def _build_block(self, hp, output_node, block_type):
if block_type == RESNET:
return basic.ResNetBlock().build(hp, output_node)
elif block_type == XCEPTION:
return basic.XceptionBlock().build(hp, output_node)
elif block_type == VANILLA:
return basic.ConvBlock().build(hp, output_node)
def _build_block(self, hp, output_node, block_type):
max_tokens = self.max_tokens or hp.Choice(
MAX_TOKENS, [500, 5000, 20000], default=5000)
if block_type == NGRAM:
output_node = preprocessing.TextToNgramVector(
max_tokens=max_tokens).build(hp, output_node)
return basic.DenseBlock().build(hp, output_node)
if block_type == BERT:
output_node = basic.BertBlock().build(hp, output_node)
else:
output_node = preprocessing.TextToIntSequence(
max_tokens=max_tokens).build(hp, output_node)
if block_type == TRANSFORMER:
output_node = basic.Transformer(
max_features=max_tokens + 1,
pretraining=self.pretraining,
).build(hp, output_node)
else:
output_node = basic.Embedding(
max_features=max_tokens + 1,
pretraining=self.pretraining,
).build(hp, output_node)
output_node = basic.ConvBlock().build(hp, output_node)
output_node = reduction.SpatialReduction().build(hp, output_node)
output_node = basic.DenseBlock().build(hp, output_node)
return output_node
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 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', ['vanilla', 'transformer', 'ngram'],
default='vanilla')
max_tokens = self.max_tokens or hp.Choice(
'max_tokens', [500, 5000, 20000], default=5000)
if block_type == 'ngram':
output_node = preprocessing.TextToNgramVector(
max_tokens=max_tokens).build(hp, output_node)
output_node = basic.DenseBlock().build(hp, output_node)
else:
output_node = preprocessing.TextToIntSequence(
max_tokens=max_tokens).build(hp, output_node)
if block_type == 'transformer':
output_node = basic.Transformer(
max_features=max_tokens + 1,
pretraining=self.pretraining).build(hp, output_node)
else:
output_node = basic.Embedding(
max_features=max_tokens + 1,
pretraining=self.pretraining).build(hp, output_node)
output_node = basic.ConvBlock().build(hp, output_node)
output_node = reduction.SpatialReduction().build(hp, output_node)
output_node = basic.DenseBlock().build(hp, output_node)
return output_node
def test_conv_block():
utils.block_basic_exam(
basic.ConvBlock(),
tf.keras.Input(shape=(32, 32, 3), dtype=tf.float32),
[
'kernel_size',
'num_blocks',
'separable',
])
def test_type_error_for_call():
block = basic.ConvBlock()
with pytest.raises(TypeError) as info:
block(block)
assert 'Expect the inputs to layer' in str(info.value)
