1. 首页
  2. JAVA
  3. TensorFlow入门：MNIST预测[restore问题]

TensorFlow入门：MNIST预测[restore问题]

•java•阅读 1677

变量的恢复可按照两种方式导入：

saver=tf.train.Saver()

saver.restore(sess,'model.ckpt')

或者：

saver=tf.train.import_meta_graph(r'D:\tmp\tensorflow\mnist\model.ckpt.meta')

saver.restore(sess,'model.ckpt')

两种方法的效果应该一致，但是实际结果不一样：

使用前者时预测结果是一致的；使用后者时，每次运行结果都不一致。无论是否重启spyde，现象都一样。

在使用前者时，必须在运行前重启spyde，否则会报错，为什么？Out_1等参数会随运行次数增加

INFO:tensorflow:Restoring parameters from D:/tmp/tensorflow/mnist/model.ckpt
Traceback (most recent call last):

  File "<ipython-input-2-61410824b24c>", line 1, in <module>
    runfile('D:/wangjc/pythonTest/TensorFlow/TestMNIST_Predict.py', wdir='D:/wangjc/pythonTest/TensorFlow')

 ......

  File "D:\software\anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1052, in _do_call
    raise type(e)(node_def, op, message)

NotFoundError: Key out_1/bias/bias not found in checkpoint
     [[Node: save_1/RestoreV2_14 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_1/Const_0, save_1/RestoreV2_14/tensor_names, save_1/RestoreV2_14/shape_and_slices)]]

Caused by op 'save_1/RestoreV2_14', defined at:
  File "D:\software\anaconda\envs\tensorflow\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 241, in <module>
    main()
  ......File "D:\software\anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py", line 1228, in __init__
    self._traceback = _extract_stack()

NotFoundError (see above for traceback): Key out_1/bias/bias not found in checkpoint
     [[Node: save_1/RestoreV2_14 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_1/Const_0, save_1/RestoreV2_14/tensor_names, save_1/RestoreV2_14/shape_and_slices)]]
NotFoundError: Key out_2/weight/weight not found in checkpoint
     [[Node: save_2/RestoreV2_23 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_2/Const_0, save_2/RestoreV2_23/tensor_names, save_2/RestoreV2_23/shape_and_slices)]]

Caused by op 'save_2/RestoreV2_23', defined at:

以上需要重启spyder的原因为saver恢复一次之后不能再次恢复，否则报错。

导致saver=tf.train.Saver()与saver=tf.train.import_meta_graph(r'D:\tmp\tensorflow\mnist\model.ckpt.meta')结果不同的原因是，后者在使用中可直接加载模型的参数，操作数等。

tf.get_default_graph()获取图

.get_tensor_by_name()获取张量

.get_operation_by_name()获取操作

注意对各部分命名。

参考1，参考2

使用下面方法的效果与直接读ckpt文件一致

saver = tf.train.Saver()
ckpt=tf.train.get_checkpoint_state(r'D:\tmp\tensorflow\mnist')

saver.restore(sess, ckpt.model_checkpoint_path)

可使用tf.get_collection('name')来读取恢复的变量

注意定义变量时最好标注标量名称，否则可能出现预测时加载参数不正确，定义方法为：

def weight_variable(shape):
    #use normal distribution numbers with stddev 0.1 to initial the weight
    initial=tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial,name='weight')

-------------------------------------------------------------------------------------------------------------------------------

训练并保存模型 代码

# -*- coding: utf-8 -*-
"""
Created on Mon Sep 11 10:16:34 2017

multy layers softmax regression

@author: Wangjc
"""

import tensorflow as tf
import os
import tensorflow.examples.tutorials.mnist.input_data as input_data
#need to show the full address, or error occus.
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
#use read_data_sets to download and load the mnist data set. if has the data, then load.
#need a long time about 5 minutes

sess = tf.InteractiveSession()
#link the back-end of C++ to compute.
#in norm cases, we should create the map and then run in the sussion.
#now, use a more convenient class named InteractiveSession which could insert compute map when running map.

x=tf.placeholder("float",shape=[None,784])
y_=tf.placeholder("float",shape=[None,10])


def weight_variable(shape):
    #use normal distribution numbers with stddev 0.1 to initial the weight
    initial=tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial,name='weight')
    
def bias_variable(shape):
    #use constant value of 0.1 to initial the bias
    initial=tf.constant(0.1, shape=shape)
    return tf.Variable(initial,name='bias')

def conv2d(x,W):
    #convolution by filter of W,with step size of 1, 0 padding size
    #x should have the dimension of [batch,height,width,channels]
    #other dimension of strides or ksize is the same with x
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

def max_pool_2x2(x):
    #pool by windows of ksize,with step size of 2, 0 padding size
    return tf.nn.max_pool(x,ksize=[1,2,2,1],
                          strides=[1,2,2,1],padding='SAME')


#------------------------------------------------
x_image = tf.reshape(x, [-1,28,28,1])
#to use conv1, need to convert x to 4D, in form of [batch,height,width,channels]
# -1 means default
    
with tf.name_scope('conv1'):
    #use 'with' and name_scope to define a name space which will show in tensorboard as a ragion
    with tf.name_scope('weight'):
        W_conv1=weight_variable([5,5,1,32])
        tf.summary.histogram('conv1'+'/weight',W_conv1)
        #summary the variation ('name', value) 
    with tf.name_scope('bias'):
        b_conv1=bias_variable([32])
        tf.summary.histogram('conv1'+'/bias',b_conv1)
#build the first conv layer:
#get 32 features from every 5*5 patch, so the shape is [5,5,1(channel),32]

    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

with tf.name_scope('pool1'):    
    h_pool1 = max_pool_2x2(h_conv1)

#--------------------------------------------
with tf.name_scope('conv2'):
    with tf.name_scope('weight'):    
        W_conv2=weight_variable([5,5,32,64])
        tf.summary.histogram('weight',W_conv2)
    with tf.name_scope('bias'):  
        b_conv2=bias_variable([64])
        tf.summary.histogram('bias',b_conv2)
#build the 2nd conv layer:
#get 64 features from every 5*5 patch, so the shape is [5,5,32(channel),64]

    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
with tf.name_scope('pool2'):    
    h_pool2 = max_pool_2x2(h_conv2)

#----------------------------------------
#image size reduce to 7*7 by pooling
#we add a full connect layer contains 1027 nuere
#need to flat pool tensor for caculate
with tf.name_scope('fc1'):
    with tf.name_scope('weight'):    
        W_fc1 = weight_variable([7*7*64, 1024])
        tf.summary.histogram('weight',W_fc1)
    with tf.name_scope('bias'):
        b_fc1 = bias_variable([1024])
        tf.summary.histogram('bias',b_fc1)

    h_pool2_flat = tf.reshape(h_pool2,[-1, 7*7*64])
    
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1) + b_fc1)

#------------------------------------
#output layer
with tf.name_scope('out'):
    keep_prob = tf.placeholder("float")
    h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
#to decrease overfit, we add dropout before output layer.
#use placeholder to represent the porbability of a neure's output value unchange

    with tf.name_scope('weight'):
        W_fc2 = weight_variable([1024, 10])
        tf.summary.histogram('weight',W_fc2)
    with tf.name_scope('bias'):
        b_fc2 = bias_variable([10])
        tf.summary.histogram('bias',b_fc2)
    y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

#---------------------------------
#train and evaluate the module
#use a ADAM

cross_entropy=-tf.reduce_sum(y_*tf.log(y_conv))
tf.summary.scalar('cross_entropy',cross_entropy)
##summary the constant ('name', value) 
train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

#sess = tf.Session()

merged=tf.summary.merge_all()
#merge all the summary nodes
writer=tf.summary.FileWriter('D:/tmp/tensorflow/mnist/',sess.graph)
# assign the event file write directory 

saver=tf.train.Saver()
#saver for variation.Dafault to save all.
checkpoint_file = os.path.join('D:/tmp/tensorflow/mnist/', 'model.ckpt')
#save directroy for variation

sess.run(tf.global_variables_initializer())
for i in range(100):
    batch = mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_:batch[1],keep_prob:1.0})
#        saver.save(sess,checkpoint_file)
#        saver.save(sess,checkpoint_file,global_step=i)
        #save variation
        print("step %d, training accuracy %g"%(i, train_accuracy))
        result=sess.run(merged,feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
        #the merged summary need to be run
        writer.add_summary(result,i)
        #add the result to summary
    train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
    
print("test accuracy %g"%accuracy.eval(feed_dict={
        x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

saver.save(sess,checkpoint_file)

读取图片，恢复参数并预测 代码

# -*- coding: utf-8 -*-
"""
Created on Mon Sep 11 10:16:34 2017

multy layers softmax regression

@author: Wangjc
"""

import tensorflow as tf
import os
import cv2
import matplotlib.pyplot as plt
#need to show the full address, or error occus.

imgs0=cv2.imread(r'D:\tmp\tensorflow\imgs\_1.png',0)
plt.imshow(imgs0)
plt.show()
imgs=imgs0/255
#imgs=(255-imgs0)/255
imgs.shape=(1,784)



sess = tf.InteractiveSession()
#link the back-end of C++ to compute.
#in norm cases, we should create the map and then run in the sussion.
#now, use a more convenient class named InteractiveSession which could insert compute map when running map.

x=tf.placeholder("float",shape=[None,784])



def weight_variable(shape):
    #use normal distribution numbers with stddev 0.1 to initial the weight
    initial=tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial,name='weight')
    
def bias_variable(shape):
    #use constant value of 0.1 to initial the bias
    initial=tf.constant(0.1, shape=shape)
    return tf.Variable(initial,name='bias')

def conv2d(x,W):
    #convolution by filter of W,with step size of 1, 0 padding size
    #x should have the dimension of [batch,height,width,channels]
    #other dimension of strides or ksize is the same with x
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

def max_pool_2x2(x):
    #pool by windows of ksize,with step size of 2, 0 padding size
    return tf.nn.max_pool(x,ksize=[1,2,2,1],
                          strides=[1,2,2,1],padding='SAME')


#------------------------------------------------
x_image = tf.reshape(x, [-1,28,28,1])
#to use conv1, need to convert x to 4D, in form of [batch,height,width,channels]
# -1 means default
    
with tf.name_scope('conv1'):
    #use 'with' and name_scope to define a name space which will show in tensorboard as a ragion
    with tf.name_scope('weight'):
        W_conv1=weight_variable([5,5,1,32])
#        tf.summary.histogram('conv1'+'/weight',W_conv1)
        #summary the variation ('name', value) 
    with tf.name_scope('bias'):
        b_conv1=bias_variable([32])
#        tf.summary.histogram('conv1'+'/bias',b_conv1)
#build the first conv layer:
#get 32 features from every 5*5 patch, so the shape is [5,5,1(channel),32]

    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)

with tf.name_scope('pool1'):    
    h_pool1 = max_pool_2x2(h_conv1)

#--------------------------------------------
with tf.name_scope('conv2'):
    with tf.name_scope('weight'):    
        W_conv2=weight_variable([5,5,32,64])
#        tf.summary.histogram('weight',W_conv2)
    with tf.name_scope('bias'):  
        b_conv2=bias_variable([64])
#        tf.summary.histogram('bias',b_conv2)
#build the 2nd conv layer:
#get 64 features from every 5*5 patch, so the shape is [5,5,32(channel),64]

    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
with tf.name_scope('pool2'):    
    h_pool2 = max_pool_2x2(h_conv2)

#----------------------------------------
#image size reduce to 7*7 by pooling
#we add a full connect layer contains 1027 nuere
#need to flat pool tensor for caculate
with tf.name_scope('fc1'):
    with tf.name_scope('weight'):    
        W_fc1 = weight_variable([7*7*64, 1024])
#        tf.summary.histogram('weight',W_fc1)
    with tf.name_scope('bias'):
        b_fc1 = bias_variable([1024])
#        tf.summary.histogram('bias',b_fc1)

    h_pool2_flat = tf.reshape(h_pool2,[-1, 7*7*64])
    
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1) + b_fc1)

#------------------------------------
#output layer
with tf.name_scope('out'):
    keep_prob = tf.placeholder("float")
#    h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
#to decrease overfit, we add dropout before output layer.
#use placeholder to represent the porbability of a neure's output value unchange

    with tf.name_scope('weight'):
        W_fc2 = weight_variable([1024, 10])
#        tf.summary.histogram('weight',W_fc2)
    with tf.name_scope('bias'):
        b_fc2 = bias_variable([10])
#        tf.summary.histogram('bias',b_fc2)
    y_conv = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)

#---------------------------------


#saver=tf.train.import_meta_graph(r'D:\tmp\tensorflow\mnist\model.ckpt.meta')
saver=tf.train.Saver()
#saver for variation.Dafault to save all.
checkpoint_file = os.path.join('D:/tmp/tensorflow/mnist/', 'model.ckpt')
#save directroy for variation

sess.run(tf.global_variables_initializer())

saver.restore(sess,checkpoint_file)
#saver.recover_last_checkpoints(checkpoint_file)

#prediction=tf.argmax(y_conv,1)
#result=prediction.eval(feed_dict={x: imgs})

result=sess.run(tf.argmax(y_conv,1),feed_dict={x: imgs,keep_prob: 0.5})
#result=prediction.eval(feed_dict={x: imgs,keep_prob: 0.5})


print('recognize result')
print(result[0])

Stack Overflow参考1，参考2

模型存储与恢复

相关推荐

Copyright © 2008-2024渝ICP备2022006305号-5.

本站所有数据收集于网络如有侵犯到您的权益请联系，进行下架处理。