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") - Notebooks
- Google Colab
- Kaggle
Request for Manual Review of SAM 3 Repository Access
Hello Meta AI Team,
My recent access request to the SAM 3 repository was rejected, and I would like to ask whether it could be manually reviewed or resubmitted.
I am a master's student at Nanjing University of Chinese Medicine, and my research focuses on medical image segmentation for cardiovascular ultrasound.
Recently, I have been working on a research project exploring the application of SAM 3.1 to echocardiographic image segmentation, with the goal of improving segmentation performance and supporting the development and evaluation of medical imaging models.
I would like to use SAM 3 for benchmarking and evaluating my research pipeline, strictly for non-commercial academic research purposes. I will fully comply with the SAM 3 license and acceptable-use policy.
I suspect my previous request may have been rejected because of incomplete affiliation information or an error in my submission. If necessary, I would be happy to provide additional verification, such as my institutional email address or links to my GitHub or Google Scholar profile.
Thank you very much for your time and consideration.
Best regards,
[Jinzhu Bu]
Master's Student
Nanjing University of Chinese Medicine