使用TensorFlow识别手写数字（MNIST数据集）

参照《TensorFlow实战》实现，加上自己的理解

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# 载入数据集,使用one-hot编码
mnist = input_data.read_data_sets("/path/to/MNIST_data",one_hot=True)

#参数配置
INPUT_NODE = 784    # 输入层：图片像素
OUTPUT_NODE = 10    # 输出层：0-9

LAYER1_NODE = 500   # 隐藏层
BATCH_SIZE = 100    # 批尺寸

LEARNING_RATE_BASE = 0.8    # 学习率
LEARNING_RATE_DECAY = 0.99  # 学习率的衰减速率

REGULARIZATION_RATE = 0.0001    # 正则化项系数
TRAINING_STEPS = 10000          # 训练轮数
MOVING_AVERAGE_DECAY = 0.99     # 滑动平均衰减率

# 前向传播计算函数
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
    # 有无滑动平均(传递函数)
    if avg_class == None:
        layer1=tf.nn.relu(tf.matmul(input_tensor,weights1)+biases1)
        return tf.matmul(layer1, weights2) + biases2
    else:
        layer1 = tf.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)

# 训练模型的过程
def train(mnist):
    # 读入X（懒惰计算）
    x = tf.placeholder(tf.float32,[None,INPUT_NODE],name="x-input")
    # 读入Y_
    y_= tf.placeholder(tf.float32,[None,OUTPUT_NODE],name="y-input")

    # 生成隐藏层的参数
    weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE,LAYER1_NODE],stddev=0.1))
    biases1 = tf.Variable(tf.constant(0.1,shape=[LAYER1_NODE]))

    # 生成输出层参数
    weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE,OUTPUT_NODE],stddev=0.1))
    biases2 = tf.Variable(tf.constant(0.1,shape=[OUTPUT_NODE]))

    # 训练轮数
    global_step = tf.Variable(0, trainable=False)

    # 滑动平均类
    variable_averges = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)

    # 对所有trainable变量使用滑动平均
    variable_averges_op = variable_averges.apply(tf.trainable_variables())

    # 计算前向传播（不用滑动评价）
    y = inference(x, None, weights1, biases1, weights2, biases2)
    # 计算前向传播（滑动平均）
    average_y = inference(x, variable_averges, weights1, biases1, weights2, biases2)

    # 交叉熵
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))

    # 计算当前batch中所有样例的交叉熵平均值
    cross_entropy_mean = tf.reduce_mean(cross_entropy)

    # 正则化项
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    regularization = regularizer(weights1) + regularizer(weights2)

    # 总损失
    loss = cross_entropy_mean +regularization

    # 指数衰减学习率
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step, 
        mnist.train.num_examples/BATCH_SIZE,
        LEARNING_RATE_DECAY,
        staircase=True
    )

    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)

    # 合并操作
    with tf.control_dependencies([train_step,variable_averges_op]):
        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.Session() as sess:
        # 初始化变量
        tf.global_variables_initializer().run()
        validate_feed = {x: mnist.validation.images,y_: mnist.validation.labels}
        test_feed = {x: mnist.test.images,y_:mnist.test.labels}
        for i in range(TRAINING_STEPS):
            if i % 1000 ==0:
                validate_acc = sess.run(accuracy,feed_dict=validate_feed)
                print("After  %d training step(s),validation accuracy using average model is %g"%(i,validate_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 step(s),test accuracy using average model is %g"%(TRAINING_STEPS,test_acc))

def main(argv=None):
    mnist = input_data.read_data_sets("/tmp/data",one_hot=True)
    train(mnist)

if __name__ == "__main__":
    tf.app.run()