cvae norm training
This commit is contained in:
+1
-1
@@ -51,7 +51,7 @@ from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary
|
||||
|
||||
|
||||
def init_wandb():
|
||||
run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/tmp', tags=config['tags'])
|
||||
run = wandb.init(project='iccv', 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.py')
|
||||
artifact.add_file('losses/losses.py')
|
||||
|
||||
@@ -0,0 +1,400 @@
|
||||
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())
|
||||
|
||||
config_module = importlib.import_module(args['config'])
|
||||
config = config_module.config
|
||||
if args['debug']:
|
||||
from configs.cvae_norm_1 import 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
|
||||
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_norm_model import CVAENorm
|
||||
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='iccv', 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_norm.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_norm_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_smpl_orig=config['is_cape'])
|
||||
|
||||
|
||||
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
|
||||
|
||||
|
||||
def train_step(batch):
|
||||
model.train()
|
||||
pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
|
||||
pred = pred * 1.1
|
||||
mesh_pred = uv2mesh(pred)
|
||||
|
||||
|
||||
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_normals'] - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_normals'] - mesh_pred) ** 2, axis=-1), axis=-1))
|
||||
ms_ssim = torch.mean(_MSSSIM(pred + 1.1, batch['uv_normals'] + 1.1))
|
||||
kl = kl_loss(mean, logvar)
|
||||
|
||||
reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim)
|
||||
loss = reconstr_loss + g_balancing_coeff * kl
|
||||
|
||||
optimizer.zero_grad()
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
model.eval()
|
||||
with torch.inference_mode():
|
||||
mean = torch.mean(mean)
|
||||
logvar = torch.mean(logvar)
|
||||
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_normals'] - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
|
||||
|
||||
return { 'train/loss': 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_mesh_loss': l2_mesh_loss,
|
||||
'train/ms_ssim': ms_ssim,
|
||||
}
|
||||
|
||||
|
||||
def valid_step(batch):
|
||||
model.eval()
|
||||
with torch.inference_mode():
|
||||
pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
|
||||
pred = pred * 1.1
|
||||
mesh_pred = uv2mesh(pred)
|
||||
|
||||
l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_normals'] - pred) ** 2), axis=-1), axis=[1, 2]))
|
||||
l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_pred - batch['mesh_normals']) ** 2, axis=-1), axis=-1))
|
||||
ms_ssim = torch.mean(_MSSSIM(pred + 1.1, batch['uv_static'] + 1.1))
|
||||
kl = kl_loss(mean, logvar)
|
||||
|
||||
reconstr_loss = l2_loss + l2_mesh_loss + (1 - ms_ssim)
|
||||
loss = reconstr_loss + g_balancing_coeff * kl
|
||||
|
||||
mean = torch.mean(mean)
|
||||
logvar = torch.mean(logvar)
|
||||
metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_normals'] - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask'])
|
||||
|
||||
|
||||
return { 'valid/loss': 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,
|
||||
}
|
||||
|
||||
|
||||
def plot_everything(batch: dict, type: str):
|
||||
model.eval()
|
||||
with torch.inference_mode():
|
||||
pred, mean, logvar = model([batch['uv_normals'], batch['uv_static'], batch['uv_body_posed'], batch['uv_mask']])
|
||||
|
||||
pred = pred * 1.1
|
||||
# mesh_pred = uv2mesh(pred).detach().cpu().numpy()
|
||||
|
||||
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])
|
||||
orig_img = (torch.permute(batch['uv_normals'], [0,2,3,1]) + 1.1) / 2.2
|
||||
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("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy")
|
||||
# mask = batch['mesh_mask'].cpu().numpy().astype(bool)
|
||||
|
||||
mean_hist = wandb.Histogram(sequence=mean.cpu().numpy().mean(axis=0))
|
||||
logvar_hist = wandb.Histogram(sequence=logvar.cpu().numpy().mean(axis=0))
|
||||
|
||||
return { **{ 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, config['signature_dynamic']))
|
||||
uv_normals = tf.one_hot(batch['uv_normals'], 7)
|
||||
nr_of_samples=2
|
||||
|
||||
pred = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[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((config['smpl_res'], 3)), F, mask)
|
||||
|
||||
pred_zero = model.sample_single(batch['uv_static'][0], batch['uv_body_posed'][0], uv_normals[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()
|
||||
|
||||
|
||||
|
||||
def test():
|
||||
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)
|
||||
|
||||
step = 0
|
||||
losses = []
|
||||
|
||||
for batch in tqdm.tqdm(dataset_test):
|
||||
batch = static_dataset_test.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
|
||||
|
||||
test_loss = test_step(batch)
|
||||
losses.append(test_loss)
|
||||
|
||||
to_log = { **{ 'current_step': step }, **test_loss }
|
||||
if step % 1000 == 0:
|
||||
figs = plot_everything(batch, 'test')
|
||||
to_log = { **to_log, **figs }
|
||||
|
||||
wandb.log(to_log, step = step)
|
||||
|
||||
# print(step)
|
||||
step += 1
|
||||
|
||||
# averages = dict()
|
||||
path_to_plotly_html = "temp/plotly_figure.html"
|
||||
|
||||
histograms = dict()
|
||||
for key in test_loss.keys():
|
||||
accumulated = [losses[i][key].numpy() for i in range(len(losses))]
|
||||
fig = ex.histogram(accumulated, title='Average: ' + str(np.asarray(accumulated).mean()))
|
||||
fig.write_html(path_to_plotly_html, auto_play = False)
|
||||
|
||||
histograms['all/' + key.split('/')[-1] + '_hist'] = wandb.Html(path_to_plotly_html)
|
||||
# averages['all/' + key.split('/')[-1] + '_avg'] = np.asarray(accumulated).mean()
|
||||
|
||||
|
||||
|
||||
wandb.log({ **histograms }, step = step)
|
||||
wandb.finish()
|
||||
pass
|
||||
|
||||
|
||||
|
||||
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)
|
||||
|
||||
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)) } }
|
||||
|
||||
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'] if 'balancing_activation_limit' in config.keys() else 0.017):
|
||||
g_balancing_coeff += 1 / 10000
|
||||
|
||||
if step % 10000 == 0:
|
||||
ckpt_saver(model, step, optimizer, None)
|
||||
|
||||
step += 1
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if not args['debug']:
|
||||
init_wandb()
|
||||
|
||||
smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device'])
|
||||
skirt_modifier = '_skirt' if config['is_skirt'] else ''
|
||||
|
||||
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 = CVAENorm(config)
|
||||
|
||||
optimizer = optim.Adam(model.parameters(), lr=config['lr'])
|
||||
_MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3)
|
||||
g_balancing_coeff = config['starting_balancing_coeff']
|
||||
|
||||
ckpt_saver = CheckpointSaver('checkpoints/iccv/' + config['name'], top_n=5)
|
||||
|
||||
step = 0
|
||||
if config['pretrained_model'] != '':
|
||||
step = load_model(model, config['pretrained_model'])
|
||||
|
||||
if not args['debug']:
|
||||
# model = torch.compile(model)
|
||||
wandb.watch(model, log='all', log_freq=10000, log_graph=True)
|
||||
|
||||
train()
|
||||
Reference in New Issue
Block a user