question of bbox in VQA feature

[1144181135]

Hi VilBert team, I read your code of VQA dataset: vilbert/datasets/vqa_dataset.py. And I see the bbox is shape of "N x 5". I have some questions:

1. what's the meaning of dimension 5? A bbox information maybe [x1, y1, x2, y2] with dimension 4. What's the last dimension mean? Classification score?
2. Does the bbox coordinations [x1, y1, x2, y2] need to be normalized to 0~1 ?
   That's all. Thank you.

[jiyt17]

Hello bro, the answer can be found in VILBERT paper and /vilbert/datasets/_image_features_reader.py