TorchSemiSeg
TorchSemiSeg copied to clipboard
docker error
When I use your docker to train,the error occured,it is likely that the version of cuda driver is too low.But my cuda driver is 465.19.01,which is supported CUDA11.3,the cuda in the docker is only 10.1,it is compatible,right?I don't why,can you help me?I will appreciative.

Hi, the docker is based on Cuda 10.1. It is recommended to install Apex in your machine manually.