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 to Reconsider My Rejected SAM3 Repository Access Application (Non-commercial Remote Sensing Image Semantic Segmentation Research)
Dear Meta SAM 3 Team,
My previous application for accessing the facebook/sam3 repository was rejected. I have now fully verified my email address and completed all information on my Hugging Face profile, including my contact details and academic professional background.
I intend to utilize SAM 3 purely for non-commercial academic research on remote sensing image semantic segmentation. My research plans include pixel-level offline semantic segmentation for aerial and satellite remote sensing imagery, extraction of ground object boundary features, land cover classification, and generating semantic point clouds from multi-source remote sensing data for environmental monitoring and land survey research.
All model weights will only be stored and run locally on my personal computing equipment. I will not redistribute or share the weights with any third party. I promise to fully comply with the SAM 3 license, acceptable use policy and all relevant terms.
Could you please re-review my access request or reset my application status so that I can resubmit the permission application again?
My Hugging Face username: zhengyang123456
Thank you very much for your time and support.