def build(self, hp, inputs=None):
input_node = nest.flatten(inputs)[0]
output_node = input_node
block_type = self.block_type or hp.Choice(
'block_type', ['resnet', 'xception', 'vanilla'], default='vanilla')
normalize = self.normalize
if normalize is None:
normalize = hp.Boolean('normalize', default=False)
augment = self.augment
if augment is None:
augment = hp.Boolean('augment', default=False)
if normalize:
output_node = preprocessing.Normalization().build(hp, output_node)
if augment:
output_node = preprocessing.ImageAugmentation().build(
hp, output_node)
if block_type == 'resnet':
output_node = basic.ResNetBlock().build(hp, output_node)
elif block_type == 'xception':
output_node = basic.XceptionBlock().build(hp, output_node)
elif block_type == 'vanilla':
output_node = basic.ConvBlock().build(hp, output_node)
return output_node
def test_imag_augmentation():
input_shape = (32, 32, 3)
block = preprocessing.ImageAugmentation()
hp = kerastuner.HyperParameters()
block = graph_module.deserialize(graph_module.serialize(block))
block.build(hp, ak.Input(shape=input_shape).build())
assert utils.name_in_hps('vertical_flip', hp)
assert utils.name_in_hps('horizontal_flip', hp)
def test_image_augmentation():
utils.block_basic_exam(
preprocessing.ImageAugmentation(),
tf.keras.Input(shape=(32, 32, 3), dtype=tf.float32),
['vertical_flip', 'horizontal_flip'],
)