def create_model():
left_input = Input(shape=(max_seq_length, ), dtype='float32')
right_input = Input(shape=(max_seq_length, ), dtype='float32')
left_sen_representation = shared_model(left_input)
right_sen_representation = shared_model(right_input)
man_distance = ManDist()(
[left_sen_representation, right_sen_representation])
sen_representation = concatenate(
[left_sen_representation, right_sen_representation, man_distance])
similarity = Dense(1, activation='sigmoid')(Dense(2)(Dense(4)(
Dense(16)(sen_representation))))
model = Model(inputs=[left_input, right_input], outputs=[similarity])
return model
if __name__ == '__main__':
# 超参
batch_size = 1024
n_epoch = 9
n_hidden = 50
left_input = Input(shape=(max_seq_length,), dtype='float32')
right_input = Input(shape=(max_seq_length,), dtype='float32')
left_sen_representation = shared_model(left_input)
right_sen_representation = shared_model(right_input)
# 引入曼哈顿距离，把得到的变换concat上原始的向量再通过一个多层的DNN做了下非线性变换、sigmoid得相似度
# 没有使用https://zhuanlan.zhihu.com/p/31638132中提到的马氏距离，尝试了曼哈顿距离、点乘和cos，效果曼哈顿最好
man_distance = ManDist()([left_sen_representation, right_sen_representation])
sen_representation = concatenate([left_sen_representation, right_sen_representation, man_distance])
similarity = Dense(1, activation='sigmoid')(Dense(2)(Dense(4)(Dense(16)(sen_representation))))
model = Model(inputs=[left_input, right_input], outputs=[similarity])
model.compile(loss='mean_squared_error', optimizer=keras.optimizers.Adam(), metrics=['accuracy'])
model.summary()
training_start_time = time()
malstm_trained = model.fit([X_train['left'], X_train['right']], Y_train,
batch_size=batch_size, epochs=n_epoch,
validation_data=([X_validation['left'], X_validation['right']], Y_validation))
training_end_time = time()
print("Training time finished.\n%d epochs in %12.2f" % (n_epoch, training_end_time - training_start_time))
# Plot accuracy
# x.add(GlobalMaxPool1D())
# x.add(Dense(250, activation='relu'))
# x.add(Dropout(0.3))
# x.add(Dense(1, activation='sigmoid'))
# LSTM
x.add(LSTM(n_hidden))
shared_model = x
# The visible layer
left_input = Input(shape=(max_seq_length, ), dtype='int32')
right_input = Input(shape=(max_seq_length, ), dtype='int32')
# Pack it all up into a Manhattan Distance model
malstm_distance = ManDist()(
[shared_model(left_input),
shared_model(right_input)])
model = Model(inputs=[left_input, right_input], outputs=[malstm_distance])
model.compile(loss='mean_squared_error',
optimizer=tf.keras.optimizers.Adam(),
metrics=['accuracy'])
model.summary()
shared_model.summary()
try:
# Start trainings
training_start_time = time()
callbacks = [EarlyStopping(monitor='val_loss', patience=3)]
malstm_trained = model.fit(
[X_train['left'], X_train['right']],
embedding_dim,
weights=[embeddings],
input_length=max_seq_length,
trainable=False)
# Embedded version of the inputs
encoded_left = embedding_layer(left_input)
encoded_right = embedding_layer(right_input)
# Since this is a siamese network, both sides share the same LSTM
shared_lstm = LSTM(50)
left_output = shared_lstm(encoded_left)
right_output = shared_lstm(encoded_right)
malstm_distance = ManDist()([left_output, right_output])
# Pack it all up into a model
model = Model(inputs=[left_input, right_input], outputs=[malstm_distance])
if gpus >= 2:
# `multi_gpu_model()` is a so quite buggy. it breaks the saved model.
model = tf.keras.utils.multi_gpu_model(model, gpus=gpus)
model.compile(loss='mean_squared_error',
optimizer=tf.keras.optimizers.Adam(),
metrics=['accuracy'])
model.summary()
# Start trainings
training_start_time = time()
malstm_trained = model.fit(
# x.add(Conv1D(250, kernel_size=5, activation='relu'))
# x.add(GlobalMaxPool1D())
# x.add(Dense(250, activation='relu'))
# x.add(Dropout(0.3))
# x.add(Dense(1, activation='sigmoid'))
# LSTM
x.add(LSTM(n_hidden))
shared_model = x
# The visible layer
left_input = Input(shape=(max_seq_length, ), dtype='int32')
right_input = Input(shape=(max_seq_length, ), dtype='int32')
# Pack it all up into a Manhattan Distance model
malstm_distance = ManDist()([x(left_input), x(right_input)])
model = Model(inputs=[left_input, right_input], outputs=[malstm_distance])
if gpus >= 2:
# `multi_gpu_model()` is a so quite buggy. it breaks the saved model.
model = tf.keras.utils.multi_gpu_model(model, gpus=gpus)
model.compile(loss='mean_squared_error',
optimizer=tf.keras.optimizers.Adam(),
metrics=['accuracy'])
model.summary()
shared_model.summary()
# Start trainings
training_start_time = time()
malstm_trained = model.fit(
[X_train['left'], X_train['right']],
