-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
pdserving 部署PP-OCR4 超显存 #7
Labels
Comments
Issue Response
根据提供的信息,您遇到了GPU显存不足的问题。根据错误信息,您可以尝试以下解决方法:
请注意,您提供的信息中还包含了版本号、运行指令和完整报错信息,这些信息对于定位问题也非常重要。如果以上方法都无法解决您的问题,请提供更多的信息以便我们能够帮助您解决。 How to use
|
有可能是输入图像太大,但是我在DB检测网络中已经限制最长边:
|
@Ace-issue-solver 有办法限制最大使用显存吗?总是OOM。 |
我记得之前我把进程改为线程,显存就降下来了,但是不知道改为线程会有什么坏处 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
Please check whether there is any other process using GPU 0.
If the above ways do not solve the out of memory problem, you can try to use CUDA managed memory. The command is
export FLAGS_use_cuda_managed_memory=false
.(at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:87)
W0828 07:40:58.236891 205 operator.cc:288] concat raises an exception paddle::memory::allocation::BadAlloc, ResourceExhaustedError:
Out of memory error on GPU 0. Cannot allocate 289.078125MB memory on GPU 0, 14.514648GB memory has been allocated and available memory is only 246.750000MB.
Please check whether there is any other process using GPU 0.
If the above ways do not solve the out of memory problem, you can try to use CUDA managed memory. The command is
export FLAGS_use_cuda_managed_memory=false
.(at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:87)
我们提供了AceIssueSolver来帮助你解答问题,你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no): yes
请尽量不要包含图片在问题中/Please try to not include the image in the issue.
The text was updated successfully, but these errors were encountered: