tensorflow入门实践（五）：模型的保存与恢复

环境：ubuntu16.04+tensorflow+cpu

文件路径：/home/qf/tensorflow/tf/tf5

      

  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'

# -*- 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()

##############################################################
#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).
###############################################################

##################################################################
#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
"""
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()
"""
##################################################################
#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。
#可以使用tf.train.latest_checkpoint（）来自动获取最后一次保存的模型。
#后半段可以使用如下代码
"""
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()

"""

下面是完整的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())

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：https://blog.csdn.net/m0_37167788/article/category/7393385