zoukankan      html  css  js  c++  java
  • 二分类问题

    二分类问题

    首先进行数据处理:

    将读入的数据转成向量,将整数序列编码为二维矩阵

    def v(sequences, dimension=10000):
        results = np.zeros((len(sequences), dimension))
        for i, sequence in enumerate(sequences):
            results[i, sequence] = 1.
        return results
    x_train = v(train_data)
    x_test = v(test_data)
    

    标签同时也要向量化:

    y_train = np.asarray(train_labels).astype('float32')
    y_test = np.asarray(test_labels).astype('float32')
    

    初始化、编译、添加层

    model = models.Sequential()
    model.add(layers.Dense(16,activation='relu',input_shape=(10000,)))
    model.add(layers.Dense(16,activation='relu'))
    model.add(layers.Dense(1,activation='sigmoid'))
    model.compile(optimizer='rmsprop',loss='binary_crossentropy',metrics=['accuracy'])
    model.fit(x_train,y_train,epochs=4,batch_size=512)
    results = model.evaluate(x_test,y_test)
    

    binary_crossentropy 作为二分类的损失函数

    metrics=['accuracy'] 监控精度

    optimizer='rmsprop' 作为优化器

    import tensorflow as tf
    import numpy as np
    from keras.datasets import imdb
    from keras import models
    from keras import layers
    def v(sequences, dimension=10000):
        results = np.zeros((len(sequences), dimension))
        for i, sequence in enumerate(sequences):
            results[i, sequence] = 1.
        return results
    (train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
    x_train = v(train_data)
    x_test = v(test_data)
    y_train = np.asarray(train_labels).astype('float32')
    y_test = np.asarray(test_labels).astype('float32')
    model = models.Sequential()
    model.add(layers.Dense(16,activation='relu',input_shape=(10000,)))
    model.add(layers.Dense(16,activation='relu'))
    model.add(layers.Dense(1,activation='sigmoid'))
    model.compile(optimizer='rmsprop',loss='mse',metrics=['accuracy'])
    model.fit(x_train,y_train,epochs=4,batch_size=512)
    results = model.evaluate(x_test,y_test)
    
  • 相关阅读:
    <style>的scope属性
    scrollIntoView的使用
    需要学习的内容列表
    react生命周期
    JS对象-不可扩展对象、密封对象、冻结对象
    神策埋点
    Django初识
    MySQL的sql_mode模式说明及设置
    MySQL的逻辑查询语句的执行顺序
    MySQL行(记录)的详细操作
  • 原文地址:https://www.cnblogs.com/strategist-614/p/12996588.html
Copyright © 2011-2022 走看看