How to see the ploted bboxes on image as result along with json output

[deepanshudashora]

I trained the model on cordv2 but I want to plot the coordinates of results also with the text output, How to show/save the output image, or just return the coordinates along with the output

[logan-markewich]

Donut doesn't predict boxes, hence the "OCR-Free" part.

You can, however, use the attention scores to create "heatmaps" of what the model thought the answer was on the page -> https://github.com/clovaai/donut/issues/45