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 Manual Review / Reset of Rejected SAM 3 Access
Hello Meta SAM 3 Team,
My request to access the facebook/sam3 repository was recently rejected. I would sincerely appreciate it if you could manually review my request or reset the request status to pending so that I can resubmit any missing or corrected information.
Hugging Face username:
landrock0720
Affiliation:
Independent Researcher
Intended use:
I am working on an industrial computer-vision research project involving automatic annotation of material images for object detection and instance segmentation.
I plan to use SAM 3 locally to generate candidate masks and bounding boxes for a YOLO training dataset. The automatically generated annotations will be reviewed or filtered before being used for model training.
This project:
is limited to industrial material inspection and dataset annotation;
does not involve surveillance, biometric identification, military applications, weapons, or other prohibited applications;
will be performed locally for research and development;
will not redistribute, publish, or share the SAM 3 model weights;
will comply with the applicable SAM 3 license, privacy policy, and usage restrictions.
If any information in my original application was incomplete or inconsistent, I would be grateful for an opportunity to correct it.
Thank you for your consideration.