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
Reconsideration Request for SAM3 Access - liu-panhua
#245
by liu-panhua - opened
Dear Meta Team and Hugging Face Support,
My previous request to access facebook/sam3 was rejected. I am a researcher focusing on archaeological heritage digital preservation and cultural relic image analysis.
I only intend to use SAM3 for non-commercial academic research:
- Segmenting archaeological site features from aerial and ground survey images
- Detecting and segmenting cultural relics (pottery, murals, stone artifacts) for standardized documentation
- Supporting 3D reconstruction of heritage sites with pixel-level segmentation masks
I confirm that I will not use the model for any commercial purposes, and all outputs will be used solely for research and academic publications in the field of cultural heritage conservation.
My Hugging Face username is liu-panhua, and my registered email is phliu@cncis.com.cn.
Could you please reconsider my request? Thank you for your time and consideration.
Best regards,
Liu Panhua