TF之LoR：基于tensorflow利用逻辑回归算LoR法实现手写数字图片识别提高准确率

TF之LoR：基于tensorflow利用逻辑回归算LoR法实现手写数字图片识别提高准确率

目录

​​输出结果​​

​​设计代码​​

---

输出结果

设计代码

#TF之LoR：基于tensorflow实现手写数字图片识别准确率

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np  
import matplotlib.pyplot as plt 

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
print(mnist)
 
#设置超参数
lr=0.001                      #学习率
training_iters=100       #训练次数
batch_size=100                #每轮训练数据的大小，如果一次训练5000张图片，电脑会卡死，分批次训练会更好
display_step=1

#tf Graph的输入
x=tf.placeholder(tf.float32, [None,784])
y=tf.placeholder(tf.float32, [None, 10])
 
#设置权重和偏置
w =tf.Variable(tf.zeros([784,10]))
b =tf.Variable(tf.zeros([10]))

#设定运行模式
pred =tf.nn.softmax(tf.matmul(x,w)+b)  #
#设置cost function为cross entropy
cost =tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred),reduction_indices=1))
#GD算法
optimizer=tf.train.GradientDescentOptimizer(lr).minimize(cost) 

#初始化权重
init=tf.global_variables_initializer() 
#开始训练
with tf.Session() as sess: 
    sess.run(init)
    avg_cost_list=[]
    for epoch in range(training_iters):  #输入所有训练数据
        avg_cost=0.
        total_batch=int(mnist.train.num_examples/batch_size)
    
        for i in range(total_batch): #遍历每个batch
……
        if (epoch+1) % display_step ==0:  #显示每次迭代日志
            print("迭代次数Epoch:","%04d" % (epoch+1),"下降值cost=","{:.9f}".format(avg_cost))
            avg_cost_list.append(avg_cost)
    print("Optimizer Finished!")
    print(avg_cost_list)
    
    #测试模型
    correct_prediction=tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
    accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
    print("Accuracy:",accuracy.eval({x:mnist.test.images[:3000],y:mnist.test.labels[:3000]}))
    
    xdata=np.linspace(0,training_iters,num=len(avg_cost_list))  
    plt.figure()  
    plt.plot(xdata,avg_cost_list,'r')
    plt.xlabel('训练轮数')
    plt.ylabel('损失函数')
    plt.title('TF之LiR：基于tensorflow实现手写数字图片识别准确率——Jason Niu')     
    plt.show()