Mask和Pad

1. 填充序列

https://tensorflow.google.cn/beta/guide/keras/masking_and_padding

raw_inputs = [
  [83, 91, 1, 645, 1253, 927],
  [73, 8, 3215, 55, 927],
  [711, 632, 71]
]

# By default, this will pad using 0s; it is configurable via the
# "value" parameter.
# Note that you could "pre" padding (at the beginning) or
# "post" padding (at the end).
# We recommend using "post" padding when working with RNN layers
# (in order to be able to use the 
# CuDNN implementation of the layers).
padded_inputs = tf.keras.preprocessing.sequence.pad_sequences(raw_inputs,
                                                              padding='post')

print(padded_inputs)

2. Mask

   经过Pad现在所有样本都具有统一的长度，必须告知模型某些部分数据实际上是填充的，应该被忽略。这种机制就是Mask。
   

There are three ways to introduce input masks in Keras models:

• Add a keras.layers.Masking layer.
• Configure a keras.layers.Embedding layer with mask_zero=True.
• Pass a mask argument manually when calling layers that support this argument (e.g. RNN layers).