def train(image_path, model_path, gpu, latent_width, color_channels, batch,
epoch, shape, kl_ratio):
if not image_path[-1] == '/':
image_path += '/'
if not os.path.exists(os.path.dirname(image_path)):
os.makedirs(os.path.dirname(image_path))
if model_path[-1] == '/':
click.echo("Model Path should be a file path not a directory path. "
"Removing trailing '/' ...")
model_path = model_path[:-1]
file_paths = [
os.path.join(image_path, f) for f in os.listdir(image_path) if
os.path.isfile(os.path.join(image_path, f)) and not f.startswith('.')
]
iae = ImageAutoEncoder(img_width=shape[0],
img_height=shape[1],
encode_layers=[1000, 700, 300],
decode_layers=[500, 700, 1000],
rec_kl_ratio=kl_ratio,
flag_gpu=gpu,
latent_width=latent_width,
color_channels=color_channels)
iae.load_images(file_paths)
iae.fit(batch_size=batch, n_epochs=epoch)
iae.dump(model_path)
def train(image_path, model_path, gpu, latent_width, color_channels, batch,
epoch, shape, kl_ratio):
if not image_path[-1] == '/':
image_path += '/'
if not os.path.exists(os.path.dirname(image_path)):
os.makedirs(os.path.dirname(image_path))
if model_path[-1] == '/':
click.echo("Model Path should be a file path not a directory path. "
"Removing trailing '/' ...")
model_path = model_path[:-1]
file_paths = [os.path.join(image_path, f)
for f in os.listdir(image_path)
if os.path.isfile(os.path.join(image_path, f))
and not f.startswith('.')]
iae = ImageAutoEncoder(img_width=shape[0],
img_height=shape[1],
encode_layers=[1000, 700, 300],
decode_layers=[500, 700, 1000],
rec_kl_ratio=kl_ratio,
flag_gpu=gpu,
latent_width=latent_width,
color_channels=color_channels)
iae.load_images(file_paths)
iae.fit(batch_size=batch, n_epochs=epoch)
iae.dump(model_path)
def generate(model_path, img_dir, number, extremity, mean, format, image_multiplier):
click.echo("Loading Model...")
model = ImageAutoEncoder.load(model_path)
click.echo("Model Loaded")
click.echo("Saving Images to {0} as {1}".format(img_dir, format))
if not img_dir[-1] == '/':
img_dir += '/'
if not os.path.exists(os.path.dirname(img_dir)):
os.makedirs(os.path.dirname(img_dir))
variance = extremity
vec = np.random.normal(mean, variance,
(number, model.latent_dim)).astype('float32')
reconstructed = model.inverse_transform(vec) * 255.0
for i in range(number):
im = reconstructed[i]
im = np.clip(image_multiplier*im/im.max(), 0, 255)
im = Image.fromarray(np.uint8(reconstructed[i]))
fname = "{0}.{1}".format(i, format)
path = os.path.join(img_dir, fname)
im.save(path)
def generate(model_path, img_dir, number, extremity, mean, format,
image_multiplier):
click.echo("Loading Model...")
model = ImageAutoEncoder.load(model_path)
click.echo("Model Loaded")
click.echo("Saving Images to {0} as {1}".format(img_dir, format))
if not img_dir[-1] == '/':
img_dir += '/'
if not os.path.exists(os.path.dirname(img_dir)):
os.makedirs(os.path.dirname(img_dir))
variance = extremity
vec = np.random.normal(mean, variance,
(number, model.latent_dim)).astype('float32')
reconstructed = model.inverse_transform(vec) * 255.0
for i in range(number):
im = reconstructed[i]
im = np.clip(image_multiplier * im / im.max(), 0, 255)
im = Image.fromarray(np.uint8(reconstructed[i]))
fname = "{0}.{1}".format(i, format)
path = os.path.join(img_dir, fname)
im.save(path)
