def test_Bidirectional():
rnn = recurrent.SimpleRNN
nb_sample = 2
dim = 2
timesteps = 2
output_dim = 2
for mode in ['sum', 'concat']:
x = np.random.random((nb_sample, timesteps, dim))
target_dim = 2 * output_dim if mode == 'concat' else output_dim
y = np.random.random((nb_sample, target_dim))
# test with Sequential model
model = Sequential()
model.add(wrappers.Bidirectional(rnn(output_dim),
merge_mode=mode, input_shape=(timesteps, dim)))
model.compile(loss='mse', optimizer='sgd')
model.fit(x, y, nb_epoch=1, batch_size=1)
# test config
model.get_config()
model = model_from_json(model.to_json())
model.summary()
# test stacked bidirectional layers
model = Sequential()
model.add(wrappers.Bidirectional(rnn(output_dim, return_sequences=True),
merge_mode=mode, input_shape=(timesteps, dim)))
model.add(wrappers.Bidirectional(rnn(output_dim), merge_mode=mode))
model.compile(loss='mse', optimizer='sgd')
model.fit(x, y, nb_epoch=1, batch_size=1)
# test with functional API
input = Input((timesteps, dim))
output = wrappers.Bidirectional(rnn(output_dim), merge_mode=mode)(input)
model = Model(input, output)
model.compile(loss='mse', optimizer='sgd')
model.fit(x, y, nb_epoch=1, batch_size=1)
# Bidirectional and stateful
input = Input(batch_shape=(1, timesteps, dim))
output = wrappers.Bidirectional(rnn(output_dim, stateful=True), merge_mode=mode)(input)
model = Model(input, output)
model.compile(loss='mse', optimizer='sgd')
model.fit(x, y, nb_epoch=1, batch_size=1)
python类Bidirectional()的实例源码
def SiameseLSTM(max_token_length, hidden_size, embedding_size=300):
text_input_1 = Input(shape=(max_token_length, embedding_size),
name='text_1')
text_mask_1 = Masking(mask_value=0.0, name='text_mask_1')(text_input_1)
# text_dropout_1 = Dropout(.5, name='text_dropout_1')(text_mask_1)
text_input_2 = Input(shape=(max_token_length, embedding_size),
name='text_2')
text_mask_2 = Masking(mask_value=0.0, name='text_mask_2')(text_input_2)
# text_dropout_2 = Dropout(.5, name='text_dropout_2')(text_mask_2)
lstm_1_a = Bidirectional(GRU(units=hidden_size,
return_sequences=True,
name='RNN_1_a'))(text_mask_1)
lstm_1_b = Bidirectional(GRU(units=hidden_size,
return_sequences=False,
name='RNN_1_b'))(lstm_1_a)
"""
lstm_1_c = Bidirectional(GRU(units=hidden_size,
return_sequences=False,
name='RNN_1_c'))(lstm_1_b)
"""
lstm_2_a = Bidirectional(GRU(units=hidden_size,
return_sequences=True,
name='RNN_2_a'))(text_mask_2)
lstm_2_b = Bidirectional(GRU(units=hidden_size,
return_sequences=False,
name='RNN_2_b'))(lstm_2_a)
"""
lstm_2_c = Bidirectional(GRU(units=hidden_size,
return_sequences=False,
name='RNN_2_c'))(lstm_2_b)
"""
cosine_similarity = Dot(axes=1, normalize=True,
name='cosine_similarity')([lstm_1_b, lstm_2_b])
model = Model(inputs=[text_input_1, text_input_2],
outputs=cosine_similarity)
return model
