MNIST数字识别问题完整版

import tensorflow as tf

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

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

#定义神经网络的前向传播
def inference(input_tensor, regularizer):
    #申明第一层神经网络的变量并完成前向传播过程
    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)

    #类似的申明第二层神经网络的变量并完成前向传播过程
    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

import os

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

#加载mnist_inference.py中定义的常量和前向传播的函数
import mnist_inference

#配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARAZTION_RATE = 0.0001
TRAINING_STEPS = 300000
MOVING_AVERAGE_DEACY = 0.99
#模型保存的路径和文件名
MODEL_SAVE_PATH = r"E:\test\mnist\to-model"
MODEL_NAME = "model.ckpt"

def train(mnist):
    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')

    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
    #直接使用mnist_inference.py中定义的前向传播过程
    y = mnist_inference.inference(x, regularizer)
    global_step = tf.Variable(0, trainable=False)

    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DEACY, global_step)
    variable_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))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)
    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(name='train')
    if not os.path.exists(MODEL_SAVE_PATH):
        os.mkdir(MODEL_SAVE_PATH)
    #初始化tensorflow持久化类
    saver = tf.train.Saver()
    with tf.Session() as sess:
        # tf.initialize_all_variables().run()
        init = tf.global_variables_initializer()
        sess.run(init)
        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})

            #每1000轮保存一次模型
            if  i % 1000 == 0:
                #输出当前训练的情况，输出模型在当前训练batch上的损失函数大小
                print("After %d training step(s), loss on training "
                "batch is %g." % (step, loss_value))
                #保存当前模型
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)

def main(argv=None):
    mnist = input_data.read_data_sets(r"E:\data\data_mnist", one_hot=True)
    train(mnist)

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

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

import mnist_inference
import mnist_train

#每10秒加载一次最新的模型，并在测试数据上测试最新模型的正确率
EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
    with tf.Graph().as_default() as g:
        # 定义输入输出的格式
        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)

        # 使用前向传播的结果计算正确率
        correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

        # 通过变量重命名的方式来加载模型
        variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DEACY)
        variable_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variable_to_restore)

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
                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)

def main(argv=None):
    mnist = input_data.read_data_sets(r"E:\data\data_mnist", one_hot=True)
    evaluate(mnist)

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