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")# pip install -U transformers accelerate # 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 and Reset of Rejected SAM 3 Access Application
Hello Meta SAM 3 Team,
My access request to the facebook/sam3 repository was recently rejected. I would like to kindly request a manual review of my application or a reset of my rejected access status so that I can submit my request again.
Hugging Face Username: byron12312
1. Research / Project Purpose
I am conducting research in computer vision, with a particular focus on image segmentation and visual understanding.
My current research project involves developing an image annotation and segmentation workflow for preparing and evaluating computer vision datasets. I would like to use SAM 3 as a segmentation foundation model to generate high-quality segmentation masks and preliminary annotations.
I also plan to integrate SAM 3 with Label Studio to build an interactive annotation workflow, allowing researchers to review, correct, and refine the automatically generated segmentation results. This will help improve annotation efficiency and consistency during research dataset preparation.
2. Institution / Affiliation
I am an independent academic researcher / graduate student working on computer vision research.
3. Intended Usage
My intended use is academic research and non-commercial evaluation.
I plan to deploy SAM 3 on a local Ubuntu server equipped with an NVIDIA GPU. The model will be used for:
- Image segmentation experiments and performance evaluation.
- Research dataset preparation and annotation.
- Generating and refining segmentation masks.
- Integration with Label Studio for interactive image annotation.
- Exploring the application of foundation models in computer vision research.
The model will be used for research and educational purposes only, and not for commercial deployment, resale, or unauthorized redistribution.
I fully understand that access to SAM 3 is subject to the applicable license terms and usage restrictions. I am willing to comply with the SAM 3 license, Hugging Face policies, and all applicable requirements.
I would sincerely appreciate it if the team could review my application again or reset my access request status so that I may resubmit the application if necessary.
Thank you very much for your time and consideration.
Best regards,
byron12312