mnist识别python代码（基于tensorflow）

import tensorflow as tf import random from ext_data import * import scipy.io as sio from tensorflow.examples.tutorials.mnist import input_data # mnist数据集下载到此目录下 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) # hyper parameters learning_rate = 0.002 training_epochs = 40 batch_size = 100 SAVE_MODEL_PATH = "model/save_net.ckpt" # input place holders X = tf.placeholder(tf.float32, [None, 784]) X_img = tf.reshape(X, [-1, 28, 28, 1]) # img 28x28x1 (black/white) Y = tf.placeholder(tf.float32, [None, 10]) drop_rate = tf.placeholder(tf.float32) W1 = tf.Variable(tf.random_normal([5, 5, 1, 6], stddev=0.01)) b1 = tf.Variable(tf.random_normal([6])) L1 = tf.nn.conv2d(X_img, W1, strides=[1, 1, 1, 1], padding='VALID') L1 = tf.nn.relu(L1 + b1) L1 = tf.nn.avg_pool(L1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') W2 = tf.Variable(tf.random_normal([5, 5, 6, 16], stddev=0.01)) b2 = tf.Variable(tf.random_normal([16])) L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding='VALID') L2 = tf.nn.relu(L2 + b2) L2 = tf.nn.avg_pool(L2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') L2_flat = tf.reshape(L2, [-1, 4 * 4 * 16]) L2_drop = tf.nn.dropout(L2_flat,drop_rate) W3 = tf.Variable(tf.random_normal([4*4*16, 10], stddev=0.01)) b3 = tf.Variable(tf.random_normal([10])) logits = tf.matmul(L2_drop, W3) + b3 cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits( logits=logits, labels=Y)) optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) #creat a saver saver = tf.train.Saver() # initialize with tf.Session() as sess: sess.run(tf.global_variables_initializer()) # train my model print('Learning started. It takes sometime.') for epoch in range(training_epochs): avg_cost = 0 total_batch = int(mnist.train.num_examples / batch_size) for i in range(total_batch): xs, ys = mnist.train.next_batch(batch_size) train_data = expend_training_data(xs, ys) batch_xs = train_data[:,0:784] batch_ys = train_data[:,784:] feed_dict = {X: batch_xs, Y: batch_ys, drop_rate:0.5} c, _ = sess.run([cost, optimizer], feed_dict=feed_dict) avg_cost += c / total_batch print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost)) print('Learning Finished!') # save the model saver.save(sess,SAVE_MODEL_PATH) # Test model and check accuracy correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) test_data = expend_training_data(mnist.test.images, mnist.test.labels) test_xs = test_data[:,0:784] test_ys = test_data[:,784:] print('Accuracy:', sess.run(accuracy, feed_dict={ X:test_xs , Y: test_ys, drop_rate:1}))