Thanks for this nice work. I wrote a quick PoC to showcase that you can easily have integration so that you can automatically load the various MobileSAM models using from_pretrained (and push them using push_to_hub), track download numbers for your models (similar to models in the Transformers library), and have nice model cards on a per-model basis. It leverages the PyTorchModelHubMixin class which allows to inherits these methods.
Usage is as follows:
from mobile_sam import MobileSAM
model = MobileSAM.from_pretrained("nielsr/mobilesam")
Hi @ChaoningZhang @qiaoyu1002 and team!
Thanks for this nice work. I wrote a quick PoC to showcase that you can easily have integration so that you can automatically load the various MobileSAM models using
from_pretrained(and push them usingpush_to_hub), track download numbers for your models (similar to models in the Transformers library), and have nice model cards on a per-model basis. It leverages the PyTorchModelHubMixin class which allows to inherits these methods.Usage is as follows:
The corresponding model is here for now: https://huggingface.co/nielsr/mobilesam. We could move all checkpoints to separate repos on your account on https://hf.co if you're interested.
Would you be interested in this integration?
Kind regards,
Niels