MNIST_UPDATE_inference.py代码如下:
# -*- coding: utf-8 -*-
import tensorflow as tf
tf.reset_default_graph()
INPUT_NODE=784
LAYER1_NODE=500
OUTPUT_NODE=10
def get_weight_variable(shape,regularizer=None):
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
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_UPDATE_train.py代码如下:
# -*- coding: utf-8 -*-
import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import MNIST_UPDATE_inference
#tf.reset_default_graph()
BATCH_SIZE=100
LEARNING_RATE_BASE=0.8
LEARNING_RATE_DECAY=0.99
REGULARAZTION_RATE=0.0001
TRAINING_STEPS=30000
MOVING_AVERAGE_DECAY=0.99
MODEL_SAVE_PATH="model/"
MODEL_NAME="mnist_model.ckpt"
def train(mnist):
x=tf.placeholder(tf.float32,[None,MNIST_UPDATE_inference.INPUT_NODE],name='x-input')
y_=tf.placeholder(tf.float32,[None,MNIST_UPDATE_inference.OUTPUT_NODE],name='y-input')
regularizer=tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
y=MNIST_UPDATE_inference.inference(x,regularizer)
global_step=tf.Variable(0,trainable=False)
variable_averages=tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,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')
saver = tf.train.Saver()
with tf.Session() as sess:
init_op=tf.global_variables_initializer()
sess.run(init_op)
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 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(argv=None):
mnist=input_data.read_data_sets("/tmp/data",one_hot=True)
train(mnist)
if __name__=='__main__':
tf.app.run()
MNIST_UPDATE_eval.py代码如下:
# -*- coding: utf-8 -*-
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import MNIST_UPDATE_inference
import MNIST_UPDATE_train
EVAL_INTERVAL_SECS=10
def evaluate(mnist):
with tf.Graph().as_default() as g:
x=tf.placeholder(tf.float32,[None,MNIST_UPDATE_inference.INPUT_NODE],name='x-input')
y_=tf.placeholder(tf.float32,[None,MNIST_UPDATE_inference.OUTPUT_NODE],name='y-input')
validate_feed={x:mnist.validation.images,y_:mnist.validation.labels}
y=MNIST_UPDATE_inference.inference(x,None)
correct_prediction=tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
variable_average=tf.train.ExponentialMovingAverage(MNIST_UPDATE_train.MOVING_AVERAGE_DECAY)
variables_to_restore=variable_average.variables_to_restore()
saver=tf.train.Saver(variables_to_restore)
with tf.Session() as sess:
ckpt=tf.train.get_checkpoint_state(MNIST_UPDATE_train.MODEL_SAVE_PATH)
if ckpt and ckpt.all_model_checkpoint_paths:
for model_file in ckpt.all_model_checkpoint_paths:
saver.restore(sess,model_file)
global_step=model_file.split('/')[-1].split('-')[-1]
accuracy_score=sess.run(accuracy,feed_dict=validate_feed)
print("After %s training steps,validation accuracy = %g"%(global_step,accuracy_score))
time.sleep(EVAL_INTERVAL_SECS)
else:
print("no checkpoint file found")
return
def main(argv=None):
mnist=input_data.read_data_sets("/tmp/data",one_hot=True)
evaluate(mnist)
if __name__=='__main__':
tf.app.run()
运行结果:
运行MNIST_UPDATE_train.py
中间省略一大堆…….
运行MNIST_UPDATE_eval.py
代码说明:(代码运行环境:VMware虚拟机,Ubuntu Linux,编译器spyder,Python3.6,TensorFlow 1.3.0,因为版本不一样,代码存在略微不一样)
MNIST_UPDATE_inference.py
因为代码里会将图模型存储,当第一次运行代码时,是成功的;但是之后再次运行就会报错,张量已存在。这个问题的解决,搜了很多,看了很多论坛,最后发现,是因为之前运行一次后,图模型中初始化了该张量,再次运行,就会与之前存在的张量同名,故出现张量已存在的情况。解决方法:在代码前面加上一句清空图的代码。
“tf.reset_default_graph()”
MNIST_UPDATE_train.py
运行代码前,需要在当前目录下,新建一个名为model的文件夹,训练完成后的模型会存在此文件夹下。每个模型会生成3个文件,其中checkpoint文件只有一个,用于记录最新模型,最多记录5个。因此该文件夹下,最多存放5个模型数据,本代码存放次数大于5,故新来的模型会覆盖旧模型,最后只剩最新的5个模型参数依然存放在文件夹下。
MNIST_UPDATE_eval.py
得到模型参数后,从模型文件中读取出数据,然后代入测试数据,进行评估。因为checkpoint文件中最多存5个模型,所以实验结果只有最新的5个模型进行评估。