Closed vehxianfish closed 3 months ago
Hi, @junjie18 . This question baffles me till now. Could you explain? Thank you very much.
@vehxianfish
Hi, thanks for your detailed comment. I think it is a history mistake when I try to seperate task and head.
In the final version of CMT, only one task head is provided, center
, height
, dim
, rot
and vel
can be replaced with one head(10 channels) here for acceleration. However, the calculation is not totally equal due the non-linearity between the two layers.
It maybe a small bug that have small influence on the final result. Welcome to share your new result.
Thanks for your response. I will try
Hi,@junjie18, thanks for your wonderful work and for opening the code.
I have a question about the formation of the format of prediction bounding boxes. For prediction boxes, the code is
which means pred_bbox is
cx, cy, cz, w, l,h, rot.sin(), rot.cos(), vx, vy
for gt_boxes in compute lossesBut in the denormalize box for the test:
, the format is
cx, cy, w, l, cz, h, rot.sin(), rot.cos(), vx, vy
. Can you give some explanations? thanks a lot