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
CUDA kernel failed : no kernel image is available for execution on the device #4
Comments
Not sure whether it is because of pytorch installation. By the way, does the same error occur on 2080 Ti or on other repos with pytorch? |
@chenxi-wang 目前在用2080Ti训练graspnet,是没有问题的,之前也用它测试过,也可以。就是尝试用1080的时候出现了问题,这张显卡是最近才装上来的,是还需要什么操作吗 |
@wozxfdha Does 1080 work fine running other programs? If not, you may check your nvidia driver and cuda installation. |
@wozxfdha I have done a test on GTX 1080 with python=3.6 cuda=10.2 pytorch=1.6.0. It works well, try to resetup the environment and check you driver and consumption of GPU memory. |
@wozxfdha I have reproduced your problem. The solution is to recompile pointnet2 and knn module. The reason maybe the change of hardware or the change of CUDA driver. |
I miss the same problem, with cuda11.0, pytorch1.7, python3.8 |
More information is needed. @Qidian213 |
@Fang-Haoshu 问题已经解决了,因为我使用的显卡是GTX3060,算力为 'compute_86', 但是我装的cuda11.0及相应的pytorch只能支持到 'compute_80' 与 'compute_75' ,当我将cuda升级到11.3 安装对应的pytorch就没问题了。 |
哥,我也遇到了这个问题,也没解决,有什么好的办法吗 driver 535 |
您好,我电脑上有两张显卡,一张2080Ti,一张1080,驱动为NVIDIA-SMI 450.66,CUDA10.1
我想在1080上跑测试,于是我将command_test.sh中的CUDA_VISIBLE_DEVICES=0改为了CUDA_VISIBLE_DEVICES=1
但当我运行sh command_test.sh时,会报如下错误:
该错误发生的位置大概是inference()中的
请问是什么原因导致的呢?
The text was updated successfully, but these errors were encountered: