Tensorflow：搭建全连接神经网络（完整代码）

最近在学图像分类识别，而说到图像的分类识别就不得不提起神经网络，而tensorflow则是搭建神经网络的神器，故本人近段时间在一直学tensorflow，写这篇博客目的就是为了记录和总结自己学习tensorflow搭建简单全连接神经网络的心得和方法

首先是基本步骤

第一步：导入各种包和数据

第二步：定义训练参数

第三步：定义网络参数

第四步：定义网络结构

第五步：创建网络及定义损失函数和优化器

第六步：创建会话，启动计算图

 

然后是分步介绍

第一步：导入各种包和数据

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./data/", one_hot=True)

     第一行是导入tensorflow包，第二和第三行是导入MNIST数据集  

 

第二步：定义训练参数

step = 5000
learning_rate = 0.001
batch = 128

step：网络迭代次数，5000代表网络迭代训练5000次

learning_rate：学习率，具体可以搜索梯度下降算法

batch：每次迭代输入网络的数据大小，128表示每次训练输入128张图片

 

第三步：定义网络参数

x = tf.placeholder(tf.float32,shape=[None,784])
y = tf.placeholder(tf.float32,shape=[None,10])

w1 = tf.Variable(tf.random_normal([784,256]))
w2 = tf.Variable(tf.random_normal([256,256]))
w_out = tf.Variable(tf.random_normal([256,10]))

b1 = tf.Variable(tf.random_normal([256]))
b2 = tf.Variable(tf.random_normal([256]))
b_out = tf.Variable(tf.random_normal([10]))

x，y占位符定义了输入数据的形状，x是图片输入，y是标签输入，后面的变量定义了网络中神经元的形状

 

第四步：定义网络结构

def Fully_neural_network(X):
    
    layer_1 = tf.nn.relu(tf.add(tf.matmul(X,w1),b1))
    layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1,w2),b2))
    layer_out = tf.matmul(layer_2,w_out)+b_out
    
    return layer_out

以一个函数来定义网络结构

 

第五步：创建网络及定义损失函数和优化器

net_out = Fully_neural_network(x) 

pre = tf.nn.softmax(net_out)

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=net_out,labels = y )) 
 
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate)

train_op = optimizer.minimize(loss)


correct_pre = tf.equal(tf.argmax(pre,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pre,tf.float32))

net_out: 网络输出

pre: 网络预测

loss: 损失函数

optimizer: 优化器

correct_pre: 对网络预测与真实标签对比

accuracy：网络预测的正确率

 

第六步：创建会话，启动计算图

 #定义全部变量初始化的节点
init = tf.global_variables_initializer()

 #创建会话
with tf.Session() as sess:      
        
    #全局变量初始化
    sess.run(init)                       
    
    #开始训练
    for i in range(1,step+1):      
        #读入数据      
        batch_x, batch_y = mnist.train.next_batch(batch)
        #启动计算图，喂入数据
        sess.run(train_op, feed_dict={x: batch_x, y: batch_y})
        #没训练100次打印loss和accuracy
        if i % 100 == 0 or i == 1:
            l, acc = sess.run([loss, accuracy], feed_dict={x: batch_x,
                                                                 y: batch_y})
            print("Step " + str(i) + ", Minibatch Loss= " + "{:.4f}".format(l) + ", Training Accuracy= " + "{:.3f}".format(acc))
            
    print("Optimization Finished!")

    # Calculate accuracy for MNIST test images
    print("Testing Accuracy:", \
        sess.run(accuracy, feed_dict={x: mnist.test.images,
                                      y: mnist.test.labels}))

完整代码

# -*- coding: utf-8 -*-
"""
Created on Wed Mar 27 10:46:42 2019

@author: wcx
"""

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./data/", one_hot=True)

step = 5000
learning_rate = 0.001
batch = 128

x = tf.placeholder(tf.float32,shape=[None,784])
y = tf.placeholder(tf.float32,shape=[None,10])

w1 = tf.Variable(tf.random_normal([784,256]))
w2 = tf.Variable(tf.random_normal([256,256]))
w_out = tf.Variable(tf.random_normal([256,10]))

b1 = tf.Variable(tf.random_normal([256]))
b2 = tf.Variable(tf.random_normal([256]))
b_out = tf.Variable(tf.random_normal([10]))

def Fully_neural_network(X):
    
    layer_1 = tf.nn.relu(tf.add(tf.matmul(X,w1),b1))
    layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1,w2),b2))
    layer_out = tf.matmul(layer_2,w_out)+b_out
    
    return layer_out

    
net_out = Fully_neural_network(x)

pre = tf.nn.softmax(net_out)



loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=net_out,labels = y )) 
 
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate)

train_op = optimizer.minimize(loss)


correct_pre = tf.equal(tf.argmax(pre,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pre,tf.float32))

init = tf.global_variables_initializer()


with tf.Session() as sess:
    
    sess.run(init)
    
    for i in range(1,step+1):
        batch_x, batch_y = mnist.train.next_batch(batch)
        sess.run(train_op, feed_dict={x: batch_x, y: batch_y})
        if i % 100 == 0 or i == 1:
            l, acc = sess.run([loss, accuracy], feed_dict={x: batch_x,
                                                                 y: batch_y})
            print("Step " + str(i) + ", Minibatch Loss= " + "{:.4f}".format(l) + ", Training Accuracy= " + "{:.3f}".format(acc))
            
    print("Optimization Finished!")

    # Calculate accuracy for MNIST test images
    print("Testing Accuracy:", \
        sess.run(accuracy, feed_dict={x: mnist.test.images,
                                      y: mnist.test.labels}))

结果