Is it possible to use Giskard for computer vision / images?

[j-adamczyk]

Checklist

• [x] I've searched the project's issues.

❓ Question

As in title, is it possible to use Giskard for computer vision, i.e. image datases? I am using HuggingFace for vision CNN models (ResNet, ConvNeXt etc.) and would like to test them.

[luca-martial]

Thanks for the question @j-adamczyk ! We're in the process of working on support computer vision. Would be great to get your feedback on our upcoming work.

[yassineAlouini]

@luca-martial Any chance you are starting to work on this for computer vision? I would be happy to research the state-of-the art about perturbation methods for binary classification for CV let's say to get started. Let me know if this could help. :ok_hand:

[luca-martial]

@luca-martial Any chance you are starting to work on this for computer vision? I would be happy to research the state-of-the art about perturbation methods for binary classification for CV let's say to get started. Let me know if this could help. 👌

@yassineAlouini Thanks for suggesting this! We'll get back to you asap with more info!

[henchaves]

@luca-martial Any chance you are starting to work on this for computer vision? I would be happy to research the state-of-the art about perturbation methods for binary classification for CV let's say to get started. Let me know if this could help. 👌

Hey @yassineAlouini, now we have a dedicated repo for CV: https://github.com/Giskard-AI/giskard-vision

[yassineAlouini]

@luca-martial Any chance you are starting to work on this for computer vision? I would be happy to research the state-of-the art about perturbation methods for binary classification for CV let's say to get started. Let me know if this could help. 👌

Hey @yassineAlouini, now we have a dedicated repo for CV: https://github.com/Giskard-AI/giskard-vision

That's great news!