379 lines
14 KiB
Python
379 lines
14 KiB
Python
import os
|
|
import time
|
|
import argparse
|
|
import wandb
|
|
import random
|
|
import numpy as np
|
|
import tensorflow as tf
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
|
|
|
|
|
|
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 collision_loss as collision_penalty
|
|
from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block, ConvNeXtReverseLabels
|
|
from dataset import DatasetFactory, StaticDataset
|
|
from custom_utils.custom_utils import batch_to_dict
|
|
from custom_utils.smpl import SMPL
|
|
|
|
name='ae_curvature_7_2'
|
|
testing = False
|
|
def init_wandb():
|
|
if not testing:
|
|
run = wandb.init(project='vae', name=name, notes='convnext + convnext, 16*8*32, ce loss. flattened latent dim of 128. trained on 100 garments. same as 7')
|
|
artifact = wandb.Artifact('code', type='code')
|
|
artifact.add_file('auto_encoder_curv.py')
|
|
artifact.add_file('dataset.py')
|
|
artifact.add_file('losses.py')
|
|
artifact.add_file('stylegan2_ae/layers/mapping_block.py')
|
|
artifact.add_file('convnext/models/convnext_tf.py')
|
|
run.log_artifact(artifact)
|
|
|
|
uv2mesh = UV2Mesh(res=256)
|
|
|
|
|
|
class DatasetSimple(tf.data.Dataset):
|
|
|
|
def _generator(folder):
|
|
# Opening the file
|
|
folder = folder.decode("utf-8")
|
|
uv_folder = os.path.join(folder, 'uv_posed')
|
|
frames = os.listdir(uv_folder)
|
|
random.shuffle(frames)
|
|
|
|
for frame in frames:
|
|
id, frame_nr = frame.split('.')[0].split('_')
|
|
mesh_mask = np.load(os.path.join(folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32)
|
|
uv_mask = np.load(os.path.join(folder, 'uv_mask', id + '.npz')); uv_mask=uv_mask['uv_mask']; uv_mask = uv_mask.astype(np.float32)
|
|
mesh_unposed = np.load(os.path.join(folder, 'mesh_unposed', id + '_' + frame_nr + '.npz')); mesh_unposed = mesh_unposed['mesh_unposed']
|
|
uv_unposed = np.load(os.path.join(folder, 'uv_unposed', id + '_' + frame_nr + '.npz')); uv_unposed = uv_unposed['uv_unposed']; uv_unposed = np.transpose(uv_unposed, [2, 0, 1])
|
|
|
|
yield uv_unposed, mesh_unposed, uv_mask, mesh_mask
|
|
|
|
def __new__(cls, folder, res=256):
|
|
return tf.data.Dataset.from_generator(
|
|
cls._generator,
|
|
output_signature = (tf.TensorSpec(shape = (3, res * 2, res,), dtype = tf.float32),
|
|
tf.TensorSpec(shape = (14475, 3,), dtype = tf.float32),
|
|
tf.TensorSpec(shape = (res * 2, res,), dtype = tf.float32),
|
|
tf.TensorSpec(shape = (14475,), dtype = tf.float32), ),
|
|
args=(folder, )
|
|
)
|
|
|
|
|
|
|
|
def filter_resolutions_featuremaps(resolutions, featuremaps, res):
|
|
index = resolutions.index(res)
|
|
filtered_resolutions = resolutions[:index + 1]
|
|
filtered_featuremaps = featuremaps[:index + 1]
|
|
return filtered_resolutions, filtered_featuremaps
|
|
|
|
|
|
def plot_3d(mesh_gt, mesh_pred, faces):
|
|
mesh_pred[:,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[:,0],
|
|
y=mesh_pred[:,1],
|
|
z=mesh_pred[:,2],
|
|
# i, j and k give the vertices of triangles
|
|
i = faces[:,0],
|
|
j = faces[:,1],
|
|
k = faces[:,2],
|
|
)
|
|
])
|
|
|
|
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
|
|
|
|
|
|
class Bottleneck(tf.keras.Model):
|
|
|
|
def __init__(self, dim, latent_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)]
|
|
)
|
|
self.flatten = tf.keras.layers.Flatten()
|
|
self.dense = tf.keras.layers.Dense(latent_dim)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.bottleneck(x)
|
|
x = self.flatten(x)
|
|
x = self.dense(x)
|
|
|
|
return x
|
|
|
|
|
|
class Decoder(tf.keras.Model):
|
|
|
|
def __init__(self, bottleneck_size, latent_dim):
|
|
super(Decoder, self).__init__()
|
|
|
|
self.dense = tf.keras.layers.Dense(16 * 8 * bottleneck_size)
|
|
self.reshape = tf.keras.layers.Reshape((16, 8, bottleneck_size))
|
|
self.decoder = ConvNeXtReverseLabels(depths=list(reversed([3, 3, 9, 3])), dims=list(reversed([bottleneck_size, 128, 64, 16])), nr_of_classes=7)
|
|
|
|
def call(self, inputs, training=None):
|
|
x = inputs
|
|
|
|
x = self.dense(x)
|
|
x = self.reshape(x)
|
|
x = self.decoder(x)
|
|
|
|
return x
|
|
|
|
|
|
class AutoEncoder(tf.keras.Model):
|
|
|
|
def __init__(self):
|
|
super(AutoEncoder, self).__init__()
|
|
|
|
|
|
bottleneck_size = 32
|
|
latent_dim = 128
|
|
self.decoder = Decoder(bottleneck_size, latent_dim)
|
|
|
|
self.bottleneck = Bottleneck(bottleneck_size, latent_dim)
|
|
|
|
self.encoder = ConvNeXt(depths=[3, 3, 9, 3], dims=[32, 64, 128, bottleneck_size], include_top=False)
|
|
|
|
|
|
|
|
def call(self, inputs, training=None):
|
|
x, uv_mask = inputs
|
|
|
|
# x = tf.transpose(x, [0,2,3,1])
|
|
x = self.encoder(x, training=training)
|
|
|
|
|
|
x = self.bottleneck(x, training=training)
|
|
|
|
x = self.decoder(x, training=training)
|
|
# x = tf.transpose(x, [0,3,1,2])
|
|
|
|
# x = x * uv_mask[:,:, tf.newaxis]
|
|
# x = x * uv_mask[:,tf.newaxis,:,:]
|
|
x = x * uv_mask[:,:,:,tf.newaxis]
|
|
|
|
return x
|
|
|
|
|
|
|
|
|
|
g_mean_iou = tf.keras.metrics.MeanIoU(num_classes=7)
|
|
def get_mean_iou(y_true, y_pred):
|
|
g_mean_iou.reset_state()
|
|
g_mean_iou.update_state(y_true, y_pred)
|
|
return g_mean_iou.result()
|
|
|
|
# https://github.com/NifTK/NiftyNet/blob/dev/niftynet/layer/loss_segmentation.py
|
|
def dice_dense(prediction, ground_truth, weight_map=None):
|
|
"""
|
|
Computing mean-class Dice similarity.
|
|
:param prediction: last dimension should have ``num_classes``
|
|
:param ground_truth: segmentation ground truth (encoded as a binary matrix)
|
|
last dimension should be ``num_classes``
|
|
:param weight_map:
|
|
:return: ``1.0 - mean(Dice similarity per class)``
|
|
"""
|
|
|
|
if weight_map is not None:
|
|
raise NotImplementedError
|
|
prediction = tf.cast(prediction, dtype=tf.float32)
|
|
ground_truth = tf.cast(ground_truth, dtype=tf.float32)
|
|
ground_truth = tf.reshape(ground_truth, prediction.shape)
|
|
# computing Dice over the spatial dimensions
|
|
reduce_axes = list(range(len(prediction.shape) - 1))
|
|
dice_numerator = 2.0 * tf.reduce_sum(
|
|
prediction * ground_truth, axis=reduce_axes)
|
|
dice_denominator = \
|
|
tf.reduce_sum(tf.square(prediction), axis=reduce_axes) + \
|
|
tf.reduce_sum(tf.square(ground_truth), axis=reduce_axes)
|
|
|
|
epsilon = 0.00001
|
|
|
|
dice_score = (dice_numerator + epsilon) / (dice_denominator + epsilon)
|
|
return tf.reduce_mean(dice_score)
|
|
|
|
|
|
@tf.function
|
|
def train_step(batch):
|
|
|
|
with tf.GradientTape() as tape:
|
|
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
|
|
|
|
pred = model([uv_curvature, batch['uv_mask']])
|
|
|
|
|
|
ce_uv_loss = scce(batch['uv_curvature'], pred)
|
|
ms_ssim = tf.reduce_mean(tf.image.ssim(pred, uv_curvature, max_val=1))
|
|
# ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(tf.math.argmax(pred, axis=-1, output_type=tf.dtypes.int32)[:,:,:,tf.newaxis], batch['uv_curvature'][:,:,:,tf.newaxis], max_val=7*2))
|
|
|
|
# loss = 1e3 * (1 - ms_ssim)
|
|
loss = ce_uv_loss
|
|
|
|
# mesh_pred = uv2mesh(tf.tile(tf.math.argmax(pred, axis=-1, output_type=tf.dtypes.int32)[:,:,:,tf.newaxis], [1,1,1,3]))[:,:,0]
|
|
# mesh_orig = tf.one_hot(batch['mesh_curvature'] + tf.cast(batch['mesh_mask'], tf.int32), 7)
|
|
# ce_mesh_loss = scce(mesh_orig, mesh_pred)
|
|
|
|
mean_iou = get_mean_iou(batch['uv_curvature'], tf.math.argmax(pred, axis=-1))
|
|
dice = dice_dense(pred, uv_curvature)
|
|
|
|
gradients = tape.gradient(loss, model.trainable_variables)
|
|
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
|
|
return { 'train/loss': loss, 'train/ce_uv_loss': ce_uv_loss, 'train/ssim': ms_ssim, 'train/mean_iou': mean_iou, 'train/dice': dice #'ce_mesh_loss': ce_mesh_loss
|
|
}
|
|
|
|
|
|
|
|
@tf.function
|
|
def valid_step(batch):
|
|
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
|
|
|
|
pred = model([uv_curvature, batch['uv_mask']])
|
|
|
|
ce_uv_loss = scce(batch['uv_curvature'], pred)
|
|
ms_ssim = tf.reduce_mean(tf.image.ssim(pred, uv_curvature, max_val=1))
|
|
loss = ce_uv_loss
|
|
|
|
mean_iou = get_mean_iou(batch['uv_curvature'], tf.math.argmax(pred, axis=-1))
|
|
dice = dice_dense(pred, uv_curvature)
|
|
|
|
return { 'valid/loss': loss, 'valid/ce_uv_loss': ce_uv_loss, 'valid/ssim': ms_ssim, 'valid/mean_iou': mean_iou, 'valid/dice': dice #'ce_mesh_loss': ce_mesh_loss
|
|
}
|
|
|
|
|
|
|
|
def train():
|
|
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)
|
|
data_valid = batch
|
|
|
|
to_log = { **train_loss, **valid_loss}
|
|
if step % 2500 == 0:
|
|
uv_curvature = tf.one_hot(data_valid['uv_curvature'], 7)
|
|
pred = model([uv_curvature, data_valid['uv_mask']])
|
|
|
|
orig_img = data_valid['uv_curvature']
|
|
pred_img = tf.math.argmax(pred, axis=-1, output_type=tf.dtypes.int32)
|
|
img = tf.concat((orig_img, pred_img), axis=2).numpy()
|
|
# imgs = { 'valid/images': [wandb.Image(img[i,:,:,np.newaxis] / 6.0) for i in range(4)] }
|
|
imgs = { 'train/images': [wandb.Image(img[i,:,:,np.newaxis] / 6.0) for i in range(4)] }
|
|
to_log = { **to_log, **imgs}
|
|
|
|
wandb.log(to_log, step=step)
|
|
print(step)
|
|
|
|
if step % 2500 == 0:
|
|
manager.save(checkpoint_number=step)
|
|
|
|
step += 1
|
|
|
|
|
|
def test():
|
|
ckpt.restore(manager.latest_checkpoint)
|
|
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([uv_curvature, batch['uv_mask']])
|
|
orig_img = batch['uv_curvature']
|
|
pred_img = tf.math.argmax(pred, axis=-1, output_type=tf.dtypes.int32)
|
|
img = tf.concat((orig_img, pred_img), axis=2).numpy()
|
|
|
|
ex.imshow(img[0] / 6.0).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())
|
|
|
|
smpl = SMPL()
|
|
scce = tf.keras.losses.SparseCategoricalCrossentropy()
|
|
|
|
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),
|
|
'mesh_curvature': (14475)
|
|
}
|
|
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/train_100',
|
|
batch_size=8,
|
|
signature=signature_dynamic,
|
|
use_filled=False)
|
|
static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100',
|
|
signature=signature_static,
|
|
use_filled=False)
|
|
dataset_valid = factory.get_dataset(folder='/home/workspace/local-data/jumpsuit_20/valid',
|
|
batch_size=8,
|
|
signature=signature_dynamic)
|
|
static_dataset_valid = StaticDataset(folder='/home/workspace/local-data/jumpsuit_20/valid',
|
|
signature=signature_static)
|
|
|
|
valid_iterator = iter(dataset_valid)
|
|
|
|
model = AutoEncoder()
|
|
# optimizer = tf.optimizers.Adam(learning_rate=0.002, beta_1=0.0, beta_2=0.99, epsilon=1e-8)
|
|
lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(0.001, decay_steps=10000, decay_rate=0.1, staircase=False)
|
|
optimizer = tf.optimizers.Adam(learning_rate=lr_schedule)
|
|
folder = 'models/ae_logs/'
|
|
|
|
ckpt = tf.train.Checkpoint(model=model)
|
|
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + name, max_to_keep=5)
|
|
|
|
if testing:
|
|
test()
|
|
else:
|
|
train() |