TensorFlow学习—Google实战（chapter05） 最佳MNIST手写数字识别code

###最佳MNISTmodel

1.通过辅助函数来定义前向传播过程并保存为mnist_inference.py文件

 # step111 定义神经网络的前向传播过程

import tensorflow as tf

# 1. 定义神经网络结构相关的参数
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

# 2. 通过tf.get_variable函数来获取变量
def get_weight_variable(shape, regularizer):
    weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))
    if regularizer != None:
        tf.add_to_collection('losses', regularizer(weights))
    return weights

# 3. 定义神经网络的前向传播过程
def inference(input_tensor, regularizer):
    with tf.variable_scope('layer1'):
        weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
        biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)

    with tf.variable_scope('layer2'):
        weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
        biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
        layer2 = tf.matmul(layer1, weights) + biases

    return layer2

2.定义训练模型，并保存为mnist_train.py 文件

# step222 训练程序

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

# 1. 定义神经网络结构相关的参数
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
MODEL_SAVE_PATH = "MNIST_model/" # 在当前目录下存在MNIST_model子文件夹
MODEL_NAME = "mnist_model"

# 2. 定义训练过程
def train(mnist):
    # 定义输入输出placeholder。
    x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')  ##里欧用placeholder()机制对输入值和真实值进行赋值
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')

    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE) ####正则化项的利用
    y = mnist_inference.inference(x, regularizer)                            ###此处y为相应于x的预测值
    global_step = tf.Variable(0, trainable=False)

    # 定义损失函数、学习率、滑动平均操作以及训练过程。
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)  ###滑动平均模型的使用
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))   ####预测值y,真实值y_之间的交叉损失函数
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))  ##加入了正则化项的的交叉熵损失函数
    learning_rate = tf.train.exponential_decay( 
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,  ###每经过m/batch_size的样本，进行一次指数衰减
        staircase=True)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)###学习率的设置及训练优化
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')

    # 初始化TensorFlow持久化类。
    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.global_variables_initializer().run()

        for i in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
            if i % 1000 == 0:
                print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)

# 3. 主程序入口
def main(argv=None):
    mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True)
    train(mnist)

if __name__ == '__main__':
    main()

3.定义评估模型，主要是用于在验证集上的运用。

 #step3333 测试程序
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train

# 1. 每10秒加载一次最新的模型
# 加载的时间间隔。
EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
        y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
        validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}

        y = mnist_inference.inference(x, None)
        correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))   
        ###tf.equal()结果是bool类型的结果值，相等返回true，不等则返回false
        ###tf.cast(x, dtype, name=None) 将x的数据格式转化成dtype.例如，原来x的数据格式是bool, 那么将其转化成float以后，就能够将其转化成0和1的序列。反之也可以
        variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_restore)

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)  #checkpoint文件会记录保存信息，通过它可以定位最新保存的模型：
                ##.meta文件保存了当前图结构
                ##.index文件保存了当前参数名
                ##.data文件保存了当前参数值
                if ckpt and ckpt.model_checkpoint_path:
                    saver.restore(sess, ckpt.model_checkpoint_path)
                    global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                    accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
                    print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))
                else:
                    print('No checkpoint file found')
                    return
            time.sleep(EVAL_INTERVAL_SECS)

# 主程序
def main(argv=None):
    mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True)
    evaluate(mnist)

if __name__ == '__main__':
    main()