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 SAM 3 Access Application(been rejection)
Hello Meta SAM 3 Team,
My access request for 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 the application again if necessary.
I am a PhD researcher at Northwestern Polytechnical University conducting non-commercial academic research in computer vision, robotics, and 3D scene understanding. I intend to use SAM 3 primarily for image/video segmentation and automatic annotation of interactive object regions, supporting research on 3D scene understanding and visual affordance learning for robotic manipulation.
The model will be used for local inference in an academic research setting. I will comply with the SAM 3 license, Meta policies, and Hugging Face terms. I will not redistribute the model weights or provide the checkpoints to third parties.
My intended use is strictly for academic research, with no military, surveillance, weapons, or other restricted applications.
I would greatly appreciate it if you could manually review my request or reset the rejected status so that I can reapply.
Thank you for your time and consideration.
Best regards,
PhD Researcher
Northwestern Polytechnical University