Xin Li
Xin Li
Hi, based on my personal experience, while running a jupyeter notebook locally, I have to change the kernel for my running file manually. Have you been able to check on...
MMYOLO currently supports a deploy solution cooperating with MMDeploy and a dedicated project called easydeploy. You can try both methods.
I got this problem on my single RTX4090 with Pytorch nightly installed with Cuda 11.8. After I had switched to Pytorch nightly on CUDA12.1, the problem was gone.
Translate "How to set random seed" to English -> [PR#930](https://github.com/open-mmlab/mmengine/pull/930)
Well, I came across this issue too. I was using a single 4090 and changed the batch size to 8 and it still failed. It seemed that it was not...
Hi, I solved this problem by re-specifying the torch versions in ~/.bashrc using `export LIBRARY_PATH=${you cuda lib64 path}:$LIBRARY_PATH` instead of $LD_LIBRARY_PATH. A bit wield.