tensorflow笔记（曹健老师）：mnist数据集手写数字识别

分为三部分:前向传播，反向传播，数据测试。适应一下简单的结构化编程

第一部分：前向传播（mnist_forward.py）

#前向传播，两层神经网络
import tensorflow as tf
import numpy as np
input_data = 784
output_data = 10
layer_data = 50
def get_weight(shape,reg):
    w = tf.Variable(tf.truncated_normal(shape = shape,stddev=0.1))
    if reg != None: tf.add_to_collection('losses',tf.contrib.layers.l2_regularizer(reg)(w))
    return w
def get_bais(shape):
    b = tf.Variable(tf.zeros(shape))
    return b
def forward(x,reg):
    w1 = get_weight([input_data,layer_data],reg)
    b1 = get_bais([layer_data])
    y1 = tf.nn.relu(tf.matmul(x,w1)+b1)

    w2 = get_weight([layer_data,output_data],reg)
    b2 = get_bais(output_data)
    y = tf.matmul(y1,w2)+b2
    return y

第二部分：反向传播(mnist_backward.py)

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

batch_size = 200
learning_rate_base = 0.1
learning_rate_decay = 0.99
regularizer = 0.0001
steps = 50000
moving_average_decay = 0.99
model_save_path = "./model/"
model_name = "mnist_model"

def backward(mnist):
    x = tf.placeholder(tf.float32,[None,mnist_forward.input_data])
    y_ = tf.placeholder(tf.float32,[None,mnist_forward.output_data])
    y = mnist_forward.forward(x,regularizer)
    global_step = tf.Variable(0,trainable=False)

    ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_,1))
    cem = tf.reduce_mean(ce)
    loss = cem + 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)

    ema = tf.train.ExponentialMovingAverage(moving_average_decay,global_step)
    ema_op = ema.apply(tf.trainable_variables())
    with tf.control_dependencies([train_step,ema_op]):
        train_op = tf.no_op(name='train')

    saver = tf.train.Saver()

    with tf.Session() as sess:
        init = tf.global_variables_initializer()
        sess.run(init)

        for i in range(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+1) % 1000 == 0:
                print('after %d steps,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():
    mnist = input_data.read_data_sets("./data/", one_hot=True)
    backward(mnist)
if __name__ == '__main__':
    main()

部分训练结果：

第三部分：进行测试(mnist_test.py)

#coding utf-8
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import mnist_backward
test_interval_secs = 5

def test(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32,[None,mnist_forward.input_data])
        y_ = tf.placeholder(tf.float32,[None,mnist_forward.output_data])
        y = mnist_forward.forward(x,None)

        ema = tf.train.ExponentialMovingAverage(mnist_backward.moving_average_decay)
        ema_restore = ema.variables_to_restore()
        saver = tf.train.Saver(ema_restore)

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

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(mnist_backward.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_store = sess.run(accuracy,feed_dict={x:mnist.test.images,y_:mnist.test.labels})
                    print("after %s training steps,test accuary = %g"%(global_step,accuracy_store))
                else:
                    print('no checkpoint found')
            time.sleep(test_interval_secs)
def main():
    mnist = input_data.read_data_sets("./data/",one_hot=True)
    test(mnist)
if __name__=='__main__':
    main()

部分测试结果（反向传播与test函数同时执行）： 

代码是在pycharm中执行的：

数据下载到data文件中，模型保存到model文件夹中（并不会全部保存，而是会保存最后更新的几个模型）