separate sub models from their training (wip)
This commit is contained in:
+29
-25
@@ -1,5 +1,5 @@
|
||||
import os
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "3"
|
||||
|
||||
import time
|
||||
import argparse
|
||||
@@ -17,10 +17,10 @@ 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
|
||||
from models.ae_body_model import AutoEncoder, AutoEncoder128, AutoEncoder32
|
||||
|
||||
|
||||
name='ae_body_8'
|
||||
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. \
|
||||
@@ -31,7 +31,8 @@ def init_wandb():
|
||||
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')
|
||||
remove multiplications with garment uv mask\
|
||||
')
|
||||
artifact = wandb.Artifact('code', type='code')
|
||||
artifact.add_file('auto_encoder_body.py')
|
||||
artifact.add_file('losses.py')
|
||||
@@ -98,7 +99,7 @@ def train_step(batch):
|
||||
|
||||
with tf.GradientTape() as tape:
|
||||
|
||||
pred = model(batch['uv_body_posed'])
|
||||
pred = model(batch['uv_body_posed' + resolution_modifier])
|
||||
# pred = (pred + zero_body) * batch['mesh_mask'][:,:,tf.newaxis]
|
||||
|
||||
mesh_pred = uv2mesh(pred)
|
||||
@@ -109,13 +110,14 @@ def train_step(batch):
|
||||
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'] - 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'] * uv_mask_body[tf.newaxis,tf.newaxis,:,:], [0,2,3,1]) + 1, max_val=2))
|
||||
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'])
|
||||
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'])
|
||||
@@ -153,12 +155,12 @@ def valid_step(batch):
|
||||
|
||||
def plot_everything(batch: dict, type: str):
|
||||
|
||||
pred = model(batch['uv_body_posed'])
|
||||
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'], [0,2,3,1])
|
||||
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)]
|
||||
@@ -170,7 +172,8 @@ def plot_everything(batch: dict, type: str):
|
||||
# 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 = batch['mesh_body_posed'].numpy()
|
||||
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
|
||||
@@ -222,37 +225,38 @@ if __name__ == '__main__':
|
||||
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 = 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_posed': (3, 512, 256,),
|
||||
'uv_body_posed': (3, 512, 256,),
|
||||
'uv_body_posed_128': (3, 512, 256,),
|
||||
'mesh_body_posed': (14475, 3,),
|
||||
# 'mesh_posed': (14475, 3,),
|
||||
# 'mesh_unposed': (14475, 3,),
|
||||
# 'uv_unposed': (3, 512, 256,)
|
||||
}
|
||||
signature_static = { #'uv_static': (3, 512, 256,),
|
||||
# 'mesh_static': (14475, 3,),
|
||||
signature_static = {
|
||||
'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=32, signature=signature_dynamic, use_filled=True)
|
||||
static_dataset_train = StaticDataset(folder='/home/workspace/local-data/train_100', signature=signature_static, use_filled=True)
|
||||
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()
|
||||
# lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(0.0005, decay_steps=30000, decay_rate=0.1, staircase=False)
|
||||
# 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()
|
||||
Reference in New Issue
Block a user