目录
问题描述:
使用keras中的顺序模型来分类keras电影评论数据集的二分类问题
代码实现:
1.引入依赖,加载数据
from cProfile import label
from keras.datasets import imdb
import numpy as np
from keras import models
from keras import layers
from keras import optimizers,optimizer_v1,optimizer_v2
import matplotlib.pyplot as plt
from keras import losses
from keras import metrics
#仅保留数据中前10000单词
(train_data,train_labels),(test_data,test_labels) = imdb.load_data(num_words=10000)
2.数据处理和数据编码
word_index = imdb.get_word_index()
#键值颠倒,将整数索引映射为单词
reverse_word_index = dict(
[(value,key) for (key,value) in word_index.items()]
)
decoded_review = ''.join([reverse_word_index.get(i-3,'?')for i in train_data[0]])
#编码成为二进制矩阵
def vectorize_sequences(sequences,dimension=10000):
results = np.zeros((len(sequences),dimension))
for i ,sequence in enumerate(sequences):
results[i,sequence] = 1
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
#标签向量化
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')
3.构建网络
'''
参考
1.#编译模型
#bianary_crossentropy----二元交叉熵
model.compile(optimize