Image Classification
Transformers
ONNX
vit
vision
Inference Endpoints

What task is the model for?

#1
by Jingya HF staff - opened
Hugging Face Optimum org

Hi @regisss , the model was exported with which head?

Hugging Face Optimum org

Better specify it in the readme, there is a contributor using it for semantic segmentation task.

Hugging Face Optimum org

Hi @Jingya , it is the ONNX conversion of google/vit-base-patch16-224 that has a classification head.
You're absolutely right, I'm going to update the model card.

Hugging Face Optimum org
Hugging Face Optimum org

Closing since the PR got merged.

regisss changed discussion status to closed

Sign up or log in to comment