Tensorflow:将前馈添加到LSTM

Question

如何使用Tensorflow在标准LSTM网络之前添加额外的前馈层？

Answer 1

n_timesteps = 15
n_dim = 5

model = models.Sequential()
model.add(layers.TimeDistributed(layers.Dense(10, activation='relu'), input_shape=(n_timesteps, n_dim)))
model.add(layers.LSTM(25))
model.add(layers.Dense(2, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam')