TensorFlow学习笔记（5）——训练全连接神经网络

全连接神经网络解决MNIST问题

这里的模型是使用滑动平均的模型
代码和我的注释：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
'''
mnist = input_data.read_data_sets("path/to/MNIST_data", one_hot=True)
print(mnist.train.num_examples)
print(mnist.validation.num_examples)
print(mnist.test.num_examples)
print(mnist.train.images[0])
print(mnist.train.labels[0])
'''

#MNIST数据集相关常数
INPUT_NODE=784
OUTPUT_NODE=10

#配置神经网络参数
LAYER1_NODE=500
BATCH_SIZE=100

LEARNING_RATE_BASE=0.8
LEARNING_RATE_DECAY=0.99
REGULARIZATION_RATE=0.0001
TRAINING_STEPS=30000
MOVING_AVERAGE_DECAY=0.99

#一个辅助函数，给定神经网络的输入和所有参数，计算神经网络的前向传播结果。定义了一个ReLU激活函数的三层全连接神经网络。
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
    #当没有提供滑动平均类时
    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):
#为输入输出占坑
    x=tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
    y_=tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')
#设置权重和偏置
    weights1=tf.Variable(tf.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)
    #这里的y是没有使用滑动平均，仅仅是前向传播的结果
    global_step = tf.Variable(0, trainable=False)#这里将训练轮数设定为不可训练的参数

    #滑动平均值，改变训练轮数的变量
    variable_averages=tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)

    variable_averages_op = variable_averages.apply(tf.trainable_variables())
    average_y=inference(x, variable_averages, weights1, biases1, weights2, biases2)

    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
#使用了交叉熵，交叉熵使用的是没有经过滑动平均的结果y
#书上给出的代码错了，此处必须指定logits和labels，看名字就知道，logits是计算结果，labels是正确答案
    cross_entropy_mean = tf.reduce_mean(cross_entropy)

    #L2正则化
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)#损失函数
    regularization = regularizer(weights1) + regularizer(weights2)
    loss = cross_entropy_mean + regularization

    #设置指数衰减的学习率
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE,
        LEARNING_RATE_DECAY)

    #梯度下降优化损失函数
    train_step=tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    with tf.control_dependencies([train_step, variable_averages_op]):
        train_op=tf.no_op("train")
#tf.control_dependencies([a,b]): c=tf.no_op()和c=tf.group(a,b)等价，就是没有执行顺序先后，是平行关系

    correct_prediction=tf.equal(tf.arg_max(average_y, 1), tf.argmax(y_,1))
    accuracy=tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    #初始化会话并开始训练过程，大概分两步，准备数据和开始迭代
    with tf.Session() as sess:
        tf.initialize_all_variables().run()

        #验证数据
        validated_feed={x: mnist.validation.images, y_: mnist.validation.labels}

        #测试数据
        test_feed = {x: mnist.test.images, y_: mnist.test.labels}

        #迭代训练
        for i in range(TRAINING_STEPS):
            #每1000轮输出一次在验证数据集上的测试结果
            if i % 1000 ==0:
                validate_acc = sess.run(accuracy, feed_dict=validated_feed)
                print("After %d training step(s), validation accuracy using average model is %g" %(i, validate_acc))

            #产生本轮使用的一个batch的训练数据，并运行训练过程
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            sess.run(train_op, feed_dict={x:xs, y_:ys})

        #训练结束后检测最终成功率
        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("path/to/MNIST_data", one_hot=True)#自动下载数据
        train(mnist)#开始训练

#tf提供的中程序入口，tf.app.run()会自动调用main函数
if __name__ == '__main__':   
        tf.app.run()