mnist实例应该是深度学习的"hello word",几乎每一个深度学习框架都有Mnist的入门例程。
在前面两篇博文,安装python3.6+tensorflow1.4.0+pycharm的基础上,应该已经可以正常运行tensorflow的代码了。
话不多说,直接上代码。
一、用简单的神经网络来训练和测试 详细介绍可参考这篇博文
from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf dir='\MNIST_data'#最好填绝对路径 # 1.Import data mnist = input_data.read_data_sets(dir, one_hot=True) # print data information print (mnist.train.images.shape,mnist.train.labels.shape) print(mnist.test.images.shape, mnist.train.labels.shape) print(mnist.validation.images.shape, mnist.validation.labels.shape) # 2.Create the model x = 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 # y=wx+b # Define loss and optimizer y_ = 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(0.01).minimize(cross_entropy) # Init model sess = tf.InteractiveSession() tf.global_variables_initializer().run() correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # Train for i in range(10000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys}) if(i%100==0): print(i,end=' ') print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})) # Test trained model print(sess.run(accuracy, feed_dict={x: mnist.test.images,y_: mnist.test.labels}))
二、卷积神经网络来训练
from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf dir = '\MNIST_data' # 最好填绝对路径 # 1.Import data mnist = input_data.read_data_sets(dir, one_hot=True) # print data information print(mnist.train.images.shape, mnist.train.labels.shape) print(mnist.test.images.shape, mnist.train.labels.shape) print(mnist.validation.images.shape, mnist.validation.labels.shape) x = tf.placeholder(tf.float32, [None, 784]) y_ = tf.placeholder(tf.float32, [None, 10]) sess = tf.InteractiveSession() 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') #第一层卷积 W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) x_image = tf.reshape(x, [-1, 28, 28, 1]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1) #第二层卷积 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) #密集连接层 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) #dropput keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #输出层 W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2 #训练和评估模型 cross_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)) sess.run(tf.global_variables_initializer()) for i in range(2000): 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})