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 AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3") - Notebooks
- Google Colab
- Kaggle
Access request for academic Quest 3 MR bowling analytics research
#186
by sri299792458 - opened
Hi,
I’m requesting access to SAM 3 for an academic Quest 3 mixed reality bowling analytics project. I want to evaluate SAM 3 as a video tracking / segmentation model on bowling clips and Quest-captured footage, as a benchmark against YOLO-style baselines.
This is for research use only. I will comply with the license and will not redistribute the weights.
Thanks for your consideration.