Instructions to use facebook/PE-Spatial-L14-448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PerceptionEncoder
How to use facebook/PE-Spatial-L14-448 with PerceptionEncoder:
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("facebook/PE-Spatial-L14-448", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Wrong tag?
#1
by Antuke - opened
The model currently present the Zero-Shot Image classification tag, from what I understand this model is designed to be a feature extractor.
Sorry if I'am wrong.
Thanks for bringing this to our attention! Yeah, the tag was wrong, should be image feature extraction. Actually this was wrong for all the new models π , fixed now.
dbolya changed discussion status to closed