tensorflow实现MNIST数据集识别

1 MNIST介绍

MNIST是一个入门级的计算机视觉数据集，它包含各种手写数字图片。关于其详细讲解，详见：MNIST机器学习入门，英文版MNIST For ML Beginners 。如果对于代码中一些关于tensorflow的API不了解，可查找官网手册：All symbols in TensorFlow。

2.代码实现

代码中需要使用MNIST数据集，如果发现在代码里下载老是出现错误的话。建议直接下载，放到当前运行目录下即可（包括整个文件夹）。

my_mnist_softmax.py

# -*- coding: utf-8 -*-# @Time    : 17-11-27# @Author  : yeqiang19910412# @FileName: my_mnist_softmax.py# @Software: PyCharm Community Edition with python3.5 tensorflow1.4# @Blog    ：http://blog.csdn.net/yeqiang19910412/article/details/78646069import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data# Import datamnist = input_data.read_data_sets("MNIST_data/",one_hot=True)# Create the modelx = tf.placeholder(tf.float32, [None, 784])W = tf.Variable(tf.zeros([784, 10]))b = tf.Variable(tf.zeros([10]))y = tf.matmul(x, W) + b# Define loss and optimizery_ = tf.placeholder(tf.float32, [None, 10])cross_entropy = tf.reduce_mean(    tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)sess = tf.InteractiveSession()tf.global_variables_initializer().run()# Trainfor _ in range(1000):    batch_xs, batch_ys = mnist.train.next_batch(100)    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})# Test trained modelcorrect_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))print(sess.run(accuracy, feed_dict={x: mnist.test.images,                                    y_: mnist.test.labels}))

my_mnist_softmax.py 完整代码

my_mnist_multilayer_convolutional_network.py

# -*- coding: utf-8 -*-# @Time    : 17-11-27# @Author  : yeqiang19910412# @FileName: my_mnist_multilayer_convolutional_network.py# @Software: PyCharm Community Edition with python3.5 tensorflow1.4# @Blog    ：http://blog.csdn.net/yeqiang19910412/article/details/78646069import tensorflow as tf# 加载数据from tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/",one_hot=True)x = tf.placeholder(tf.float32, [None, 784])y_ = tf.placeholder(tf.float32, [None, 10])# 初始化卷积核的权重参数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)def conv2d(x, W):    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')def max_pool_2x2(x):    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],                        strides=[1, 2, 2, 1], padding='SAME')x_image = tf.reshape(x, [-1,28,28,1])# 第一个卷积层W_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)# 第二个卷积层W_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)W_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([1024])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)keep_prob = tf.placeholder(tf.float32)h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))with tf.Session() as sess:    sess.run(tf.global_variables_initializer())    for i in range(20000):        batch = mnist.train.next_batch(50)        if i % 100 == 0:            train_accuracy = accuracy.eval(feed_dict={                x: batch[0], y_: batch[1], keep_prob: 1.0})            print("step %d, training accuracy %g" % (i, train_accuracy))        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})    print('test accuracy %g' % accuracy.eval(feed_dict={        x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

my_mnist_multilayer_convolutional_network.py 完整代码

注意：这其中还涉及到卷积神经网络的一些基本概念，可以参看 CS231n课程卷积神经网络笔记，英文版CS231n Convolutional Neural Networks for Visual Recognition

接下来要结合tensorboard

参考文献：
1.[tensorflow在mnist集上的使用示例（一）](http://blog.csdn.net/nnnnnnnnnnnny/article/details/56845456
主要贡献在于两个程序的源代码

2.Tensorflow学习笔记(4)-mnist(Multilayer_Convolutional_Network)
主要贡献在于my_mnist_multilayer_convolutional_network.py 的详细解读