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 Review of Rejected SAM3 Access Application
Hello Meta SAM3 team,
My Hugging Face username is @zemengzero .
I recently submitted an access request for the SAM3 Gating Group Collection, but the request was rejected without a reason being displayed.
I would appreciate clarification and respectfully request a review of my application.
My intended use is a research and engineering evaluation of SAM3-based open-vocabulary object detection and tracking. Specifically, I plan to evaluate the open-source DART (Detect Anything in Real Time) framework on a small private video test set.
The evaluation will:
- use SAM3 only for local inference;
- focus on person, dog, and cat detection and temporal tracking;
- not redistribute, publish, or expose the SAM3 checkpoints;
- not use SAM3 for any prohibited, military, surveillance, or unlawful purpose;
- comply with the SAM License, Meta Privacy Policy, and applicable export-control requirements.
If my request was rejected because any application field was incomplete or inconsistent, please let me know what needs to be corrected. I am happy to provide accurate affiliation and research-purpose information through an appropriate private channel.
email: zemengzero@gmail.com
Organization: Huazhong University of Science and Technology
Hugging Face username: zemengzero
Could you please reconsider my access request or advise me on the appropriate next step?
Thank you for your time and assistance.