B2D_VAD_Dataset

[Zhihua-Hua]

In your code, the ego_lcf_feat of the B2D_VAD_Dataset has been modified, where the first two dimensions and the eighth dimension differ from those in VAD.

Bench2DriveZoo/mmcv/datasets/B2D_vad_dataset.py

Line 227 in 914b328

ego_lcf_feat[0:2] = input_dict['ego_translation'][0:2]

Bench2DriveZoo/mmcv/datasets/B2D_vad_dataset.py

Line 232 in 914b328

ego_lcf_feat[7] = np.sqrt(input_dict['ego_translation'][0]**2+input_dict['ego_translation'][1]**2)

https://github.com/hustvl/VAD/blob/3c2929fe36034b8881fd549394ee62f56b8ea44c/tools/data_converter/vad_nuscenes_converter.py#L508
Does it have any special meaning?

[jiaxiaosong1002]

@Zhihua-Hua Hi, good point! It is indeed a bug. However, since the feature is fed into MLP later, it would not be a big problem and you may fix the bug and re-train the model by yourself. We do not anticipate any major influence and thus we leave it here so that the public leaderboard is stable.