簡單全連接配接神經網絡--MNIST

使用全連接配接神經網絡進行手寫數字識别，這個效果比CNN要差，僅做練習。

1、mnist_inference.py

#coding:utf-8

import tensorflow as tf

#定義神經網絡結構相關的參數
INPURT_NODE = 
OUTPUT_NIDE = 
LAYER1_NODE = 

def get_weight_variable(shape,regularizer):
    weights = tf.get_variable("weight",shape,initializer=tf.truncated_normal_initializer(stddev=))

    if regularizer != None:
        tf.add_to_collection("losses",regularizer(weights))

    return weights


def inference(input_tensor,regularizer):
    with tf.variable_scope("layer1"):
        weights = get_weight_variable([INPURT_NODE,LAYER1_NODE],regularizer)

        biases = tf.get_variable("biases",[LAYER1_NODE],initializer=tf.constant_initializer())

        layer1 = tf.nn.relu(tf.matmul(input_tensor,weights)+biases)


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


    return layer2
           

2、train.py

#coding:utf-8

import tensorflow as tf
import os

from tensorflow.examples.tutorials.mnist import input_data

#加載剛剛些的前向傳播過程
import mnist_inference



#配置神經網絡的參數
BATCH_SIZE = 
LEARNING_RATE_BASE = #指數衰減基礎學習率
LEARNING_RATE_DECAY = #衰減率
REGULARAZTION_RATE = #正則化的權重
TRAIN_STEP = 
MOVING_AVERAGE_DECAY = #滑動平均率

MODEL_SAVE_PATH = "./model"
MODEL_NAME = "model.ckpt"

def train(mnist):
    x = tf.placeholder(tf.float32,[None,mnist_inference.INPURT_NODE],name="x-input")
    y_ = tf.placeholder(tf.float32,[None,mnist_inference.OUTPUT_NIDE],name="y-input")

    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)

    y = mnist_inference.inference(x,regularizer)

    global_step = tf.Variable(,trainable=False)#設定global_step為不可訓練數值，在訓練過程中它不進行相應的更新

    #對w,b進行滑動平均操作
    variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)#對滑動平均函數進行輸入滑動平均率以及步數
    variable_average_op = variable_average.apply(tf.trainable_variables())#對是以可訓練的參數進行滑動平均操作

    #計算損失函數
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels = y_,logits = y)
    cross_entropy_mean = tf.reduce_mean(cross_entropy)

    loss = cross_entropy_mean+tf.add_n(tf.get_collection("losses"))#這裡計算collection裡的所有的和。之前把w正則化的值放在了collection裡

    #對 學習率 進行指數衰減
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY) 

    #定義訓練過程
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)#每當進行一次訓練global_step會加1

    #一次進行多個操作,既進行反向傳播更新神經網絡中的參數，又更新每一個參數的滑動平均值(滑動平均是影子操作)
    with tf.control_dependencies([train_step,variable_average_op]):
        train_op = tf.no_op(name="train")


    #儲存操作
    saver = tf.train.Saver()

    #啟動程式

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

        for i in range(TRAIN_STEP):
            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輪儲存一次模型
            if i% ==:
                print "step ",step,"   ","loss  ",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("/tmp/data",one_hot=True)
    train(mnist)

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