TensorFlow实现Logistic回归

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 np
import pandas as pd
from pandas import Series,DataFrame

from matplotlib import pyplot as plt
%matplotlib inline

#导入tensorflow
import 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_context

mnist = input_data.read_data_sets('./TensorFlow',one_hot=True)

test = mnist.test
test_images = test.images

train = mnist.train
images = train.images

3.模拟线性方程

#创建占矩阵位符X,Y
X = 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b
W = 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 = 0.01
optimizer = 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三水点靠木。