Would LiT support Object Detection Computer Vision models?

Question

Would LiT support Object Detection Computer Vision models?

lhphanto opened this issue 2 years ago · 1 comments

Question as in the title. Thanks! :-)

Answer 1 · 2023-02-06T04:17:05.000Z

I think it would be possible. Image input should work fine, but you may need to do some custom UI work (https://github.com/PAIR-code/lit/wiki/frontend_development.md#custom-client--modules) to show the bounding boxes. If you wanted to just show the outputs as a list though, like [("Car", 0.85), ("Bicycle", 0.78), ...] you could use the existing SparseMultilabel() output type.