object_level_visual_reasoning icon indicating copy to clipboard operation
object_level_visual_reasoning copied to clipboard

Using mask rcnn data

Open nirat1606 opened this issue 4 years ago • 1 comments

Hi Fabien,

I want to use the mask-rcnn predictions for EPIC-Kitchen dataset. Can you elaborate how to interpret the pickle files provided as Complementary data-masks. For beginning, I would like to know a way to overlay mask and bounding boxes on the corresponding frames. Any tutorial or readme for doing so would be highly appreciated

Thanks, Nirat

nirat1606 avatar Nov 22 '19 23:11 nirat1606

Hi Nirat,

Thanks for the interest in our work. You can find the line by line implementation about how to retrieve the bboxes/segmentations for each detected objects per frames here. First I am retrieving the object id, then reformatting the bounding box and finally rescaling the mask. If you feel that the predictions are not good enough you can use this pre-trained Mask-RCNN on your own data. I hope that these explanations could help for your work. Best,

Fabien

fabienbaradel avatar Dec 02 '19 10:12 fabienbaradel