-
Notifications
You must be signed in to change notification settings - Fork 7.8k
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
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
更换了高精度的检测模型det和识别模型rec以后,cuda会报错: [Hint: 'CUDNN_STATUS_NOT_SUPPORTED'. The functionality requested is not presently supported by cuDNN. ] #10760
Comments
补充一下cuda的版本:cuda 11.7 |
@tink2123 我也有这个问题啊,同cuda 11.7 paddlepaddle-gpu 2.5.1 cudnn8.9.2 报错如下,和楼主的差不多,求解答。正常的v4,v3轻量级模型都可以正常推理
|
@tink2123 能解答下吗,别沉啊 |
paddlepaddle-gpu 2.5.1 对应的cuda是11.8,cudnn是8.6.0。我刚开始也碰到了这个问题,安装好正确的cuda版本之后就可以正常使用teacher模型了。 |
@crazbot 可以了,感谢~ |
我也是paddlepaddle-gpu 2.5.1,cuda11.8,但是cudnn是8.9.3,这个版本似乎不行 |
问题类似,在paddleOCR中使用ch_PP-OCRv4_det_server_infer模型,也报类似错误。paddlepaddle-gpu 2.5.1 ,cuda11.7、11.8+cudnn 8.6.0、8.6.4、8.6.5都试过,没有解决 |
paddlepaddle-gpu 2.5.1, cuda 11.6 + cudnn8.6.0 测试可以 |
别沉 我也遇见了 |
你好,请问你解决了吗?我也是CUDA11.7,cudnn8.9.5试过不行。 |
没有,后来没再研究这个
…________________________________
发件人: lzzzzj ***@***.***>
发送时间: 2023年12月15日 7:47
收件人: PaddlePaddle/PaddleOCR ***@***.***>
抄送: gitcnbubble ***@***.***>; Comment ***@***.***>
主题: Re: [PaddlePaddle/PaddleOCR] 更换了高精度的检测模型det和识别模型rec以后,cuda会报错: [Hint: 'CUDNN_STATUS_NOT_SUPPORTED'. The functionality requested is not presently supported by cuDNN. ] (Issue #10760)
paddlepaddle-gpu 2.5.1 对应的cuda是11.8,cudnn是8.6.0。我刚开始也碰到了这个问题,安装好正确的cuda版本之后就可以正常使用teacher模型了。
问题类似,在paddleOCR中使用ch_PP-OCRv4_det_server_infer模型,也报类似错误。paddlepaddle-gpu 2.5.1 ,cuda11.7、11.8+cudnn 8.6.0、8.6.4、8.6.5都试过,没有解决
你好,请问你解决了吗?我也是CUDA11.7,cudnn8.9.5试过不行。
感谢
―
Reply to this email directly, view it on GitHub<#10760 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/BC2PHUPMUYZRULHWMBGTQTDYJP6ARAVCNFSM6AAAAAA4A6BVJ2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQNJXGQZDGOJYGY>.
You are receiving this because you commented.Message ID: ***@***.***>
|
我也遇到了这个问题,paddlepaddle-gpu 2.6.0 paddleocr 2.7.0 cuda117 cudnn 8.9.7 |
在codelab上遇到同样问题,有大佬出来解答下吗? |
我也遇到了这个问题,paddlepaddle-gpu 2.6.0 paddleocr 2.7.0 cuda118 cudnn 8.9.6 |
加一,解决了吗 |
奇奇怪怪,我一开始使用server版本的v4模型报这个错,但是换了mobile的v4就没事了,cuda11.8+cuudnn8.9,windows |
实测ubuntu20.04+cuda11.8+cudnn8.6可以运行server模型 |
1 similar comment
实测ubuntu20.04+cuda11.8+cudnn8.6可以运行server模型 |
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
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
The text was updated successfully, but these errors were encountered: