Open macclark3 opened 3 years ago
Unfortunately, WIT only works for simple classification or regression tasks. It doesn't have support for handing bounding boxes as outputs.
The Language Interpretability Tool (https://github.com/PAIR-code/lit/, https://pair-code.github.io/lit/) is a successor of WIT and will have support for Image models as of tomorrow's release version 0.4. It also doesn't have bounding boxes as a supported output type, but the LIT tool is fully extensible and it could be added by someone like yourself.
Hello, I'm new to WIT and am wondering if it can be used on a multi-class object detection model? The model outputs bounding box coordinates and classification for each detected object in the image.