用Tensorflow实现卷积神经网络CNN

一时失言乱红尘 2022-05-26 23:43 286阅读 0赞

# 一、数据准备 #

实验数据使用MNIST数据集。  
MNIST 数据集已经是一个被”嚼烂”了的数据集, 很多教程都会对它”下手”, 几乎成为一个 “典范”。

在很多tensorflow教程中，用下面这一句下载mnist数据集：

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

但实际运行时根本无法通过网络下载，解决方案就是手工下载数据，然后直接导入使用。

下载地址：[http://yann.lecun.com/exdb/mnist/][http_yann.lecun.com_exdb_mnist]  
4个文件，注意下载后不需要解压。

如果把上述下载的文件放在与运行的.py文件同一个目录下，那么导入数据的代码是这样的：

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

# 二、代码 #

import tensorflow as tf
    from tensorflow.examples.tutorials.mnist import input_data
    # number 1 to 10 data
    mnist = input_data.read_data_sets('./', one_hot=True)
    
    def compute_accuracy(v_xs, v_ys):
        global prediction
        y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
        correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
        return result
    
    # 产生随机变量，符合 normal 分布
    # 传递 shape 就可以返回weight和bias的变量
    def weight_variable(shape):
        initial = tf.truncated_normal(shape, stddev=0.1)    
        return tf.Variable(initial)                         
    
    def bias_variable(shape):
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)
    
    # 定义2维的 convolutional 图层
    def conv2d(x, W):
        # stride [1, x_movement, y_movement, 1]
        # Must have strides[0] = strides[3] = 1
        # strides 就是跨多大步抽取信息
        return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')     
    
    # 定义 pooling 图层
    def max_pool_2x2(x):
        # stride [1, x_movement, y_movement, 1]
        # 用pooling对付跨步大丢失信息问题
        return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')        
    
    # define placeholder for inputs to network
    xs = tf.placeholder(tf.float32, [None, 784])        # 784＝28x28
    ys = tf.placeholder(tf.float32, [None, 10])
    keep_prob = tf.placeholder(tf.float32)
    x_image = tf.reshape(xs, [-1, 28, 28, 1])           # 最后一个1表示数据是黑白的
    # print(x_image.shape) # [n_samples, 28,28,1]
    
    ## 1. conv1 layer ##
    # 把x_image的厚度1加厚变成了32
    W_conv1 = weight_variable([5, 5, 1, 32])                # patch 5x5, in size 1, out size 32
    b_conv1 = bias_variable([32])
    # 构建第一个convolutional层，外面再加一个非线性化的处理relu
    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)            # output size 28x28x32
    # 经过pooling后，长宽缩小为14x14
    h_pool1 = max_pool_2x2(h_conv1)                                     # output size 14x14x32
    
    ## 2. conv2 layer ##
    # 把厚度32加厚变成了64
    W_conv2 = weight_variable([5,5, 32, 64])                # patch 5x5, in size 32, out size 64
    b_conv2 = bias_variable([64])
    # 构建第二个convolutional层
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)            # output size 14x14x64
    # 经过pooling后，长宽缩小为7x7
    h_pool2 = max_pool_2x2(h_conv2)                                     # output size 7x7x64
    
    ## 3. func1 layer ##
    # 飞的更高变成1024
    W_fc1 = weight_variable([7*7*64, 1024])
    b_fc1 = bias_variable([1024])
    # [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
    # 把pooling后的结果变平
    h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
    
    ## 4. func2 layer ##
    # 最后一层，输入1024，输出size 10，用 softmax 计算概率进行分类的处理
    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])
    prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
    
    
    # the error between prediction and real data
    cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                                  reduction_indices=[1]))       # loss
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
    
    sess = tf.Session()
    # important step
    sess.run(tf.global_variables_initializer())
    
    for i in range(1000):
        batch_xs, batch_ys = mnist.train.next_batch(100)
        sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
        if i % 50 == 0:
            print(compute_accuracy(
                mnist.test.images, mnist.test.labels))

运行结果：

![result.png][]

# 三、Github代码下载 #

[下载][Link 1]

# 四、参考 #

[http://v.youku.com/v\_show/id\_XMTYyMTUyMjc0OA==.html?spm=a2hzp.8253869.0.0][http_v.youku.com_v_show_id_XMTYyMTUyMjc0OA_.html_spm_a2hzp.8253869.0.0]

[https://github.com/MorvanZhou/tutorials/tree/master/tensorflowTUT/tf18\_CNN3][https_github.com_MorvanZhou_tutorials_tree_master_tensorflowTUT_tf18_CNN3]

[https://www.jianshu.com/p/e2f62043d02b][https_www.jianshu.com_p_e2f62043d02b]

[https://blog.csdn.net/i8088/article/details/79126150][https_blog.csdn.net_i8088_article_details_79126150]

> 更多内容请关注微信公众号  
> ![wechat\_public.jpg][wechat_public.jpg]

[http_yann.lecun.com_exdb_mnist]: http://yann.lecun.com/exdb/mnist/
[result.png]: /images/20220527/823d772ae467496ab85f8a086236fbf5.png
[Link 1]: https://github.com/zhenghaishu/MachineLearning/tree/master/CNN
[http_v.youku.com_v_show_id_XMTYyMTUyMjc0OA_.html_spm_a2hzp.8253869.0.0]: http://v.youku.com/v_show/id_XMTYyMTUyMjc0OA==.html?spm=a2hzp.8253869.0.0
[https_github.com_MorvanZhou_tutorials_tree_master_tensorflowTUT_tf18_CNN3]: https://github.com/MorvanZhou/tutorials/tree/master/tensorflowTUT/tf18_CNN3
[https_www.jianshu.com_p_e2f62043d02b]: https://www.jianshu.com/p/e2f62043d02b
[https_blog.csdn.net_i8088_article_details_79126150]: https://blog.csdn.net/i8088/article/details/79126150
[wechat_public.jpg]: /images/20220527/422889ead9b34ae68fb9956a5bb52ee3.png