MNIST數據集介紹html
MNIST數據集中包含了各類各樣的手寫數字圖片,數據集的官網是:http://yann.lecun.com/exdb/mnist/index.html,咱們能夠從這裏下載數據集。使用以下的代碼對數據集進行加載:網絡
from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
運行上述代碼會自動下載數據集並將文件解壓在MNIST_data文件夾下面。代碼中的one_hot=True,表示將樣本的標籤轉化爲one_hot編碼。session
MNIST數據集中的圖片是28*28的,每張圖被轉化爲一個行向量,長度是28*28=784,每個值表明一個像素點。數據集中共有60000張手寫數據圖片,其中55000張訓練數據,5000張測試數據。dom
在MNIST中,mnist.train.images是一個形狀爲[55000, 784]的張量,其中的第一個維度是用來索引圖片,第二個維度圖片中的像素。MNIST數據集包含有三部分,訓練數據集,驗證數據集,測試數據集(mnist.validation)。測試
標籤是介於0-9之間的數字,用於描述圖片中的數字,轉化爲one-hot向量即表示的數字對應的下標爲1,其他的值爲0。標籤的訓練數據是[55000,10]的數字矩陣。編碼
下面定義了一個簡單的網絡對數據集進行訓練,代碼以下:spa
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()