TensorFlow tf.keras.layers.TimeDistributed

对时间序列每个timestamp的向量空间做一个层

# as the first layer in a model
model = Sequential()
model.add(TimeDistributed(Dense(8), input_shape=(10, 16)))  # 对序列的每个timestamp加一个dense层
# now model.output_shape == (None, 10, 8)

参考：
官网
http://www.voidcn.com/article/p-clryhrrh-bth.html