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 / Reset of Rejected SAM 3 Access β Academic Surgical Research
Hello SAM 3 Team,
My access request to facebook/sam3 was rejected, and I would like to request a manual review.
Hugging Face username: kluykluy
Name: SARUN JUENGPANICH
Affiliation: Zhejiang University
Research purpose:
I am conducting non-commercial academic research on offline surgical anatomy segmentation and robotic suturing simulation.
The checkpoint will only be used for research and offline evaluation. There is no clinical deployment, no execution on a physical robot, and no redistribution of the original model weights.
I will comply with the SAM License and provide appropriate attribution in publications.
Could you please review my request or reset its status to pending?
Thank you for your consideration.