def fetch_datasets(self, activation_func_bounds):
self.dataset = inp.read_ds_zip(FLAGS.input_path)
if DEV:
self.dataset = self.dataset[:FLAGS.batch_size*5]
shape = list(self.dataset.shape)
self.epoch_size = int(shape[0] / FLAGS.batch_size)
self._batch_shape = shape
self._batch_shape[0] = FLAGS.batch_size
self.dataset = self.dataset[:int(len(self.dataset) / FLAGS.batch_size) * FLAGS.batch_size]
self.dataset = inp.rescale_ds(self.dataset, activation_func_bounds.min, activation_func_bounds.max)
self._image_shape = list(self.dataset.shape)[1:]
self.test_set = inp.read_ds_zip(FLAGS.test_path)[0:FLAGS.test_max]
self.test_set = inp.rescale_ds(self.test_set, self._activation.min, self._activation.max)
def fetch_datasets(self, activation_func_bounds):
original_data, filters = inp.get_images(FLAGS.input_path)
assert len(filters) == len(original_data)
original_data, filters = self.bloody_hack_filterbatches(original_data, filters)
ut.print_info('shapes. data, filters: %s' % str((original_data.shape, filters.shape)))
original_data = inp.rescale_ds(original_data, activation_func_bounds.min, activation_func_bounds.max)
self._image_shape = inp.get_image_shape(FLAGS.input_path)
if DEV:
original_data = original_data[:300]
self.epoch_size = math.ceil(len(original_data) / FLAGS.batch_size)
self.test_size = math.ceil(len(original_data) / FLAGS.batch_size)
return original_data, filters
def fetch_datasets(self, activation_func_bounds):
original_data, filters = inp.get_images(FLAGS.input_path)
assert len(filters) == len(original_data)
original_data, filters = self.bloody_hack_filterbatches(
original_data, filters)
ut.print_info('shapes. data, filters: %s' % str(
(original_data.shape, filters.shape)))
original_data = inp.rescale_ds(original_data,
activation_func_bounds.min,
activation_func_bounds.max)
self._image_shape = inp.get_image_shape(FLAGS.input_path)
if DEV:
original_data = original_data[:300]
self.epoch_size = math.ceil(len(original_data) / FLAGS.batch_size)
self.test_size = math.ceil(len(original_data) / FLAGS.batch_size)
return original_data, filters
def fetch_datasets(): activation_func_bounds = act.sigmoid original_data, filters = inp.get_images(source) original_data = inp.rescale_ds(original_data, activation_func_bounds.min, activation_func_bounds.max) part = 1. return original_data[:len(original_data)*part], original_data[len(original_data)*part:]