使用tensorflow识别自己手写的数字时的问题

最新推荐文章于 2024-05-21 14:45:00 发布

te_er

最新推荐文章于 2024-05-21 14:45:00 发布

阅读量1.2k

点赞数

CC 4.0 BY-SA版权

文章标签： Mnist tensorflow 识别手写数字深度学习

本文链接：https://blog.youkuaiyun.com/lvmeierxiangnile/article/details/79154394

在尝试使用TensorFlow加载Mnist训练模型进行手写数字识别时遇到了问题。系统发出警告，提示从旧的`initialize_all_variables`方法迁移至`tf.global_variables_initializer`。之后在恢复模型参数时发生了`NotFoundError`，指出Key `Variable_10`未在检查点中找到，这可能是因为模型保存和加载的变量不匹配。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

runfile('E:/python_workspace/Mnist_train_modle/test.py', wdir='E:/python_workspace/Mnist_train_modle')
WARNING:tensorflow:From C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\util\tf_should_use.py:175: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
INFO:tensorflow:Restoring parameters from E:\python_workspace\Mnist_train_modle\model.ckpt
Traceback (most recent call last):

File "<ipython-input-17-923ce19d8850>", line 1, in <module>
runfile('E:/python_workspace/Mnist_train_modle/test.py', wdir='E:/python_workspace/Mnist_train_modle')

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
execfile(filename, namespace)

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "E:/python_workspace/Mnist_train_modle/test.py", line 88, in <module>
saver.restore(sess, "E:\python_workspace\Mnist_train_modle\model.ckpt")#这里使用了之前保存的模型参数

File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1560, in restore
{self.saver_def.filename_tensor_name: save_path})

File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\cli