MNIST数据集介绍
MNIST数据集中包含了各种各样的手写数字图片,数据集的官网是:http://yann.lecun.com/exdb/mnist/index.html,我们可以从这里下载数据集。使用如下的代码对数据集进行加载:
from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
运行上述代码会自动下载数据集并将文件解压在MNIST_data文件夹下面。代码中的one_hot=True,表示将样本的标签转化为one_hot编码。
MNIST数据集中的图片是28*28的,每张图被转化为一个行向量,长度是28*28=784,每一个值代表一个像素点。数据集*有60000张手写数据图片,其中55000张训练数据,5000张测试数据。
在MNIST中,mnist.train.images是一个形状为[55000, 784]的张量,其中的第一个维度是用来索引图片,第二个维度图片中的像素。MNIST数据集包含有三部分,训练数据集,验证数据集,测试数据集(mnist.validation)。
标签是介于0-9之间的数字,用于描述图片中的数字,转化为one-hot向量即表示的数字对应的下标为1,其余的值为0。标签的训练数据是[55000,10]的数字矩阵。
下面定义了一个简单的网络对数据集进行训练,代码如下:
import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data import matplotlib.pyplot as plt mnist = input_data.read_data_sets('MNIST_data', one_hot=True) tf.reset_default_graph() x = tf.placeholder(tf.float32, [None, 784]) y = tf.placeholder(tf.float32, [None, 10]) w = tf.Variable(tf.random_normal([784, 10])) b = tf.Variable(tf.zeros([10])) pred = tf.matmul(x, w) + b pred = tf.nn.softmax(pred) cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(pred), reduction_indices=1)) learning_rate = 0.01 optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) training_epochs = 25 batch_size = 100 display_step = 1 save_path = 'model/' saver = tf.train.Saver() with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for epoch in range(training_epochs): avg_cost = 0 total_batch = int(mnist.train.num_examples/batch_size) for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) _, c = sess.run([optimizer, cost], feed_dict={x:batch_xs, y:batch_ys}) avg_cost += c / total_batch if (epoch + 1) % display_step == 0: print('epoch= ', epoch+1, ' cost= ', avg_cost) print('finished') correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) print('accuracy: ', accuracy.eval({x:mnist.test.images, y:mnist.test.labels})) save = saver.save(sess, save_path=save_path+'mnist.cpkt') print(" starting 2nd session ...... ") with tf.Session() as sess: sess.run(tf.global_variables_initializer()) saver.restore(sess, save_path=save_path+'mnist.cpkt') correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) print('accuracy: ', accuracy.eval({x: mnist.test.images, y: mnist.test.labels})) output = tf.argmax(pred, 1) batch_xs, batch_ys = mnist.test.next_batch(2) outputval= sess.run([output], feed_dict={x:batch_xs, y:batch_ys}) print(outputval) im = batch_xs[0] im = im.reshape(-1, 28) plt.imshow(im, cmap='gray') plt.show() im = batch_xs[1] im = im.reshape(-1, 28) plt.imshow(im, cmap='gray') plt.show()