分為三個文件：mnist_inference.py：定義前向傳播的過程以及神經網絡中的參數，抽象成為一個獨立的庫函數；mnist_train.py：定義神經網絡的訓練過程，在此過程中，每個一段時間保存一次模型訓練的中間結果；mnist_eval.py：定義測試過程。

mnist_inference.py：

#coding=utf8
import tensorflow as tf


#1. 定義神經網絡結構相關的參數。

INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

#2. 通過tf.get_variable函數來獲取變量。
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. 定義神經網絡的前向傳播過程。使用命名空間方式，不需要把所有的變量都作為變量傳遞到不同的函數中提高程序的可讀性

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

mnist_train.py：

#coding=utf8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference

import os

#1. 定義神經網絡結構相關的參數。

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/"
MODEL_NAME="mnist_model"


#2. 定義訓練過程。

def train(mnist):

    # 定義輸入輸出placeholder。
    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(REGULARIZATION_RATE)
    y = mnist_inference.inference(x, regularizer)
    global_step = tf.Variable(0, trainable=False)
    
    # 定義損失函數、學習率、滑動平均操作以及訓練過程。
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    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))
    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,
        staircase=True)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name=‘train‘)
        
    # 初始化TensorFlow持久化類。
    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)


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

if __name__ == ‘__main__‘:
    main()





結果如下：

mnist_eval.py：

import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
#coding=utf8
import mnist_train

#1. 每10秒加載一次最新的模型

# 加載的時間間隔。
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))

        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)
                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("MNIST_data", one_hot=True)
    evaluate(mnist)

if __name__ == ‘__main__‘:
    main()

結果如下：

Tensorflow 解決MNIST問題的重構程序