I know that both of re_coco_det and re_coco_gt have the following two fields
img_feat
img_bb
And img_bb in re_coco_gt is ground-truth bounding boxes while in re_coco_det, it is predicted bounding boxes from Faster-RCNN. What about img_feat? How is img_feat calculated in re_coco_gt and re_coco_det, respectively?
Hello,
I know that both of
re_coco_det
andre_coco_gt
have the following two fieldsimg_feat
img_bb
And
img_bb
inre_coco_gt
is ground-truth bounding boxes while inre_coco_det
, it is predicted bounding boxes from Faster-RCNN. What aboutimg_feat
? How isimg_feat
calculated inre_coco_gt
andre_coco_det
, respectively?Thanks for any input!