深度学习——tensorflow2.0搭建文本分类模型

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)

2.0.0-alpha0

imdb = keras.datasets.imdb
vocab_size = 10000
index_from = 3
# num_words：词表的最大值；index_from：从这个index开始索引实际单词，默认为3
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words = vocab_size, index_from = index_from)

word_index = imdb.get_word_index()
print(len(word_index)) 

88584

word_index = {k:(v+3) for k, v in word_index.items()}
word_index['<PAD>'] = 0
word_index['<START>'] = 1
word_index['<UNK>'] = 2
word_index['<END>'] = 3

reverse_word_index = dict([(value, key) for key, value in word_index.items()])

def decode_review(text_ids):
    return ' '.join([reverse_word_index.get(word_id, "<UNK>") for word_id in text_ids])

max_length = 500

# keras.preprocessing.sequence.pad_sequences:由于输入是变长的，因此需要使用padding进行对齐
train_data = keras.preprocessing.sequence.pad_sequences(
    train_data, # list of list
    value = word_index['<PAD>'], # padding填充的数值
    padding = 'post',            # post, pre:post表示在句子的后面进行padding，pre表示在句子的前面进行padding
    maxlen = max_length)

test_data = keras.preprocessing.sequence.pad_sequences(
    test_data, # list of list
    value = word_index['<PAD>'],
    padding = 'post', # post, pre
    maxlen = max_length)

embedding_dim = 16
batch_size = 512

bi_rnn_model = keras.models.Sequential([
    keras.layers.Embedding(vocab_size, embedding_dim, input_length = max_length),
    keras.layers.Bidirectional(keras.layers.LSTM(units = 32, return_sequences = False)),
    keras.layers.Dense(32, activation = 'relu'),
    keras.layers.Dense(1, activation='sigmoid'),
])

bi_rnn_model.summary(