![cuda driver version is insufficient for runtime version cuda driver version is insufficient for runtime version](https://i.imgur.com/MKfLJig.png)
#Cuda driver version is insufficient for runtime version how to#
I have no idea how to solve this problem. However when I run “eval_mot.py”, I get this error:ĬUDA driver version is insufficient for CUDA runtime version In other to run the code I installed PyTorch 0.4 on the docker image by this command: pip install torch=0.4 -f Īs it is written in the readme file of code, I executed the ‘make.sh’, It was successful. I couldn’t run the code, because I had installed the latest version of that image and it includes Cuda 10 and the latest version of PyTorch while the code needs Cuda 9 and PyTorch 0.4).
![cuda driver version is insufficient for runtime version cuda driver version is insufficient for runtime version](https://img-blog.csdnimg.cn/20190226161503719.png)
When I looked at ‘Issues’ on the repository page, It was suggested that Cuda 9.0 and Pytorch 0.4 should be used in order to solve the problem. 0 match only) uninstall the original Cuda device query runtime api version cudart static linking cudagetdevicecount returned 35-> cuda driver. It is written in the readme file of code, first ‘make.sh’ should be executed.
![cuda driver version is insufficient for runtime version cuda driver version is insufficient for runtime version](https://debugah.com/wp-content/uploads/2021/05/573274-20200617171454409-1541198822-624x362.png)
My system has Ubuntu 18.04, Cuda 10.1, last version of CuDNN, 1080Ti GPU and 32 GB Ram.įirst, I installed the latest version of deepo which is a docker image that contains many deep learning libraries. CUDA driver version is insufficient for CUDA runtime version CUDACUDA 1.CUDA driver versionNVIDIA GPU nvidia-smi.