tensorflow实现卷积神经网(CNN),还加了个dropout

来自<Tensorflow实战>一书# 两个卷积　一个全连接层from tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tfmnist = input_data.read_data_sets("MNIST_data/", one_hot=True)sess = tf.InteractiveSession()# 有许多权重偏置要创建，先定义俩留着用def weight_variable(shape):    initial = tf.truncated_normal(shape, stddev= 0.1)  # 标准差0.1    return tf.Variable(initial)def bias_variable(shape):    initial = tf.constant(0.1,shape=shape)  # 偏置增加小正值防止死亡节点    return tf.Variable(initial)# 定义卷积层和池化层def conv2d(x, W):    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')  # 卷积的输出输入保持同样的尺寸  # strides[图片，长，宽，channel]def max_pool_2x2(x):    return tf.nn.max_pool(x,ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')# 定义输入空间x = tf.placeholder(tf.float32,[None, 784])y_ = tf.placeholder(tf.float32,[None,10])x_image = tf.reshape(x, [-1,28,28,1])# 第一个卷积层+池化W_conv1 = weight_variable([5,5,1,32])b_conv1 = bias_variable([32])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)# 第二个卷积层+池化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)# 连一个全连接层W_fc1 = weight_variable([7*7*64, 1024])b_fc1 = bias_variable([1024])h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])  # 把第二个卷积层的输出reshape成1Ｄ的h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)# Dropout层keep_prob = tf.placeholder(tf.float32)h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)# Softmax层W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)# Adam优化器＋cross entropy＋小学习速率cross_entropy =tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y_conv), reduction_indices=[1]))train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)# 评测准确率correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))# 训练tf.global_variables_initializer().run()for i in range(20000):    batch = mnist.train.next_batch(50)    if i%100 == 0:        train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 0.5})        print("step %d, training accuracy %g"%(i,train_accuracy))    train_step.run(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})# 全部训练完成　测试print("test accuracy ％g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))