def test_embedding_block():
utils.block_basic_exam(
basic.Embedding(),
tf.keras.Input(shape=(32,), dtype=tf.float32),
[
'pretraining',
'embedding_dim',
])
def test_embedding_block():
input_shape = (32,)
block = basic.Embedding()
block.max_features = 100
hp = kerastuner.HyperParameters()
block.build(hp, ak.Input(shape=input_shape).build())
assert utils.name_in_hps('pretraining', hp)
assert utils.name_in_hps('embedding_dim', 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 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