Instructions to use ETH-CVG/lightglue_superpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ETH-CVG/lightglue_superpoint with Transformers:
# Load model directly from transformers import AutoImageProcessor, AutoModelForKeypointMatching processor = AutoImageProcessor.from_pretrained("ETH-CVG/lightglue_superpoint") model = AutoModelForKeypointMatching.from_pretrained("ETH-CVG/lightglue_superpoint") - Notebooks
- Google Colab
- Kaggle
Example Not Working
#4
by Tobi314 - opened
Hi,
First of all, thanks for providing this model!
I think there is a small problem with the example. The example currently says one should do:
from transformers import AutoImageProcessor, AutoModel
processor = AutoImageProcessor.from_pretrained("stevenbucaille/lightglue_superpoint")
model = AutoModel.from_pretrained("stevenbucaille/lightglue_superpoint")
However, this does not work. I think the correct call should be:
from transformers import AutoImageProcessor, AutoModel
processor = AutoImageProcessor.from_pretrained("ETH-CVG/lightglue_superpoint")
model = AutoModel.from_pretrained("ETH-CVG/lightglue_superpoint")
This is also what is provided when one clicks on "Use this model".
It's no big deal but it would be great if the example worked out of the box.
Hi @Tobi314 ,
Thanks for letting us know, this is indeed a leftover from development, I fixed it now !
Steven
stevenbucaille changed discussion status to closed