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 Reconsideration of SAM 3 Access
Hello Meta SAM team,
I am an undergraduate student at Xidian University in China. I am currently trying to reproduce the BasketEvent paper for academic learning and research.
This is my first time using Hugging Face, and I may have provided incomplete information or made a mistake in my original access request. I sincerely apologize for any misunderstanding.
I would like to use SAM 3 only to reproduce the paper's basketball player and ball segmentation and tracking pipeline. The model will be used locally for non-commercial academic purposes. I will not redistribute the model weights or use them for surveillance, biometric identification, military, weapons, or any other prohibited applications.
Could you please reconsider my request, or reset it to pending so that I can submit the corrected information?
Hugging Face username: lin139
Affiliation: Xidian University
Program: Undergraduate student
Thank you very much for your time and consideration.
Best regards,
zilin Fang