def test_image_block():
block = hyperblock_module.ImageBlock(normalize=None, augment=None)
block.set_state(block.get_state())
hp = kerastuner.HyperParameters()
block.build(hp, ak.Input())
assert common.name_in_hps('block_type', hp)
assert common.name_in_hps('normalize', hp)
assert common.name_in_hps('augment', hp)
def assemble(self, input_node):
block = hyperblock.ImageBlock()
if max(self._shape[0], self._shape[1]) < 32:
if self._num_samples < 10000:
self.hps.append(hp_module.Choice(
block.name + '_resnet/v1/conv4_depth', [6],
default=6))
self.hps.append(hp_module.Choice(
block.name + '_resnet/v2/conv4_depth', [6],
default=6))
self.hps.append(hp_module.Choice(
block.name + '_resnet/next/conv4_depth', [6],
default=6))
self.hps.append(hp_module.Int(
block.name + '_xception/num_residual_blocks', 2, 4,
default=4))
return block(input_node)
def assemble(self, input_node):
# for image, use the num_instance to determine the range of the sizes of the
# resnet and xception
# use the image size to determine how the down sampling works, e.g. pooling.
return hyperblock.ImageBlock()(input_node)
