Can sam-hq perform breakpoint training: continue training on the already trained sam-hq, or continue training on the official sam-hq weights

Open YUANMU227 opened this issue 1 year ago • 2 comments

Can sam-hq perform breakpoint training: continue training on the already trained sam-hq, or continue training on the official sam-hq weights？

Modifying the --start_epoch parameter will not allow continued training on the existing epoch_*.pth.

How to perform breakpoint training?

Mar 13 '24 09:03 YUANMU227

It seems that currently the restore restore_model logic is available only on eval: https://github.com/SysCV/sam-hq/blob/322488826bda616798901c6280d13a9a90444ae7/train/train.py#L361-L373

Mar 18 '24 16:03 bhack

@lkeab Can you share the sam-hq only network checkpoint so that we could eventually restore it for the train?

Mar 21 '24 11:03 bhack