def load_model(self, file_path):
self.model = self.load_customed_model(file_path)
picked = Pick()(self.model.get_layer(index=2).output)
self.encoder = Model(self.model.input, picked)
self.word_embedding_size = self.model.input_shape[2]
self.max_length = self.model.input_shape[1]
self.latent_size = self.model.get_layer(
index=2).layer.recurrent_layer.units
self.encoding_size = self.model.get_layer(index=3).input_shape[2]
self.input_transformer = WordEmbeddingTransformer(
self.word2vec_model, self.max_length)
self.output_transformer = WordEmbeddingTransformer(
self.word2vec_model, self.max_length)
def __init__(self,
word2vec_model,
max_length=10,
latent_size=300,
learning_rate=0.0001,
conv_size=5,
channel_size=10,
**kwargs):
self.word2vec_model = word2vec_model
self.input_transformer = WordEmbeddingConv3DTransformer(
word2vec_model,
max_length,
)
self.output_transformer = WordEmbeddingTransformer(
word2vec_model, max_length)
self.word_embedding_size = word2vec_model.get_size()
self.conv_size = conv_size
self.channel_size = channel_size
self.encoding_size = (self.word_embedding_size // self.conv_size *
self.channel_size)
super(Seq2VecC2RWord, self).__init__(max_length, latent_size,
learning_rate)
self.custom_objects['RNNDecoder'] = RNNDecoder
self.custom_objects['MaskPooling'] = MaskPooling
self.custom_objects['MaskToSeq'] = MaskToSeq
self.custom_objects['MaskConv'] = MaskConv
self.custom_objects['MaskConvNet'] = MaskConvNet
self.custom_objects['ConvEncoder'] = ConvEncoder
self.custom_objects['RNNCell'] = RNNCell
self.custom_objects['Pick'] = Pick
def __init__(self,
word2vec_model,
max_length=10,
latent_size=20,
encoding_size=100,
learning_rate=0.0001,
**kwargs):
self.word2vec_model = word2vec_model
self.input_transformer = WordEmbeddingTransformer(
word2vec_model, max_length)
self.output_transformer = WordEmbeddingTransformer(
word2vec_model, max_length)
self.word_embedding_size = word2vec_model.get_size()
self.encoding_size = encoding_size
super(Seq2VecR2RWord, self).__init__(max_length=max_length,
latent_size=latent_size,
learning_rate=learning_rate)
self.custom_objects[
'BidirectionalRNNEncoder'] = BidirectionalRNNEncoder
self.custom_objects['RNNDecoder'] = RNNDecoder
self.custom_objects['RNNCell'] = RNNCell
self.custom_objects['Pick'] = Pick
class TestWordEmbeddingTransformerClass(WordEmbeddingTransformerBase,
TestCase):
def setUp(self):
super(TestWordEmbeddingTransformerClass, self).setUp()
self.transformer = WordEmbeddingTransformer(
word2vec_model=self.word2vec, max_length=self.max_length)
def test_seq_transform_shape(self):
transformed_seq = self.transformer.seq_transform(self.seqs[0])
self.assertEqual(len(transformed_seq[0]), self.word2vec.get_size())
def test_call_zero_padding(self):
transformed_seqs = self.transformer(self.seqs)
np.testing.assert_array_almost_equal(
np.zeros((len(self.seqs), self.word2vec.get_size())),
transformed_seqs[:, -1, :])
self.assertTrue(np.sum(transformed_seqs[:, :-1, :], dtype=bool))
def test_call_shape(self):
self.assertEqual(
self.transformer(self.seqs).shape,
(len(self.seqs), self.max_length, self.word2vec.get_size()))
def load_model(self, file_path):
self.model = self.load_customed_model(file_path)
picked = Pick()(self.model.get_layer(index=7).output)
self.encoder = Model(self.model.input, picked)
self.char_embedding_size = self.model.get_layer(
index=1).output_shape[2]
self.max_length = self.model.get_layer(index=0).output_shape[1]
self.max_index = self.model.input_shape[2]
self.conv_size = self.char_embedding_size \
// self.model.get_layer(index=4).output_shape[2]
self.channel_size = self.model.get_layer(index=4).output_shape[3]
self.encoding_size = self.encoder.output_shape[1]
self.latent_size = self.model.get_layer(
index=8).layer.recurrent_layer.units
self.input_transformer = CharEmbeddingOneHotTransformer(
self.max_index,
self.max_length,
)
self.output_transformer = WordEmbeddingTransformer(
self.word2vec,
self.max_length,
)
def setUp(self):
super(TestWordEmbeddingTransformerClass, self).setUp()
self.transformer = WordEmbeddingTransformer(
word2vec_model=self.word2vec, max_length=self.max_length)