hu-po

Do we wait for Meta to provide a training/fine-tuning script? Or should the open source hivemind write it?

I am attempting some fine tuning in [this repo](https://github.com/hu-po/ashenvenus). Perhaps people can find use in it. The biggest thing I figured out is that you have to break up the...

> Could you please recommend the minimum hardware configuration for fine-tuning the SAM? eg. 4090 x 4? I can get the smallest pre-trained model (`vit_b`) with a batch size of...

> hi @hu-po , > > Thanks for sharing the fine-tuning code very much. Would it be possible for you to give guidance on how to prepare the customized dataset...

> @hu-po > hi, nice work for sharing finetune script , is "FragmentDataset" the datasets that released by official datasets [https://segment-anything.com/dataset/index.html](url) > No, it's a custom dataset for x-ray data...

Perhaps https://www.robots.ox.ac.uk/~vgg/data/voxceleb/ It is CC BY 4.0

Sorry but I am very busy with a different project and I cannot put time into this :( . Best of luck guys!

The `gazenet/unity/gazesim/` folder in the repo can be imported into Unity as a project. From there you can build and run the "game" to generate data. If you are not...