Jiamin Ren
Jiamin Ren
What problem? I will give a example soon.
which task did you test? imagenet or face recognition?
Have you changed any code? Just running the script ```face_recognition/train.sh``` will be ok.
This is a distributed framework, and it should be run on multi-gpus by using ```torch.distributed.launch```.
You can show more logs and your codes.
https://github.com/MIC-DKFZ/nnDetection/blob/3416b80cc90346349951dcc805b260f72b80fc16/nndet/io/transforms/instances.py#L126 Plus one and minus one may exceed the image boundary.