large refactor
This commit is contained in:
+27
-60
@@ -5,7 +5,7 @@ import wandb
|
||||
import random
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
|
||||
|
||||
|
||||
from custom_utils.custom_utils import UV2Mesh, maskFacesBatch
|
||||
@@ -15,20 +15,22 @@ import plotly.express as ex
|
||||
from tf_utils import check_tf_version, allow_memory_growth
|
||||
from dataset import DatasetFactory, StaticDataset
|
||||
from custom_utils.custom_utils import batch_to_dict
|
||||
from custom_utils.smpl import SMPL
|
||||
from models.ae_curv_model import AutoEncoder
|
||||
from models.cond_encoder import AutoEncoder
|
||||
from configs.config_ae_curv import config
|
||||
|
||||
|
||||
name='ae_curvature_x_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')
|
||||
run = wandb.init(project='vae', name=config['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('configs/config.py')
|
||||
artifact.add_file('configs/config_ae_curv.py')
|
||||
artifact.add_file('models/base.py')
|
||||
artifact.add_file('models/cond_encoder.py')
|
||||
artifact.add_file('dataset.py')
|
||||
artifact.add_file('convnext/models/convnext_tf.py')
|
||||
run.log_artifact(artifact)
|
||||
|
||||
@@ -110,7 +112,7 @@ def dice_dense(prediction, ground_truth, weight_map=None):
|
||||
return tf.reduce_mean(dice_score)
|
||||
|
||||
|
||||
@tf.function
|
||||
# @tf.function
|
||||
def train_step(batch):
|
||||
|
||||
with tf.GradientTape() as tape:
|
||||
@@ -121,22 +123,14 @@ def train_step(batch):
|
||||
|
||||
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
|
||||
}
|
||||
return { 'train/loss': loss, 'train/ce_uv_loss': ce_uv_loss, 'train/ssim': ms_ssim, 'train/mean_iou': mean_iou, 'train/dice': dice }
|
||||
|
||||
|
||||
|
||||
@@ -157,11 +151,10 @@ def valid_step(batch):
|
||||
}
|
||||
|
||||
|
||||
|
||||
def train():
|
||||
step = 0
|
||||
for batch in dataset_train:
|
||||
batch = static_dataset_train.expand_batch(batch_to_dict(batch, signature_dynamic))
|
||||
batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
|
||||
|
||||
train_loss = train_step(batch)
|
||||
|
||||
@@ -194,7 +187,7 @@ def train():
|
||||
def test():
|
||||
ckpt.restore(manager.latest_checkpoint)
|
||||
for batch in dataset_train:
|
||||
batch = static_dataset_train.expand_batch(batch_to_dict(batch, signature_dynamic))
|
||||
batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic']))
|
||||
uv_curvature = tf.one_hot(batch['uv_curvature'], 7)
|
||||
|
||||
pred = model([uv_curvature, batch['uv_mask']])
|
||||
@@ -208,57 +201,31 @@ def test():
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
init_wandb()
|
||||
# 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()
|
||||
|
||||
resolution_modifier = ''
|
||||
if config['resolution'] != 512:
|
||||
resolution_modifier = '_' + str(config['resolution'])
|
||||
|
||||
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)
|
||||
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']])
|
||||
static_dataset_train = StaticDataset(folder=config['train_dir'], signature=config['signature_static'], use_filled=config['use_filled'], resolutions=[config['resolution']])
|
||||
dataset_valid = factory.get_dataset(folder=config['valid_dir'], batch_size=config['batch_size'], signature=config['signature_dynamic'])
|
||||
static_dataset_valid = StaticDataset(folder=config['valid_dir'], signature=config['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/'
|
||||
model = AutoEncoder(config['cond_ae'])
|
||||
optimizer = tf.optimizers.Adam(learning_rate=config['lr'])
|
||||
|
||||
ckpt = tf.train.Checkpoint(model=model)
|
||||
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + name, max_to_keep=5)
|
||||
manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=3)
|
||||
|
||||
|
||||
if testing:
|
||||
test()
|
||||
|
||||
Reference in New Issue
Block a user