Instructions to use facebook/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="facebook/sam3")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request for Manual Review of Rejected SAM 3 Access
Hello SAM 3 Team,
My access request for facebook/sam3 was rejected, with no reason provided. I would like to request a manual review, or a reset of my status from rejected to pending, so that I can reapply.
Hugging Face username: zhiliao1820172250
Affiliation: PhD researcher, The Hong Kong Polytechnic University
Use: non-commercial academic computer vision research
I intend to run SAM 3 locally to segment robot arms, grippers, and manipulated objects in tabletop demonstration videos. The masks will be used only for dataset annotation and evaluation in 3D scene understanding / affordance research (robot learning). I will not use the model for military, surveillance, weapons, or other restricted applications, and I will not redistribute the checkpoints.
I will comply with the SAM 3 license, Meta’s acceptable-use policy, Meta Privacy Policy, and Hugging Face terms.
Could you please reconsider the request, or reset it so I can submit a complete application again?
Thank you for your time.