TensorFlow2：使用RNN进行文本分类

（一） 实验环境

import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

print('Tensorflow version: ', tf.__version__)

### Tensorflow version:  2.3.0 

（二） 实验数据

max_features = 20000  # Only consider the top 20k words
maxlen = 200  # Only consider the first 200 words of each movie review

(x_train, y_train), (x_val, y_val) = keras.datasets.imdb.load_data(
    num_words=max_features
)

x_train = keras.preprocessing.sequence.pad_sequences(x_train, maxlen=maxlen)
x_val = keras.preprocessing.sequence.pad_sequences(x_val, maxlen=maxlen)

print(len(x_train), "Training sequences")
print(len(x_val), "Validation sequences")

### 25000 Training sequences
### 25000 Validation sequences

（三） 构建模型

# Input for variable-length sequences of integers
inputs = keras.Input(shape=(None,), dtype="int32")

# Embed each integer in a 128-dimensional vector
x = layers.Embedding(max_features, 128)(inputs)

# Add 2 bidirectional LSTMs
x = layers.Bidirectional(layers.LSTM(64, return_sequences=True))(x)
x = layers.Bidirectional(layers.LSTM(64))(x)

# Add a classifier
outputs = layers.Dense(1, activation="sigmoid")(x)

model = keras.Model(inputs, outputs)
model.summary()

模型结构如下，bidirectional层的输出维度为(None, None, 128) ，这里的128怎么来的？

前向和后向两个方向的LSTM层均为64。bidirectional层默认是将两个方向的输出进行concat，所以得到的长度为128。

Model: "functional_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, None)]            0         
_________________________________________________________________
embedding (Embedding)        (None, None, 128)         2560000   
_________________________________________________________________
bidirectional (Bidirectional (None, None, 128)         98816     
_________________________________________________________________
bidirectional_1 (Bidirection (None, 128)               98816     
_________________________________________________________________
dense (Dense)                (None, 1)                 129       
=================================================================
Total params: 2,757,761
Trainable params: 2,757,761
Non-trainable params: 0
_________________________________________________________________

（四） 模型的编译和训练

model.compile("adam", "binary_crossentropy", metrics=["accuracy"])

model.fit(x_train, y_train, batch_size=16, epochs=2, validation_data=(x_val, y_val))