八、（1）神经网络——简单神经网络，手写数字预测。

八、（1）神经网络——简单神经网络，手写数字预测。

本文通过预测手写数字来练习简单的神经网络。主要步骤为训练模型、保存模型、预测数据集、将数据集转图片、将图片转成数据集格式。

数据集下载地址：http://yann.lecun.com/exdb/mnist/

第一步：训练模型并保存。

 # -*- coding: utf-8 -*-
"""
Created on Mon May 27 23:55:27 2019

@author: sun
"""

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#0为预测,1为测试。
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_integer("is_train", 1, "指定程序是预测还是训练")



def full_connected():

    # 获取真实的数据，将下载好的数据放入指定路径
    mnist = input_data.read_data_sets("./data/mnist/input_data/", one_hot=True)

    # 1、建立数据的占位符 x [None, 784]    y_true [None, 10]
    with tf.variable_scope("data"):
        x = tf.placeholder(tf.float32, [None, 784])

        y_true = tf.placeholder(tf.int32, [None, 10])

    # 2、建立一个全连接层的神经网络 w [784, 10]   b [10]
    with tf.variable_scope("fc_model"):
    
        # 随机初始化权重和偏置
        weight = tf.Variable(tf.random_normal([784, 10], mean=0.0, stddev=1.0), name="w")

        bias = tf.Variable(tf.constant(0.0, shape=[10]))

        # 预测None个样本的输出结果matrix [None, 784]* [784, 10] + [10] = [None, 10]
        y_predict = tf.matmul(x, weight) + bias

    # 3、求出所有样本的损失，然后求平均值
    with tf.variable_scope("soft_cross"):

        # 求平均交叉熵损失
        loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true, logits=y_predict))

    # 4、梯度下降求出损失
    with tf.variable_scope("optimizer"):

        train_op = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

    # 5、计算准确率
    with tf.variable_scope("acc"):

        equal_list = tf.equal(tf.argmax(y_true, 1), tf.argmax(y_predict, 1))

        # equal_list  None个样本   [1, 0, 1, 0, 1, 1,..........]
        accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))
    
    # 收集变量 单个数字值收集
    loss_summary = tf.summary.scalar("losses", loss)
    accuracy_summary = tf.summary.scalar("acc", accuracy)

    # 高纬度变量收集
    weight_summary = tf.summary.histogram("weightes", weight)
    bias_summary = tf.summary.histogram("biases", bias)
    
    # 定义一个初始化变量的op
    init_op = tf.global_variables_initializer()
    
        # 定义一个合并变量de op
    merged = tf.summary.merge([loss_summary,accuracy_summary,weight_summary,bias_summary])
    
    # 创建一个saver
    saver = tf.train.Saver()
    
    # 开启会话去训练
    with tf.Session() as sess:
        # 初始化变量
        sess.run(init_op)

        # 建立events文件，然后写入
        filewriter = tf.summary.FileWriter("./tmp/summary/test/", graph=sess.graph)
        
        if FLAGS.is_train == 1:
            
        # 迭代步数去训练，更新参数预测
            for i in range(2000):

                # 取出真实存在的特征值和目标值
                mnist_x, mnist_y = mnist.train.next_batch(50)

                # 运行train_op训练
                sess.run(train_op, feed_dict={x: mnist_x, y_true: mnist_y})


                # 写入每步训练的值
                summary = sess.run(merged, feed_dict={x: mnist_x, y_true: mnist_y})

                filewriter.add_summary(summary, i)

                print("训练第%d步,准确率为:%f" % (i, sess.run(accuracy, feed_dict={x: mnist_x, y_true: mnist_y})))
  
            # 保存模型
            saver.save(sess, "./tmp/ckpt/fc_model")
        else:
            # 第一步中，设置为0则运行该部分代码，加载模型
            saver.restore(sess, "./tmp/ckpt/fc_model")

            # 如果是0，做出预测
            for i in range(100):

                # 每次测试一张图片 [0,0,0,0,0,1,0,0,0,0]
                x_test, y_test = mnist.test.next_batch(1)

                print("第%d张图片，手写数字图片目标是:%d, 预测结果是:%d" % (
                    i,
                    tf.argmax(y_test, 1).eval(),
                    tf.argmax(sess.run(y_predict, feed_dict={x: x_test, y_true: y_test}), 1).eval()
                ))

            
    return None
            
            
if __name__ == "__main__":
    full_connected() 

运行结果如图示：

在保存模型的路径中查看保存的模型：

第二步：加载模型预测数据集。代码只需要将第一步代码中的“1”改为“0”即可。

运行结果如图示：

第三步：（1）将数据集转为图片查看。

# -*- coding: utf-8 -*-
"""
Created on Tue May 28 00:23:16 2019

@author: sun
"""

import numpy as np
import struct
from PIL import Image
import os

 #指定测试集路径
data_file = 't10k-images.idx3-ubyte'
# It's 7840016B, but we should set to 7840000B
data_file_size = 7840016
data_file_size = str(data_file_size - 16) + 'B'
 
data_buf = open(data_file, 'rb').read()
 
magic, numImages, numRows, numColumns = struct.unpack_from(
    '>IIII', data_buf, 0)
datas = struct.unpack_from(
    '>' + data_file_size, data_buf, struct.calcsize('>IIII'))
datas = np.array(datas).astype(np.uint8).reshape(
    numImages, 1, numRows, numColumns)
 
label_file = 't10k-labels.idx1-ubyte'
 
# It's 10008B, but we should set to 10000B
label_file_size = 10008
label_file_size = str(label_file_size - 8) + 'B'
 
label_buf = open(label_file, 'rb').read()
 
magic, numLabels = struct.unpack_from('>II', label_buf, 0)
labels = struct.unpack_from(
    '>' + label_file_size, label_buf, struct.calcsize('>II'))
labels = np.array(labels).astype(np.int64)
 
datas_root = 'mnist_test'
if not os.path.exists(datas_root):
    os.mkdir(datas_root)
 
for i in range(10):
    file_name = datas_root + os.sep + str(i)
    if not os.path.exists(file_name):
        os.mkdir(file_name)
 
for ii in range(numLabels):
    img = Image.fromarray(datas[ii, 0, 0:28, 0:28])
    label = labels[ii]
    file_name = datas_root + os.sep + str(label) + os.sep + \
        'mnist_test_' + str(ii) + '.png'
    img.save(file_name)

每个数字都被存储到对应的一个文件夹中，运行结果如图示：

（2）将数据集转为图片和对应的标签txt

from PIL import Image
import struct


def read_image(filename):
    f = open(filename,'rb')
    index = 0
    buf = f.read()
    f.close()
    magic, images, rows, columns = struct.unpack_from('>IIII' , buf , index)
    index += struct.calcsize('>IIII')

    for i in range(images):
        image = Image.new('L', (columns, rows))
        for x in range(rows):
            for y in range(columns):
                image.putpixel((y, x), int(struct.unpack_from('>B', buf, index)[0]))
                index += struct.calcsize('>B')

        print('save ' + str(i) + 'image')
        image.save(r'C:\Users\sun\Desktop\论文\算法代码\深度学习算法\神经网络简单\dataimg\img' + str(i) + '.png')


def read_label(filename, saveFilename):
    f = open(filename, 'rb')
    index = 0
    buf = f.read()
    f.close()
    magic, labels = struct.unpack_from('>II' , buf , index)
    index += struct.calcsize('>II')
    labelArr = [0] * labels
    for x in range(labels):
        labelArr[x] = int(struct.unpack_from('>B', buf, index)[0])
        index += struct.calcsize('>B')
        save = open(saveFilename, 'w')
        save.write(','.join(map(lambda x: str(x), labelArr)))
        save.write('\n')
        save.close()
        print('save labels success')


if __name__ == '__main__':
     read_image(r'C:\Users\sun\Desktop\论文\算法代码\深度学习算法\神经网络简单\data\input_data\t10k-images.idx3-ubyte')
     read_label(r'C:\Users\sun\Desktop\论文\算法代码\深度学习算法\神经网络简单\data\input_data\t10k-labels.idx1-ubyte', r'C:\Users\sun\Desktop\论文\算法代码\深度学习算法\神经网络简单\label.txt')
     

运行结果如图示：

第四步：将图片转为数据集格式

该部分代码参考链接https://www.cnblogs.com/aodu/p/9487414.html

搞定收工。

“☺☺☺ 若本篇文章对你有一丝丝帮助，请帮顶、评论点赞，谢谢。☺☺☺”

↓↓↓↓