将训练好的模型参数保存起来,以便以后进行验证或测试,这是我们经常要做的事情。tf里面提供模型保存的是tf.train.Saver()模块。
模型保存,先要创建一个Saver对象:如
saver=tf.train.Saver()
在创建这个Saver对象的时候,有一个参数我们经常会用到,就是 max_to_keep 参数,这个是用来设置保存模型的个数,默认为5,即 max_to_keep=5,保存最近的5个模型。如果你想每训练一代(epoch)就想保存一次模型,则可以将 max_to_keep设置为None或者0,如:
saver=tf.train.Saver(max_to_keep=0)
但是这样做除了多占用硬盘,并没有实际多大的用处,因此不推荐。
当然,如果你只想保存最后一代的模型,则只需要将max_to_keep设置为1即可,即
saver=tf.train.Saver(max_to_keep=1)
创建完saver对象后,就可以保存训练好的模型了,如:
saver.save(sess,'ckpt/mnist.ckpt',global_step=step)
第一个参数sess,这个就不用说了。第二个参数设定保存的路径和名字,第三个参数将训练的次数作为后缀加入到模型名字中。
saver.save(sess, 'my-model', global_step=0) ==> filename: 'my-model-0'
...
saver.save(sess, 'my-model', global_step=1000) ==> filename: 'my-model-1000'
看一个mnist实例:
# -*- coding: utf-8 -*-
"""
Created on Sun Jun 4 10:29:48 2017 @author: Administrator
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=False) x = tf.placeholder(tf.float32, [None, 784])
y_=tf.placeholder(tf.int32,[None,]) dense1 = tf.layers.dense(inputs=x,
units=1024,
activation=tf.nn.relu,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
kernel_regularizer=tf.nn.l2_loss)
dense2= tf.layers.dense(inputs=dense1,
units=512,
activation=tf.nn.relu,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
kernel_regularizer=tf.nn.l2_loss)
logits= tf.layers.dense(inputs=dense2,
units=10,
activation=None,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
kernel_regularizer=tf.nn.l2_loss) loss=tf.losses.sparse_softmax_cross_entropy(labels=y_,logits=logits)
train_op=tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
correct_prediction = tf.equal(tf.cast(tf.argmax(logits,1),tf.int32), y_)
acc= tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) sess=tf.InteractiveSession()
sess.run(tf.global_variables_initializer()) saver=tf.train.Saver(max_to_keep=1)
for i in range(100):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_op, feed_dict={x: batch_xs, y_: batch_ys})
val_loss,val_acc=sess.run([loss,acc], feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print('epoch:%d, val_loss:%f, val_acc:%f'%(i,val_loss,val_acc))
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
sess.close()
代码中红色部分就是保存模型的代码,虽然我在每训练完一代的时候,都进行了保存,但后一次保存的模型会覆盖前一次的,最终只会保存最后一次。因此我们可以节省时间,将保存代码放到循环之外(仅适用max_to_keep=1,否则还是需要放在循环内).
在实验中,最后一代可能并不是验证精度最高的一代,因此我们并不想默认保存最后一代,而是想保存验证精度最高的一代,则加个中间变量和判断语句就可以了。
saver=tf.train.Saver(max_to_keep=1)
max_acc=0
for i in range(100):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_op, feed_dict={x: batch_xs, y_: batch_ys})
val_loss,val_acc=sess.run([loss,acc], feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print('epoch:%d, val_loss:%f, val_acc:%f'%(i,val_loss,val_acc))
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
sess.close()
如果我们想保存验证精度最高的三代,且把每次的验证精度也随之保存下来,则我们可以生成一个txt文件用于保存。
saver=tf.train.Saver(max_to_keep=3)
max_acc=0
f=open('ckpt/acc.txt','w')
for i in range(100):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_op, feed_dict={x: batch_xs, y_: batch_ys})
val_loss,val_acc=sess.run([loss,acc], feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print('epoch:%d, val_loss:%f, val_acc:%f'%(i,val_loss,val_acc))
f.write(str(i+1)+', val_acc: '+str(val_acc)+'\n')
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
f.close()
sess.close()
模型的恢复用的是restore()函数,它需要两个参数restore(sess, save_path),save_path指的是保存的模型路径。我们可以使用tf.train.latest_checkpoint()来自动获取最后一次保存的模型。如:
model_file=tf.train.latest_checkpoint('ckpt/')
saver.restore(sess,model_file)
则程序后半段代码我们可以改为:
sess=tf.InteractiveSession()
sess.run(tf.global_variables_initializer()) is_train=False
saver=tf.train.Saver(max_to_keep=3) #训练阶段
if is_train:
max_acc=0
f=open('ckpt/acc.txt','w')
for i in range(100):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_op, feed_dict={x: batch_xs, y_: batch_ys})
val_loss,val_acc=sess.run([loss,acc], feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print('epoch:%d, val_loss:%f, val_acc:%f'%(i,val_loss,val_acc))
f.write(str(i+1)+', val_acc: '+str(val_acc)+'\n')
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
f.close() #验证阶段
else:
model_file=tf.train.latest_checkpoint('ckpt/')
saver.restore(sess,model_file)
val_loss,val_acc=sess.run([loss,acc], feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print('val_loss:%f, val_acc:%f'%(val_loss,val_acc))
sess.close()
标红的地方,就是与保存、恢复模型相关的代码。用一个bool型变量is_train来控制训练和验证两个阶段。
整个源程序:
# -*- coding: utf-8 -*-
"""
Created on Sun Jun 4 10:29:48 2017 @author: Administrator
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=False) x = tf.placeholder(tf.float32, [None, 784])
y_=tf.placeholder(tf.int32,[None,]) dense1 = tf.layers.dense(inputs=x,
units=1024,
activation=tf.nn.relu,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
kernel_regularizer=tf.nn.l2_loss)
dense2= tf.layers.dense(inputs=dense1,
units=512,
activation=tf.nn.relu,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
kernel_regularizer=tf.nn.l2_loss)
logits= tf.layers.dense(inputs=dense2,
units=10,
activation=None,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.01),
kernel_regularizer=tf.nn.l2_loss) loss=tf.losses.sparse_softmax_cross_entropy(labels=y_,logits=logits)
train_op=tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
correct_prediction = tf.equal(tf.cast(tf.argmax(logits,1),tf.int32), y_)
acc= tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) sess=tf.InteractiveSession()
sess.run(tf.global_variables_initializer()) is_train=True
saver=tf.train.Saver(max_to_keep=3) #训练阶段
if is_train:
max_acc=0
f=open('ckpt/acc.txt','w')
for i in range(100):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_op, feed_dict={x: batch_xs, y_: batch_ys})
val_loss,val_acc=sess.run([loss,acc], feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print('epoch:%d, val_loss:%f, val_acc:%f'%(i,val_loss,val_acc))
f.write(str(i+1)+', val_acc: '+str(val_acc)+'\n')
if val_acc>max_acc:
max_acc=val_acc
saver.save(sess,'ckpt/mnist.ckpt',global_step=i+1)
f.close() #验证阶段
else:
model_file=tf.train.latest_checkpoint('ckpt/')
saver.restore(sess,model_file)
val_loss,val_acc=sess.run([loss,acc], feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print('val_loss:%f, val_acc:%f'%(val_loss,val_acc))
sess.close()
参考文章:http://blog.csdn.net/u011500062/article/details/51728830