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 SAM3 access - 1107wzy
Hello Meta SAM Team,
My access request for the SAM3 Gating Group Collection was rejected. I would like to clarify my affiliation and intended use and request a manual reconsideration.
- Hugging Face username: 1107wzy
- Name: Zhengyang Wang (Alvin)
- Affiliation: Beijing Normal-Hong Kong Baptist University (BNBU)
- Role: Undergraduate student, Computer Science and Technology
- Country/Region: China
My intended use is a local academic computer-vision project involving photographs of sports archery paper targets. I plan to use the official pretrained SAM3 model to segment the arrows visible in these images, and combine the masks with an existing YOLO detector to estimate arrow impact locations and ring scores. The outputs will be checked against human-reviewed image annotations.
I only need pretrained inference for this project; I am not requesting access to train or fine-tune SAM3. My email is verified, and I have updated my public profile to clarify my university affiliation and research interests. I will use the model in accordance with the SAM License and applicable requirements, and will not redistribute the weights.
Could you please reconsider my access request, or reset it to pending if additional or corrected application information is needed? I would be happy to provide further project details through an appropriate channel.
Thank you for your time and consideration.