GPU memory for fine-tuning mask decoder only

Hi, Thanks for the excellent work.

I will be fine tuning SAM mask-decoder only (keeping image and prompt encoder frozen) on few custom medical images. I have only 8GB of GPU memory available.

Do you think that this capacity is enough for fine-tuning mask decoder only. As in paper, it is mentioned that mask-decoder is very light weight. If not, is there any special setting that I can do to fix the tuning process within available memory?

Thanks!

The issue does not name a file, test, or training entry point. Start with the repository's example notebooks and SAM model code, then determine whether mask-decoder-only fine-tuning and 8GB GPU guidance are documented. Done means providing verified memory guidance or settings for the described setup.

Written by the indexing model from the issue text.