lzccccc

Hi, You need to put offline kitti eval code under the folder "/smoke/data/datasets/evaluation/kitti/kitti_eval" if you are using the train/val split. It will compile it automatically and evaluate the performance. The...

The visualization code is not included in this repo. A similar one can be found here: https://github.com/lzccccc/3d-bounding-box-estimation-for-autonomous-driving/blob/master/utils/visualization3Dbox.py

@lfydegithub Please follow the steps l mentioned here. > Hi, > > You need to put offline kitti eval code under the folder "/smoke/data/datasets/evaluation/kitti/kitti_eval" > if you are using the...

Hi, How much AP did you achieve? As indicated in Sec. 5.1 of our paper, the performance degrades on train/val set because of the lack of examples. This is reasonable...

Hi, Thanks for your kind words and the detailed description provided regarding the horizontal flip problems. I will start with your second question. I double-checked the rotation transformation in the...

> I do not understand why the angles are being modified back to the original ones as the transformed ones are saved in the targets. The angles are not modified...

The `+-PI` operation is found empirically to transform modified observation angle (3) to roty (2) under horizontal flip condition.

Hi, The result is tested at IoU threshhold 0.5 with 11 recall points

Hi. I did this project for a company so I can not provide you the trained weights. If you use pretrained weights from ImageNet, you can obtain a similar result...

Hi, I don't understand your question.