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 Rejected SAM 3/3.1 Access Request
#349
by ZitanGong - opened
Hello,
I am a student conducting academic research on semantic segmentation of
low-altitude UAV imagery. I would like to evaluate SAM3 as a zero-shot
baseline on a public semantic segmentation competition dataset.
The model will only be used for academic experimentation and performance
evaluation. It will not be used for surveillance, identification, military,
or other prohibited applications.
Could you please reconsider my access request?
Thank you.
ZitanGong changed discussion status to closed