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 Reconsideration of Rejected SAM 3/3.1 Access Request
Dear Meta SAM Team:
Hello. I am a Chinese university student and I am currently conducting research on the topic of AI-assisted image annotation. As far as I know, SAM 3 and SAM 3.1 perform extremely well in this regard. Therefore, I would like to try deploying and running SAM 3 or SAM 3.1.
This is an independent personal project. It has no relation to any organization and is solely for my personal use. Moreover, I will strictly adhere to all the requirements of the Meta SAM team.
My initial request for access was rejected. Perhaps it was because I did not explain my intended use clearly enough. Could you reconsider my request for access, or reset its status so that I can submit corrected and more complete information?
If you need any other information, please do let me know.
Thank you very much for your time and assistance.