **figs, **figs_coll, **{ type + '/images': imgs, type + '/mean_hist': mean_hist, type + '/logvar_hist': logvar_hist } }
def sample(folder):
@@ -219,8 +276,6 @@ def sample(folder):
mesh_posed_zero = smpl.run_garment(pose, shape, mesh_pred_zero).numpy()
meshes = []
meshes.append(go.Mesh3d(
# 8 vertices of a cube
@@ -314,7 +369,10 @@ def sample(folder):
def test():
load_model(model, 'checkpoints/' + config['name'].split('_')[0])
str_split = config['name'].split('_')
test_idx = str_split.index('test')
checkpoint_name = '_'.join(str_split[:test_idx])
load_model(model, 'checkpoints/' + checkpoint_name)
dataset_test = factory.get_dataset(folder=config['test_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False, do_repeat=False)
static_dataset_test = StaticDataset(folder=config['test_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=False)
@@ -322,23 +380,20 @@ def test():
step = 0
losses = []
for batch in dataset_test:
for batch in tqdm.tqdm(dataset_test):
batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
test_loss = valid_step(batch)
test_loss = test_step(batch)
losses.append(test_loss)
to_log = { **{ 'current_step': step }, **test_loss }
if step % 100 == 0:
if step % 1000 == 0:
figs = plot_everything(batch, 'test')
to_log = { **to_log, **figs }
wandb.log(to_log, step = step)
if step > 30:
break
print(step)
# print(step)
step += 1
# averages = dict()
@@ -362,20 +417,19 @@ def test():
if __name__ == '__main__':
init_wandb()
allow_memory_growth()
# init_wandb()
parser = argparse.ArgumentParser(description='')
parser.add_argument('--name', type=str)
args = vars(parser.parse_args())
smpl = SMPL()
smpl = SMPL(use_one_hot=config['use_one_hot'])
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'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=config['dataset_in_memory'])
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']], in_memory=config['dataset_in_memory'], use_one_hot=config['use_one_hot'])
static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=True)
dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=config['dataset_in_memory'])
dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=config['dataset_in_memory'], use_one_hot=config['use_one_hot'])
static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']], in_memory=True)
model = CVAE(config)
@@ -385,43 +439,46 @@ if __name__ == '__main__':
g_balancing_coeff = config['starting_balancing_coeff']
# sample('checkpoints/cvae_13')
test()
# test()
# ckpt = tf.train.Checkpoint(model=model)
# manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
ckpt = tf.train.Checkpoint(model=model)
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20)
# 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']))
if config['pretrained_model'] != '':
load_model(model, config['pretrained_model'])
# train_loss = train_step(batch)
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']))
# 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)
train_loss = train_step(batch)
# to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
# if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
# train_figs = plot_everything(batch, 'train')
# valid_figs = plot_everything(data_valid, 'valid')
# to_log = { **to_log, **train_figs, **valid_figs }
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)
# if step % 10000 == 0:
# manager.save(checkpoint_number=step)
# if step == 0:
# to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } }
to_log = { **train_loss, **valid_loss, **{ 'current_step': step} }
if step % 5000 == 0 or (step < 5000 and step % 500 == 0):
train_figs = plot_everything(batch, 'train')
valid_figs = plot_everything(data_valid, 'valid')
to_log = { **to_log, **train_figs, **valid_figs }
# if train_loss['train/euclid_error'] < 0.01:
# if balancing_activated_step == 0:
# balancing_activated_step = step
# g_balancing_coeff = g_balancing_coeff + 1 / 15000
if step % 10000 == 0:
manager.save(checkpoint_number=step)
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 } }
if train_loss['train/euclid_error'] < 0.019:
if balancing_activated_step == 0:
balancing_activated_step = step
g_balancing_coeff = g_balancing_coeff + 1 / 10000
to_log = { **to_log, **{ 'train/balancing_coeff': g_balancing_coeff } }
# wandb.log(to_log, step = step)
wandb.log(to_log, step = step)
# print(step)
print(step)
# step += 1
step += 1