def build(self, hp, inputs=None):
if self.identity:
return IdentityLayer(name=self.name)(inputs)
if self.num_classes:
expected = self.num_classes if self.num_classes > 2 else 1
if self.output_shape[-1] != expected:
raise ValueError('The data doesn\'t match the expected shape. '
'Expecting {} but got {}'.format(
expected, self.output_shape[-1]))
inputs = nest.flatten(inputs)
utils.validate_num_inputs(inputs, 1)
input_node = inputs[0]
output_node = input_node
if len(output_node.shape) > 2:
dropout_rate = self.dropout_rate or hp.Choice(
'dropout_rate', [0.0, 0.25, 0.5], default=0)
if dropout_rate > 0:
output_node = tf.keras.layers.Dropout(dropout_rate)(
output_node)
output_node = block_module.SpatialReduction().build(
hp, output_node)
output_node = tf.keras.layers.Dense(self.output_shape[-1])(output_node)
if self.loss == 'binary_crossentropy':
output_node = Sigmoid(name=self.name)(output_node)
else:
output_node = tf.keras.layers.Softmax(name=self.name)(output_node)
return output_node
def test_spatial_reduction():
input_shape = (32, 32, 3)
block = block_module.SpatialReduction()
hp = kerastuner.HyperParameters()
block.build(hp, ak.Input(shape=input_shape).build())
assert name_in_hps('reduction_type', hp)
def build(self, hp, inputs=None):
input_node = nest.flatten(inputs)[0]
output_node = input_node
vectorizer = self.vectorizer or hp.Choice(
'vectorizer', ['sequence', 'ngram'], default='sequence')
if not isinstance(input_node, node_module.TextNode):
raise ValueError('The input_node should be a TextNode.')
if vectorizer == 'ngram':
output_node = preprocessor_module.TextToNgramVector()(output_node)
output_node = block_module.DenseBlock()(output_node)
else:
output_node = preprocessor_module.TextToIntSequence()(output_node)
output_node = block_module.EmbeddingBlock(
pretraining=self.pretraining)(output_node)
output_node = block_module.ConvBlock(separable=True)(output_node)
output_node = block_module.SpatialReduction()(output_node)
output_node = block_module.DenseBlock()(output_node)
return output_node
def assemble(self, input_node):
block = hyperblock.ImageBlock(seed=self.seed)
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))
output_node = block(input_node)
output_node = block_module.SpatialReduction()(output_node)
return block_module.DenseBlock()(output_node)