mnist_forward
#在前向传播过程中，需要定义网络模型输入层个数、隐藏层节点数、输出层个数
#定义网络参数w、偏置b，定义由输入到输出的神经网络架构
import tensorflow as tf
#网络输入节点数，代表每张输入图片的像素个数
INPUT_NODE=784
#隐藏层节点数
OUTPUT_NODE=10
#输出节点数
LAYER1_NODE=500
#对参数w的设置，包括参数w的形状和是否正则化的标志
def get_weight(shape,regularizer):
w=tf.Variable(tf.truncated_normal(shape,stddev=0.1))
if regularizer!=None:tf.add_to_collection('losses',tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
#对偏置b的设置
def get_bias(shape):
b=tf.Variable(tf.zeros(shape))
return b
#向前传播过程
def forward(x,regularizer):
w1=get_weight([INPUT_NODE,LAYER1_NODE],regularizer)
b1=get_bias([LAYER1_NODE])
y1=tf.nn.relu(tf.matmul(x,w1)+b1)
w2=get_weight([LAYER1_NODE,OUTPUT_NODE],regularizer)
b2=get_bias([OUTPUT_NODE])
y=tf.matmul(y1,w2)+b2
return y
mnist_backward
#coding:utf-8
#反向传播过程实现利用训练数据集对神经网络模型训练，通过降低损失函数值，
#实现网络模型参数的优化，从而得到准确率高且泛化能力强的神经网络模型
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import os
#每轮喂入神经网络的图片数
BATCH_SIZE=200
#初始学习率
LEARNING_RATE_BASE = 0.1
#学习率衰减率
LEARNING_RATE_DECAY=0.99
#正则化系数
REGULARIZER=0.0001
#训练轮数
STEPS=50000
#滑动平均衰减率
MOVING_AVERAGE_DECAY=0.99
#模型保存路径
MODEL_SAVE_PATH="./model/"
#模型保存名称
MODEL_NAME="mnist_model"
def backward(mnist):
#占位
x=tf.placeholder(tf.float32,[None,mnist_forward.INPUT_NODE])
y_=tf.placeholder(tf.float32,[None,mnist_forward.OUTPUT_NODE])
#前向传播，计算训练数据集上的预测结果y
y=mnist_forward.forward(x,REGULARIZER)
#赋值计算轮数，设置为不可训练类型
global_step=tf.Variable(0,trainable=False)
#设置损失函数（所有函数正则化损失）
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'))
#指定指数衰减学习率
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)
#定义参数的滑动平均
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_op=tf.initialize_all_variables()
sess.run(init_op)
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%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():
mnist=input_data.read_data_sets("./data/",one_hot=True)
backward(mnist)
if __name__=='__main__':
main()
mnist_test
#coding:utf-8
#当训练完模型后，给神经网络模型输入测试集验证网络的正确性和泛化性
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_NODE])
y_=tf.placeholder(tf.float32,[None,mnist_forward.OUTPUT_NODE])
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)
corrent_prediction=tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(corrent_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_score=sess.run(accuracy,feed_dict={x:mnist.test.images,y_:mnist.test.labels})
print("After %s training step(s),test accuracy=%g"%(global_step,accuracy_score))
else:
print("No checkpoint file found")
return
time.sleep(TEST_INTERVAL_SECS)
def main():
mnist=input_data.read_data_sets("./data/",one_hot=True)
test(mnist)
if __name__=='__main__':
main()
断点续训
在mnist_backward中增加
ckpt=tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess,ckpt.model_checkpoint_path)
问题
在执行mnist_backward的时候会报错，这边是创建了model文件夹后成功的。
