本篇博客主要介绍通过TensorFlow实现MNIST数据集的手写数字识别。
准备数据:
首先需要获取数据,可以通过以下代码进行获取:
from tensorflow.examples.tutorials.mnist import input_data
# 获取数据,number 1 to 10
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
注:由于使用以上代码获取数据经常获取不到,因此需要先对数据进行下载,在代码同目录下创建MNIST_data目录,并在http://yann.lecun.com/exdb/mnist/下载下面四个文件,不用解压直接放到MNIST_data目录下。
搭建网络:
MNIST数据集包含了55000张训练图片,每张图片的分辨率为28x28,即网络的输入为28x28=784个像素,黑色的部分值值为1,白色的部分值为0
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
每张图片表示一个数字,即输出为10类,如输出为[0 1 0 0 0 0 0 0 0 0]表示数字1
ys = tf.placeholder(tf.float32, [None, 10])
计算损失:
激活函数选用softmax,softmax经常用于classification(分类)。
prediction = add_layer(xs, 784, 10, activation_function=tf.nn.softmax)
损失函数选用交叉熵函数,交叉熵函数用来衡量预测值和真实值之间的相似程度。如果完全相同,他们的交叉熵为0.
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)选用梯度下降算法更新参数。
完整代码:
# encoding:utf-8 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # 获取数据,number 1 to 10 mnist = input_data.read_data_sets('MNIST_data', one_hot=True) def add_layer(inputs, in_size, out_size, activation_function=None): with tf.name_scope('layer'): with tf.name_scope('weights'): W = tf.Variable(tf.random_normal([in_size, out_size]), name='W') with tf.name_scope('bias'): b = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b') with tf.name_scope('Wx_plus_b'): Wx_plus_b = tf.matmul(inputs, W) + b if activation_function is None: outputs = Wx_plus_b else: outputs = activation_function(Wx_plus_b) return outputs def compute_accuracy(v_xs, v_ys): global prediction y_pre = sess.run(prediction, feed_dict={xs: v_xs}) corrct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1)) accuracy = tf.reduce_mean(tf.cast(corrct_prediction, tf.float32)) result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys}) return result # define placeholder for inputs to network xs = tf.placeholder(tf.float32, [None, 784]) # 28x28 ys = tf.placeholder(tf.float32, [None, 10]) # add output layer, softmax通常用于做classification prediction = add_layer(xs, 784, 10, activation_function=tf.nn.softmax) # the error between prediction and real data cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1])) train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy) sess = tf.Session() # important step sess.run(tf.initialize_all_variables()) 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}) if i % 50 == 0: print(compute_accuracy( mnist.test.images, mnist.test.labels ))
运行结果:
Extracting MNIST_data\train-images-idx3-ubyte.gz Extracting MNIST_data\train-labels-idx1-ubyte.gz Extracting MNIST_data\t10k-images-idx3-ubyte.gz Extracting MNIST_data\t10k-labels-idx1-ubyte.gz 2018-07-09 15:15:20.559165: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE instructions, but these are available on your machine and could speed up CPU computations. 2018-07-09 15:15:20.559887: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE2 instructions, but these are available on your machine and could speed up CPU computations. 2018-07-09 15:15:20.560547: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations. 2018-07-09 15:15:20.561141: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations. 2018-07-09 15:15:20.561767: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations. 2018-07-09 15:15:20.562236: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. 2018-07-09 15:15:20.562993: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations. 2018-07-09 15:15:20.563277: W c:\l\tensorflow_1501918863922\work\tensorflow-1.2.1\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations. WARNING:tensorflow:From D:\Users\Seavan_CC\Anaconda3\lib\site-packages\tensorflow\python\util\tf_should_use.py:170: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02. Instructions for updating: Use `tf.global_variables_initializer` instead. 0.0908 0.636 0.733 0.7702 0.7961 0.8105 0.824 0.8305 0.838 0.8426 0.8491 0.8514 0.8518 0.8556 0.8625 0.8645 0.8666 0.8704 0.8735 0.8699