262 lines
12 KiB
Python
262 lines
12 KiB
Python
import os
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = "3"
|
|
|
|
import time
|
|
import argparse
|
|
import wandb
|
|
import random
|
|
import cv2
|
|
import numpy as np
|
|
import tensorflow as tf
|
|
from custom_utils.custom_utils import UV2Mesh, maskFacesBatch
|
|
import plotly.graph_objects as go
|
|
import plotly.express as ex
|
|
|
|
from tf_utils import check_tf_version, allow_memory_growth
|
|
from losses import edge_loss, uv_mask_loss
|
|
from dataset import DatasetFactory, StaticDataset
|
|
from custom_utils.custom_utils import batch_to_dict
|
|
from custom_utils.smpl import SMPL
|
|
from models.ae_body_model import AutoEncoder, AutoEncoder128, AutoEncoder32
|
|
|
|
|
|
name='ae_body_8_d128'
|
|
def init_wandb():
|
|
run = wandb.init(project='vae', name=name,
|
|
notes='convnext + convnext, add dense with tanh at the end of reverse convnext, larger features. add lr scheduler. fft3d instead of rfft3d. \
|
|
fft2d per channel and separate for top and bottom. fft_loss, all data. added convnext block as bottleneck, same as before, added extra metric. \
|
|
. lowered learning rate because it goes to nan. shallow third stage. slower lr decay. with validation. higher lr rate.\
|
|
two more downscaling than up, so decoder output is resized wto final resolution\
|
|
larger batch_size.\
|
|
flattened bottleneck with 128 latent_dim\ remove global orientation\
|
|
fixed gender issue with deoriented bodies, again, aaand again\
|
|
trained on 100 garments\
|
|
remove multiplications with garment uv mask\
|
|
')
|
|
artifact = wandb.Artifact('code', type='code')
|
|
artifact.add_file('auto_encoder_body.py')
|
|
artifact.add_file('losses.py')
|
|
artifact.add_file('models/ae_body_model.py')
|
|
artifact.add_file('dataset.py')
|
|
artifact.add_file('convnext/models/convnext_tf.py')
|
|
run.log_artifact(artifact)
|
|
|
|
uv2mesh = UV2Mesh(res=256)
|
|
|
|
|
|
|
|
def plot_3d(mesh_gt, mesh_pred_unposed, faces, collision, collision_faces, collision_color):
|
|
mesh_pred_unposed[:,1] += 1
|
|
collision[:,1] += 2
|
|
fig = go.Figure(data=[
|
|
go.Mesh3d(
|
|
# 8 vertices of a cube
|
|
x=mesh_gt[:,0],
|
|
y=mesh_gt[:,1],
|
|
z=mesh_gt[:,2],
|
|
# i, j and k give the vertices of triangles
|
|
i = faces[:,0],
|
|
j = faces[:,1],
|
|
k = faces[:,2]
|
|
),
|
|
go.Mesh3d(
|
|
# 8 vertices of a cube
|
|
x=mesh_pred_unposed[:,0],
|
|
y=mesh_pred_unposed[:,1],
|
|
z=mesh_pred_unposed[:,2],
|
|
# i, j and k give the vertices of triangles
|
|
i = faces[:,0],
|
|
j = faces[:,1],
|
|
k = faces[:,2],
|
|
),
|
|
go.Mesh3d(
|
|
# 8 vertices of a cube
|
|
x=collision[:,0],
|
|
y=collision[:,1],
|
|
z=collision[:,2],
|
|
# i, j and k give the vertices of triangles
|
|
i = collision_faces[:,0],
|
|
j = collision_faces[:,1],
|
|
k = collision_faces[:,2],
|
|
vertexcolor=collision_color
|
|
)
|
|
])
|
|
|
|
fig.update_layout(scene_aspectmode='manual',
|
|
scene_aspectratio=dict(x=1, y=2, z=1))
|
|
fig.update_layout(
|
|
scene = dict(
|
|
xaxis = dict(nticks=4, range=[-1,1],),
|
|
yaxis = dict(nticks=4, range=[-1,3],),
|
|
zaxis = dict(nticks=4, range=[-1,1],),)
|
|
)
|
|
|
|
return fig
|
|
|
|
|
|
@tf.function
|
|
def train_step(batch):
|
|
|
|
with tf.GradientTape() as tape:
|
|
|
|
pred = model(batch['uv_body_posed' + resolution_modifier])
|
|
# pred = (pred + zero_body) * batch['mesh_mask'][:,:,tf.newaxis]
|
|
|
|
mesh_pred = uv2mesh(pred)
|
|
# mesh_pred = pred
|
|
mesh_orig = batch['mesh_body_posed']
|
|
|
|
|
|
e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, tf.ones_like(batch['mesh_mask'])))
|
|
c_loss = 0 # 1e-2 * tf.reduce_mean(collision_penalty(mesh_pred, batch['mesh_body_posed'], batch['mesh_mask']))
|
|
# l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['mesh_unposed'] - pred)), axis=-1) * batch['mesh_mask'])
|
|
l1_loss = tf.reduce_mean(tf.reduce_sum(((tf.math.abs(batch['uv_body_posed' + resolution_modifier] - pred) * uv_mask_body[tf.newaxis,tf.newaxis,:,:])), axis=1))
|
|
# ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.transpose(pred * uv_mask_body[tf.newaxis,tf.newaxis,:,:], [0,2,3,1]) + 1, tf.transpose(batch['uv_body_posed' + resolution_modifier] * uv_mask_body[tf.newaxis,tf.newaxis,:,:], [0,2,3,1]) + 1, max_val=2))
|
|
ms_ssim = tf.reduce_mean(tf.image.ssim(tf.transpose(pred * uv_mask_body[tf.newaxis,tf.newaxis,:,:], [0,2,3,1]) + 1, tf.transpose(batch['uv_body_posed' + resolution_modifier] * uv_mask_body[tf.newaxis,tf.newaxis,:,:], [0,2,3,1]) + 1, max_val=2))
|
|
fft_loss = 0 # tf.reduce_mean(tf.reduce_sum(tf.math.abs(tf.signal.fft3d(tf.complex(pred, tf.zeros_like(pred))) - tf.signal.fft3d(tf.complex(batch['uv_body_posed'], tf.zeros_like(batch['uv_body_posed'])))), axis=[1,2,3]))
|
|
# loss = fft_loss_pc # + e_loss + c_loss
|
|
loss = 1e3 * (1 - ms_ssim)
|
|
|
|
mesh_orig_2 = uv2mesh(batch['uv_body_posed' + resolution_modifier])
|
|
# mesh_skinned = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred)
|
|
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/euclid_error_posed': euclid_posed }
|
|
|
|
|
|
|
|
# UPDATE!
|
|
@tf.function
|
|
def valid_step(batch):
|
|
pred = model([batch['uv_body_posed'], batch['uv_mask']])
|
|
|
|
mesh_pred = uv2mesh(pred)
|
|
mesh_orig = batch['mesh_body_posed']
|
|
e_loss = 1e-2 * tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask']))
|
|
c_loss = 0 #1e-2 * tf.reduce_mean(collision_penalty(mesh_pred, batch['mesh_body_posed'], batch['mesh_mask']))
|
|
l1_loss = tf.reduce_mean(tf.reduce_sum((tf.math.abs(batch['uv_body_posed'] - pred)), axis=1) * batch['uv_mask'])
|
|
ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.transpose(pred, [0,2,3,1]) + 1, tf.transpose(batch['uv_body_posed'], [0,2,3,1]) + 1, max_val=2))
|
|
fft_loss = 0 #tf.reduce_mean(tf.reduce_sum(tf.math.abs(tf.signal.fft3d(tf.complex(pred, tf.zeros_like(pred))) - tf.signal.fft3d(tf.complex(batch['uv_body_posed'], tf.zeros_like(batch['uv_body_posed'])))), axis=[1,2,3]))
|
|
loss = 1e3 * (1 - ms_ssim)
|
|
mesh_orig_2 = uv2mesh(batch['uv_body_posed'])
|
|
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'])
|
|
|
|
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
|
|
}
|
|
|
|
|
|
def plot_everything(batch: dict, type: str):
|
|
|
|
pred = model(batch['uv_body_posed' + resolution_modifier])
|
|
|
|
mesh_pred = uv2mesh(pred)
|
|
mesh_orig = batch['mesh_body_posed']
|
|
|
|
orig_img = tf.transpose(batch['uv_body_posed' + resolution_modifier], [0,2,3,1])
|
|
pred_img = tf.transpose(pred, [0,2,3,1])
|
|
img = tf.concat((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)
|
|
garment_unposed, faces = mesh_pred.numpy(), F
|
|
# gt = [mesh_orig[i].numpy()[mask[i], :] for i in range(pred.shape[0])]
|
|
gt = [mesh_orig[i].numpy()[:, :] for i in range(pred.shape[0])]
|
|
|
|
body = uv2mesh(batch['uv_body_posed' + resolution_modifier]).numpy()
|
|
# 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])]
|
|
garment_posed = garment_unposed
|
|
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_faces = [np.concatenate((F, faces + 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, collision[i], collision_faces[i], collision_color[i]) for i in range(4) }
|
|
# 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) }
|
|
|
|
return { **figs, **{ type + '/images': imgs } }
|
|
|
|
|
|
|
|
def train():
|
|
valid_iterator = iter(dataset_valid)
|
|
|
|
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)
|
|
|
|
if step % 2500 == 0:
|
|
train_figs = plot_everything(batch, 'train')
|
|
valid_figs = {}#plot_everything(data_valid, 'valid')
|
|
wandb.log({ **train_loss, **valid_loss, **train_figs, **valid_figs }, step=step)
|
|
else:
|
|
wandb.log({ **train_loss, **valid_loss }, step=step)
|
|
|
|
if step % 10000 == 0:
|
|
manager.save(checkpoint_number=step)
|
|
|
|
|
|
|
|
print(step)
|
|
|
|
step += 1
|
|
|
|
if __name__ == '__main__':
|
|
init_wandb()
|
|
allow_memory_growth()
|
|
parser = argparse.ArgumentParser(description='')
|
|
parser.add_argument('--name', type=str)
|
|
args = vars(parser.parse_args())
|
|
|
|
smpl = SMPL()
|
|
# uv_mask_body = np.load('custom_utils/mask_256x512.npy')
|
|
# uv_mask_body = cv2.dilate(uv_mask_body.astype(np.float32), cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2)
|
|
|
|
uv_mask_body = tf.ones((128, 64))
|
|
resolution_modifier = '_128'
|
|
resolutions = [128]
|
|
|
|
factory = DatasetFactory()
|
|
signature_dynamic = { 'id': (),
|
|
'pose_shape': (72 + 11,),
|
|
'uv_body_posed_128': (3, 512, 256,),
|
|
'mesh_body_posed': (14475, 3,),
|
|
}
|
|
signature_static = {
|
|
'mesh_mask': (14475,),
|
|
# 'uv_mask': (512, 256,),
|
|
}
|
|
|
|
dataset_train = factory.get_dataset(folder='/home/workspace/local-data/train_100', batch_size=32, signature=signature_dynamic, use_filled=True, resolutions=resolutions)
|
|
static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static, use_filled=True, resolutions=resolutions)
|
|
dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/valid', batch_size=32, signature=signature_dynamic)
|
|
static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/valid', signature=signature_static)
|
|
|
|
# model = AutoEncoder()
|
|
# model = AutoEncoder32()
|
|
model = AutoEncoder128()
|
|
|
|
optimizer = tf.optimizers.Adam(learning_rate=0.0001)
|
|
folder = 'models/ae_logs/'
|
|
|
|
ckpt = tf.train.Checkpoint(model=model)
|
|
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + name, max_to_keep=3)
|
|
ckpt.restore(manager.latest_checkpoint)
|
|
|
|
train() |