TensorFlow实现Logistic回归

技术  /  管理员 发布于 7年前   161

本文实例为大家分享了TensorFlow实现Logistic回归的具体代码，供大家参考，具体内容如下

1.导入模块

import numpy as npimport pandas as pdfrom pandas import Series,DataFramefrom matplotlib import pyplot as plt%matplotlib inline#导入tensorflowimport tensorflow as tf#导入MNIST(手写数字数据集)from tensorflow.examples.tutorials.mnist import input_data

2.获取训练数据和测试数据

import ssl ssl._create_default_https_context = ssl._create_unverified_contextmnist = input_data.read_data_sets('./TensorFlow',one_hot=True)test = mnist.testtest_images = test.imagestrain = mnist.trainimages = train.images

3.模拟线性方程

#创建占矩阵位符X,YX = tf.placeholder(tf.float32,shape=[None,784])Y = tf.placeholder(tf.float32,shape=[None,10])#随机生成斜率W和截距bW = tf.Variable(tf.zeros([784,10]))b = tf.Variable(tf.zeros([10]))#根据模拟线性方程得出预测值y_pre = tf.matmul(X,W)+b#将预测值结果概率化y_pre_r = tf.nn.softmax(y_pre)

4.构造损失函数

# -y*tf.log(y_pre_r) --->-Pi*log(Pi)  信息熵公式cost = tf.reduce_mean(-tf.reduce_sum(Y*tf.log(y_pre_r),axis=1))

5.实现梯度下降，获取最小损失函数

#learning_rate:学习率,是进行训练时在最陡的梯度方向上所采取的「步」长；learning_rate = 0.01optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

6.TensorFlow初始化，并进行训练

#定义相关参数#训练循环次数training_epochs = 25#batch 一批，每次训练给算法10个数据batch_size = 10#每隔5次，打印输出运算的结果display_step = 5#预定义初始化init = tf.global_variables_initializer()#开始训练with tf.Session() as sess:  #初始化  sess.run(init)  #循环训练次数  for epoch in range(training_epochs):    avg_cost = 0.    #总训练批次total_batch =训练总样本量/每批次样本数量    total_batch = int(train.num_examples/batch_size)    for i in range(total_batch):      #每次取出100个数据作为训练数据      batch_xs,batch_ys = mnist.train.next_batch(batch_size)      _, c = sess.run([optimizer,cost],feed_dict={X:batch_xs,Y:batch_ys})      avg_cost +=c/total_batch    if(epoch+1)%display_step == 0:      print(batch_xs.shape,batch_ys.shape)      print('epoch:','%04d'%(epoch+1),'cost=','{:.9f}'.format(avg_cost))  print('Optimization Finished!')  #7.评估效果  # Test model  correct_prediction = tf.equal(tf.argmax(y_pre_r,1),tf.argmax(Y,1))  # Calculate accuracy for 3000 examples  # tf.cast类型转换  accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))  print("Accuracy:",accuracy.eval({X: mnist.test.images[:3000], Y: mnist.test.labels[:3000]}))

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。