Rauf Yagfarov

I use wbf function like this: `wbf_weights = [2,1]` `bboxes_after, scores_after, _ = weighted_boxes_fusion(bboxes_before, scores_before, labels, weights=wbf_weights, iou_thr=0.5, skip_box_thr=0.5)` I have two models. Here is what i got: Before WBF...

Hi! Could you show arguments you pass ?

@sarimmehdi I have the same problem. I don't multiply intrinsic matrix by waymo_cam_RT in adapter.py and multiply objects coordinates to transformation matrix from vehicle to camera coordinate system (Tr_velo_to_cam) and...

I found a solution and made changes in [my fork](https://github.com/RocketFlash/Waymo_Kitti_Adapter) of this repo. I transformed 3D bounding boxes into KITTI styled ( 3D bounding boxes in camera coordinate system). And...

@z393 I am using https://github.com/kuixu/kitti_object_vis for visualization. Have you tried to visualize this sample without KITTI convertation ? Maybe problem is in shifted boxes due to interpolation based labelling. Try...

Tried to train the model without AMP and mAP start growing. I've read other issues and it seems something wrong with AMP training

Why this feature disappeared in versions >= 1.0.0 ?

@Charmve I understand that it's not possible to get it directly, but I think maybe it's possible somehow get such things from some internal layers ? Features responsible for "glassness"...

Yes, the problem was in visualization, or in data representation. Conversion code from this repo presents box as center point of the box, but kitti uses center of the bottom...