zoukankan      html  css  js  c++  java
  • Tensorflow学习教程------利用卷积神经网络对mnist数据集进行分类_利用训练好的模型进行分类

    #coding:utf-8
    
    import tensorflow as tf
    from PIL import Image,ImageFilter
    from tensorflow.examples.tutorials.mnist import input_data
    
    def imageprepare(argv): # 该函数读一张图片,处理后返回一个数组,进到网络中预测
        """
        This function returns the pixel values.
        The imput is a png file location.
        """
        im = Image.open(argv).convert('L')
        width = float(im.size[0])
        height = float(im.size[1])
        newImage = Image.new('L', (28, 28), (255))  # creates white canvas of 28x28 pixels
    
        if width > height:  # check which dimension is bigger
            # Width is bigger. Width becomes 20 pixels.
            nheight = int(round((20.0 / width * height), 0))  # resize height according to ratio width
            if nheight == 0:  # rare case but minimum is 1 pixel
                nheight = 1
                # resize and sharpen
            img = im.resize((20, nheight), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
            wtop = int(round(((28 - nheight) / 2), 0))  # caculate horizontal pozition
            newImage.paste(img, (4, wtop))  # paste resized image on white canvas
        else:
            # Height is bigger. Heigth becomes 20 pixels.
            nwidth = int(round((20.0 / height * width), 0))  # resize width according to ratio height
            if (nwidth == 0):  # rare case but minimum is 1 pixel
                nwidth = 1
                # resize and sharpen
            img = im.resize((nwidth, 20), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
            wleft = int(round(((28 - nwidth) / 2), 0))  # caculate vertical pozition
            newImage.paste(img, (wleft, 4))  # paste resized image on white canvas
    
        # newImage.save("sample.png")
    
        tv = list(newImage.getdata())  # get pixel values
    
        # normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
        tva = [(255 - x) * 1.0 / 255.0 for x in tv]
        return tva
    def weight_variable(shape):
        initial = tf.truncated_normal(shape,stddev=0.1) #生成一个截断的正态分布
        return tf.Variable(initial)
    
    def bias_variable(shape):
        initial = tf.constant(0.1,shape = shape)
        return tf.Variable(initial)
    
    #卷基层
    def conv2d(x,W):
        return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
    #池化层
    def max_pool_2x2(x):
        return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
    #定义两个placeholder
    x = tf.placeholder(tf.float32, [None,784])
    #y = tf.placeholder(tf.float32,[None,10])
    
    #改变x的格式转为4D的向量[batch,in_height,in_width,in_channels]
    x_image = tf.reshape(x, [-1,28,28,1])
    
    #初始化第一个卷基层的权值和偏置
    W_conv1 = weight_variable([5,5,1,32]) #5*5的采样窗口 32个卷积核从一个平面抽取特征 32个卷积核是自定义的
    b_conv1 = bias_variable([32])  #每个卷积核一个偏置值
    
    #把x_image和权值向量进行卷积,再加上偏置值,然后应用于relu激活函数
    h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
    h_pool1 = max_pool_2x2(h_conv1) #进行max-pooling
    
    #初始化第二个卷基层的权值和偏置
    W_conv2 = weight_variable([5,5,32,64]) # 5*5的采样窗口 64个卷积核从32个平面抽取特征  由于前一层操作得到了32个特征图
    b_conv2 = bias_variable([64]) #每一个卷积核一个偏置值
    
    #把h_pool1和权值向量进行卷积 再加上偏置值 然后应用于relu激活函数
    h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
    h_pool2 = max_pool_2x2(h_conv2) #进行max-pooling
    
    #28x28的图片第一次卷积后还是28x28 第一次池化后变为14x14
    #第二次卷积后 变为14x14 第二次池化后变为7x7
    #通过上面操作后得到64张7x7的平面
    
    #初始化第一个全连接层的权值
    W_fc1 = weight_variable([7*7*64,1024])#上一层有7*7*64个神经元,全连接层有1024个神经元
    b_fc1 = bias_variable([1024]) #1024个节点
    
    #把第二个池化层的输出扁平化为一维
    h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
    #求第一个全连接层的输出
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
    
    #keep_prob用来表示神经元的输出概率
    keep_prob  = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
    
    #初始化第二个全连接层
    W_fc2 = weight_variable([1024,10])
    b_fc2 = bias_variable([10])
    
    #计算输出
    gailv = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2) 
    
    saver = tf.train.Saver()
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        saver.restore(sess,'/home/xxx/logs/mnistmodel-1')
        array = imageprepare('/home/xxx/logs/7.jpg') # 读一张包含数字的图片
        prediction = tf.argmax(gailv, 1) # 预测
        prediction = prediction.eval(feed_dict={x:[array],keep_prob:1.0},session=sess)
        print('The digits in this image is:%d' % prediction[0])

    结果 手写数字图片7被预测为7

    I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0 
    I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0:   Y 
    I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0)
    The digits in this image is:7
  • 相关阅读:
    centos7.6 安装与配置 MongoDB yum方式
    MongoDB 介绍
    centos 关闭selinux
    前端 HTML标签属性
    前端 HTML 标签嵌套规则
    前端 HTML 标签分类
    前端 HTML body标签相关内容 常用标签 表单标签 form里面的 input标签介绍
    前端 HTML body标签相关内容 常用标签 表单标签 form 表单控件分类
    前端 HTML form表单标签 select标签 option 下拉框
    POJ 1426
  • 原文地址:https://www.cnblogs.com/cnugis/p/7647471.html
Copyright © 2011-2022 走看看