def split_samples(args):
assets = AssetManager(args.base_dir)
data = np.load(assets.get_preprocess_file_path(args.input_data_name))
imgs, classes, contents = data['imgs'], data['classes'], data['contents']
n_classes = np.unique(classes).size
n_samples = imgs.shape[0]
n_test_samples = int(n_samples * args.test_split)
test_idx = np.random.choice(n_samples, size=n_test_samples, replace=False)
train_idx = ~np.isin(np.arange(n_samples), test_idx)
np.savez(file=assets.get_preprocess_file_path(args.test_data_name),
imgs=imgs[test_idx],
classes=classes[test_idx],
contents=contents[test_idx],
n_classes=n_classes)
np.savez(file=assets.get_preprocess_file_path(args.train_data_name),
imgs=imgs[train_idx],
classes=classes[train_idx],
contents=contents[train_idx],
n_classes=n_classes)
def train_encoders(args): assets = AssetManager(args.base_dir) model_dir = assets.get_model_dir(args.model_name) tensorboard_dir = assets.get_tensorboard_dir(args.model_name) data = np.load(assets.get_preprocess_file_path(args.data_name)) imgs, classes, contents, n_classes = data['imgs'], data['classes'], data['contents'], data['n_classes'] imgs = imgs.astype(np.float32) / 255.0 converter = Converter.load(model_dir, include_encoders=False) glo_backup_dir = os.path.join(model_dir, args.glo_dir) if not os.path.exists(glo_backup_dir): os.mkdir(glo_backup_dir) converter.save(glo_backup_dir) converter.train_encoders( imgs=imgs, classes=classes, batch_size=default_config['train_encoders']['batch_size'], n_epochs=default_config['train_encoders']['n_epochs'], model_dir=model_dir, tensorboard_dir=tensorboard_dir ) converter.save(model_dir)
def train_encoders(args): assets = AssetManager(args.base_dir) model_dir = assets.get_model_dir(args.model_name) tensorboard_dir = assets.get_tensorboard_dir(args.model_name) data = np.load(assets.get_preprocess_file_path(args.data_name)) imgs = data['imgs'].astype(np.float32) / 255.0 backup_dir = os.path.join(model_dir, 'latent') if not os.path.exists(backup_dir): lord = Lord.load(model_dir, include_encoders=False) os.mkdir(backup_dir) lord.save(backup_dir) else: lord = Lord.load(backup_dir, include_encoders=False) lord.train_encoders( imgs=imgs, classes=data['classes'], batch_size=default_config['train_encoders']['batch_size'], n_epochs=default_config['train_encoders']['n_epochs'], model_dir=model_dir, tensorboard_dir=tensorboard_dir ) lord.save(model_dir)
def train(args):
assets = AssetManager(args.base_dir)
if not args.retrain:
model_dir = assets.recreate_model_dir(args.model_name)
tensorboard_dir = assets.recreate_tensorboard_dir(args.model_name)
else:
model_dir = assets.get_model_dir(args.model_name)
tensorboard_dir = assets.get_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs = data['imgs'].astype(np.float32) / 255.0
config = dict(
img_shape=imgs.shape[1:],
n_imgs=imgs.shape[0],
n_classes=data['n_classes'].item(),
)
config.update(base_config)
lord = Lord(config)
if args.retrain:
lord.load(model_dir, latent=True, amortized=False)
lord.config = config
lord.train_latent(imgs=imgs,
classes=data['classes'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir,
retrain=args.retrain)
lord.save(model_dir, latent=True, amortized=False)
def train(args):
assets = AssetManager(args.base_dir)
model_dir = assets.recreate_model_dir(args.model_name)
tensorboard_dir = assets.recreate_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs = data['imgs'].astype(np.float32) / 255.0
config = Config(
img_shape=imgs.shape[1:],
n_imgs=imgs.shape[0],
n_classes=data['n_classes'].item(),
content_dim=default_config['content_dim'],
class_dim=default_config['class_dim'],
content_std=default_config['content_std'],
content_decay=default_config['content_decay'],
n_adain_layers=default_config['n_adain_layers'],
adain_dim=default_config['adain_dim'],
perceptual_loss_layers=default_config['perceptual_loss']['layers'],
perceptual_loss_weights=default_config['perceptual_loss']['weights'],
perceptual_loss_scales=default_config['perceptual_loss']['scales'])
lord = Lord.build(config)
lord.train(imgs=imgs,
classes=data['classes'],
batch_size=default_config['train']['batch_size'],
n_epochs=default_config['train']['n_epochs'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir)
lord.save(model_dir)
def preprocess(args): assets = AssetManager(args.base_dir) img_dataset = dataset.get_dataset(args.dataset_id, args.dataset_path) imgs, classes, contents = img_dataset.read_images() n_classes = np.unique(classes).size np.savez( file=assets.get_preprocess_file_path(args.data_name), imgs=imgs, classes=classes, contents=contents, n_classes=n_classes )
def split_samples(args):
assets = AssetManager(args.base_dir)
data = np.load(assets.get_preprocess_file_path(args.input_data_name))
imgs, classes, contents = data['imgs'], data['classes'], data['contents']
n_classes = np.unique(classes).size
# NOTE: This is a static split, valid only for CIFAR-10
test_idx = np.arange(50000, 60000)
train_idx = np.arange(50000)
np.savez(
file=assets.get_preprocess_file_path(args.test_data_name),
imgs=imgs[test_idx], classes=classes[test_idx], contents=contents[test_idx], n_classes=n_classes
)
np.savez(
file=assets.get_preprocess_file_path(args.train_data_name),
imgs=imgs[train_idx], classes=classes[train_idx], contents=contents[train_idx], n_classes=n_classes
)
def split_classes(args):
assets = AssetManager(args.base_dir)
data = np.load(assets.get_preprocess_file_path(args.input_data_name))
imgs, classes, contents = data['imgs'], data['classes'], data['contents']
# Seed
np.random.seed(2020)
n_classes = np.unique(classes).size
test_classes = np.random.choice(n_classes, size=args.num_test_classes, replace=False)
test_idx = np.isin(classes, test_classes)
train_idx = ~np.isin(classes, test_classes)
np.savez(
file=assets.get_preprocess_file_path(args.test_data_name),
imgs=imgs[test_idx], classes=classes[test_idx], contents=contents[test_idx], n_classes=n_classes
)
np.savez(
file=assets.get_preprocess_file_path(args.train_data_name),
imgs=imgs[train_idx], classes=classes[train_idx], contents=contents[train_idx], n_classes=n_classes
)
def train(args):
wandb.config.update(default_config)
args_dict = vars(args)
args_dict.pop('func')
wandb.config.update(args_dict)
assets = AssetManager(args.base_dir)
model_dir = assets.recreate_model_dir(args.model_name)
tensorboard_dir = assets.recreate_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs, classes, contents, n_classes = data['imgs'], data['classes'], data['contents'], data['n_classes']
imgs = imgs.astype(np.float32) / 255.0
converter = Converter.build(
img_shape=imgs.shape[1:],
n_imgs=imgs.shape[0],
n_classes=n_classes,
content_dim=args.content_dim,
class_dim=args.class_dim,
content_std=args.content_std,
content_decay=args.content_decay,
n_adain_layers=default_config['n_adain_layers'],
adain_enabled=args.adain,
adain_dim=default_config['adain_dim'],
adain_normalize=args.adain_normalize,
perceptual_loss_layers=default_config['perceptual_loss']['layers'],
perceptual_loss_weights=default_config['perceptual_loss']['weights'],
perceptual_loss_scales=default_config['perceptual_loss']['scales'],
)
converter.train(
imgs=imgs,
classes=classes,
batch_size=default_config['train']['batch_size'],
n_epochs=default_config['train']['n_epochs'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir
)
converter.save(model_dir)
def train_encoders(args):
assets = AssetManager(args.base_dir)
model_dir = assets.get_model_dir(args.model_name)
tensorboard_dir = assets.get_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs = data['imgs'].astype(np.float32) / 255.0
lord = Lord()
lord.load(model_dir, latent=True, amortized=False)
lord.train_amortized(imgs=imgs,
classes=data['classes'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir)
lord.save(model_dir, latent=False, amortized=True)
def train(args):
assets = AssetManager(args.base_dir)
model_dir = assets.recreate_model_dir(args.model_name)
tensorboard_dir = assets.recreate_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs = data['imgs'].astype(np.float32) / 255.0
config = dict(
img_shape=imgs.shape[1:],
n_imgs=imgs.shape[0],
n_classes=data['n_classes'].item(),
)
config.update(base_config)
lord = Lord(config)
lord.train(imgs=imgs,
classes=data['classes'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir)
def __init__(self,
subset=None,
base_dir='results',
model_name='minst_10_model',
data_name='minst_10_test',
include_encoders=True):
self.data_name = data_name
assets = AssetManager(base_dir)
data = np.load(assets.get_preprocess_file_path(data_name))
imgs, classes, contents, n_classes = data['imgs'], data[
'classes'], data['contents'], data['n_classes']
imgs = imgs.astype(np.float32) / 255.0
if subset is not None:
self.curr_imgs = imgs[:subset]
self.classes = classes[:subset]
else:
self.curr_imgs = imgs
self.classes = classes
self.onehot_enc = OneHotEncoder()
self.onehot_classes = self.onehot_enc.fit_transform(
self.classes.reshape(-1, 1))
self.n_classes = self.onehot_classes.shape[1]
self.n_images = self.curr_imgs.shape[0]
self.converter = Converter.load(assets.get_model_dir(model_name),
include_encoders=include_encoders)
self.content_codes = self.converter.content_encoder.predict(
self.curr_imgs)
self.class_codes = self.converter.class_encoder.predict(self.curr_imgs)
class_adain_params = self.converter.class_modulation.predict(
self.class_codes)
self.class_adain_params = class_adain_params.reshape(
class_adain_params.shape[0], -1)
self.curr_imgs, self.classes, self.onehot_classes, self.content_codes, self.class_codes, self.class_adain_params = \
shuffle(self.curr_imgs, self.classes, self.onehot_classes, self.content_codes, self.class_codes,
self.class_adain_params)
def __init__(self,
digit,
subset=None,
base_dir='results',
model_name='minst_10_model',
data_name='minst_10_test'):
self.digit = digit
assets = AssetManager(base_dir)
data = np.load(assets.get_preprocess_file_path(data_name))
imgs, classes, contents, n_classes = data['imgs'], data[
'classes'], data['contents'], data['n_classes']
imgs = imgs.astype(np.float32) / 255.0
curr_zero_idx = (classes == digit)
curr_zero_idx[subset:] = False # if have the time use np.csum isntead
self.curr_imgs = imgs[curr_zero_idx, ]
self.n_images = self.curr_imgs.shape[0]
self.converter = Converter.load(assets.get_model_dir(model_name),
include_encoders=True)
self.content_codes = self.converter.content_encoder.predict(
self.curr_imgs)
class_codes = self.converter.class_encoder.predict(self.curr_imgs)
self.class_adain_params = self.converter.class_modulation.predict(
class_codes)
