3层全连接神经网络

输入层是28x28=784个节点
隐层500个结点
输出层10个结点
采用了L2正则化，指数衰减学习率，滑动平均优化后的结果正确率
98.3%左右

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import os
import warnings
warnings.filterwarnings("ignore")
os.environ["TF_CPP_MIN_LOG_LEVEL"] = '3'

input_node = 784   #输入层节点数
output_node = 10   #输出层节点数
layer1_node = 500  # 隐层节点数
batch_size = 100   #每次读取的数据量
learning_rate_base = 0.8
learning_rate_decay = 0.99
regularization_rate = 0.0001
traing_steps = 10000    #训练轮数
moving_average_decay = 0.99   #平滑指数


def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
    if avg_class is None:
        layer1 = tf.compat.v1.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
        return tf.matmul(layer1, weights2) + biases2
    else:
        layer1 = tf.compat.v1.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1))
                                       + avg_class.average(biases1))
        return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2)

def train(mnist):
    x = tf.compat.v1.placeholder(tf.float32, [None, input_node], name="x-input")
    y_ = tf.compat.v1.placeholder(tf.float32, [None, output_node], name="y-input")
    weights1 = tf.Variable(tf.random.truncated_normal([input_node, layer1_node], stddev=0.1))
    biases1 = tf.Variable(tf.constant(0.1, shape=[layer1_node]))
    weights2 = tf.Variable(tf.truncated_normal([layer1_node, output_node], stddev=0.1))
    biases2 = tf.Variable(tf.constant(0.1, shape=[output_node]))

    y = inference(x, None, weights1, biases1, weights2, biases2)

    global_step = tf.Variable(0, trainable=False)

    variable_average = tf.train.ExponentialMovingAverage(moving_average_decay, global_step)
    variable_averages_op = variable_average.apply(tf.compat.v1.trainable_variables())
    average_y = inference(x, variable_average, weights1, biases1, weights2, biases2)
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
    cross_entropy = tf.reduce_mean(cross_entropy)
    regularizer = tf.contrib.layers.l2_regularizer(regularization_rate)
    regularization = regularizer(weights1) + regularizer(weights2)
    loss = cross_entropy + regularization
    learning_rate = tf.compat.v1.train.exponential_decay(learning_rate_base, global_step, mnist.train.num_examples / batch_size,
                                               learning_rate_decay)

    train_step = tf.compat.v1.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([variable_averages_op,train_step]):
        train_op = tf.no_op(name='train')

    correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    with tf.compat.v1.Session() as sess:
        tf.compat.v1.global_variables_initializer().run()
        validata_feed = {x: mnist.validation.images, y_: mnist.validation.labels}
        test_feed = {x: mnist.test.images, y_: mnist.test.labels}
        for i in range(traing_steps):
            if i % 1000 == 0:
                validata_acc = sess.run(accuracy, feed_dict=validata_feed)
                print("After %d training steps,validation accuracy " "using average model is %g" % (i, validata_acc))
            xs, ys = mnist.train.next_batch(batch_size)
            sess.run(train_op, feed_dict={x: xs, y_: ys})
        test_acc = sess.run(accuracy, feed_dict=test_feed)
        print("After %d training steps,test accuracy " "using average model is %g" % (
            traing_steps, test_acc,))



mnist = input_data.read_data_sets("C:/Users/tang/Desktop/deeplearning/mnist数据集", one_hot=True)
train(mnist)

（跟书上结果一致）运行结果：

After 0 training steps,validation accuracy using average model is 0.0998
After 1000 training steps,validation accuracy using average model is 0.9764
After 2000 training steps,validation accuracy using average model is 0.9806
After 3000 training steps,validation accuracy using average model is 0.9818
After 4000 training steps,validation accuracy using average model is 0.9828
After 5000 training steps,validation accuracy using average model is 0.983
After 6000 training steps,validation accuracy using average model is 0.9836
After 7000 training steps,validation accuracy using average model is 0.9838
After 8000 training steps,validation accuracy using average model is 0.9838
After 9000 training steps,validation accuracy using average model is 0.9834
After 10000 training steps,test accuracy using average model is 0.9832