PaddlePaddle / PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Apache License 2.0
12.38k stars 2.84k forks source link

'cudaErrorNoKernelImageForDevice #8523

Open Albert57060839 opened 11 months ago

Albert57060839 commented 11 months ago

问题确认 Search before asking

Bug组件 Bug Component

No response

Bug描述 Describe the Bug

I installed paddle-gpu according to my cuda and cudnn version. The paddle.utils.run_check() says successfully install. paddle.utils.run_check() Running verify PaddlePaddle program ... I0809 09:51:49.239790 16004 interpretercore.cc:237] New Executor is Running. W0809 09:51:49.240792 16004 gpu_resources.cc:96] The GPU architecture in your current machine is Pascal, which is not compatible with Paddle installation with arch: 70 75 80 86 , it is recommended to install the corresponding wheel package according to the installation information on the official Paddle website. W0809 09:51:49.240792 16004 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.0, Runtime API Version: 12.0 W0809 09:51:49.244793 16004 gpu_resources.cc:149] device: 0, cuDNN Version: 8.9. I0809 09:51:49.707787 16004 interpreter_util.cc:518] Standalone Executor is Used. PaddlePaddle works well on 1 GPU. PaddlePaddle is installed successfully! Let's start deep learning with PaddlePaddle now.

but when I use gpu to run the pipeline to detect human, it has following error: ExternalError: CUDA error(209), no kernel image is available for execution on the device. [Hint: 'cudaErrorNoKernelImageForDevice'. This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifiescode generation options for a particular CUDA source file that do not include the corresponding device configuration.] (at C:\home\workspace\Paddle\paddle\phi\kernels\gpu\multiclass_nms3_kernel.cu:606) [operator < multiclass_nms3 > error]

复现环境 Environment

paddle 2.5.1 cuda 12.0 cudnn 8.9.1

Bug描述确认 Bug description confirmation

是否愿意提交PR? Are you willing to submit a PR?

jeychandar commented 8 months ago

@Albert57060839 Hi Sir. I also reached the same issue. Could you help me out how to resolve.Thanks in advance.

image

juelietq commented 6 months ago

Has it been resolved?

jeychandar commented 6 months ago

Yes It has been resolved

juelietq commented 6 months ago

How to resolve

jeychandar commented 6 months ago

I am not sure how to resolve for GPU version Instead I worked on CPU and thats worked well. So try to install paddlepaddle cpu instead of paddle paddle gpu.

lyuwenyu commented 4 months ago

应该是nms-gpu有点问题 用最新的paddle版本试一下