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 vectorizer == 'ngram':
output_node = preprocessing.TextToNgramVector().build(hp, output_node)
output_node = basic.DenseBlock().build(hp, output_node)
else:
output_node = preprocessing.TextToIntSequence().build(hp, output_node)
output_node = basic.Embedding(
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_text_to_ngram_vector():
utils.block_basic_exam(
preprocessing.TextToNgramVector(),
tf.keras.Input(shape=(1, ), dtype=tf.string),
['ngrams'],
)