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") - Notebooks
- Google Colab
- Kaggle
Request to reconsider and reset my SAM 3 access application
Hello Meta SAM 3 team,
My previous access request to the facebook/sam3 repository was rejected.
I have now verified my email address and completed my Hugging Face
profile and contact information, including my professional information.
I would like to use SAM 3 for non-commercial robotics and 3D perception
research. My intended use includes offline semantic annotation of RGB-D
frames, semantic point-cloud generation, and semantic scene graph
construction for robot localization and navigation.
The model weights will only be used locally. I will not redistribute the
weights, and I will comply with the SAM 3 license, acceptable-use policy,
and all applicable terms.
Could you please reconsider my request or reset my access status so that
I can submit the gated-access application again?
Hugging Face username: YOUR_USERNAME
Thank you.