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 / Reset of Rejected SAM 3 Access β Academic Landslide Segmentation Research
#342
by sdshsk12345 - opened
Hello Meta SAM 3 Team,
My access request for the facebook/sam3 model repository was recently rejected. I would sincerely appreciate it if you could manually review my application or reset my application status so that I can submit the required information again.
**Hugging Face username:**sdshsk12345
Research purpose:
I am conducting academic research on landslide recognition and segmentation using UAV and remote-sensing imagery. I plan to use SAM 3 for the following non-commercial research purposes:
- Prompt-based segmentation of landslide regions;
- Semi-automatic annotation of irregular landslide boundaries;
- Comparison with SAM 2.1 and domain-specific segmentation models;
- Evaluation of transfer learning for geological-hazard imagery;
- Research on improving landslide boundary recognition.
The model will only be used for academic research and evaluation. I will comply with the applicable license, privacy policy, and acceptable-use requirements. I will not redistribute the model weights or use them for unauthorized commercial purposes.
Could you please reconsider my application or reset its status so that I can reapply with complete information?
Thank you very much for your time and consideration.
Best regards,