peteanderson80/bottom-up-attention

Could you share the class labels of VQA object detection using Faster R-CNN?

Kerry-zzx opened this issue · 5 comments

Could you share the class labels of VQA object detection using Faster R-CNN?

Hi,
Could you share the mapping from class id to class label for Faster R-CNN?

@Kerry-zzx @abhidipbhattacharyya were you able to get this mapping. I am also looking for the same, but it is difficult to get.

Actually with little more digging found the vocabulary here - https://github.com/peteanderson80/bottom-up-attention/tree/master/data/genome/1600-400-20.

qin79 commented

if i want to get the class(label) of the bounding box, how can i do?
should i rewrite the bottom-up-attention/tools/generate_tsv.py to get?

@qin79 I could get class labels, bounding box and features using this repo - https://github.com/airsplay/py-bottom-up-attention.