Where2comm
Where2comm copied to clipboard
MediaBrain-SJTU
Hi, thanks for your inspiring work! There seems no instructions for converting the raw DAIR-V2X to the specific training format, which is referred as `root_dir: "/GPFS/rhome/quanhaoli/workspace/dataset/my_dair_v2x/v2x_c/cooperative-vehicle-infrastructure/train.json"` in the [config file.](https://github.com/MediaBrain-SJTU/Where2comm/blob/efeee4a33b78c362b277d7f698ad4b3b2da0392c/opencood/hypes_yaml/dair-v2x/dair_where2comm_attn_multiscale_resnet.yaml#L3)...
Thanks for your excellent work and wonderful open-source code! When I read the code, I found a possible issue about the implementation of MHA message fusion part. In this line...
Hi, author. Thanks for your great jobs. 1. When does the project support for the other datasets as described in the paper, i.e., V2X-SIm and Coperception? 2. How to access...
hello!I would like to ask how to reproduce these communication volume?In my experiment, by changing the communication threshold, the communication volume will only change between 22.62 and 23.62.
Hi, thanks for your inspiring work! The link that Download raw data of DAIR-V2X is dead. Excuse me, where can I download this dataset? Any advice would be greatly appreciated!
I have reviewed the method you used to calculate communication bandwidth in the paper and code. May I ask if the calculation method you used is to calculate the feature...
 When I try to run the code "CUDA_VISIBLE_DEVICES=7 python opencood/tools/train.py --hypes_yaml opencood/hypes_yaml/dair-v2x/dair_when2com.yaml", it gives me above. I have tried many methods, but none of them work. Hope for your...
您好，感谢您出色的工作，我对您的工作非常关注并敬佩，在论文中我看到您提到使用自创的无人机数据集进行训练，不知到您是否愿意提供无人机数据集相关的训练代码以及yaml配置文件，我愿意有偿咨询相关问题。万分感谢
when I want to train it, `(Where2comm) aitest8@9207cdaf7f93:~/Where2comm$ python opencood/tools/train.py --hypes_yaml opencood/hypes_yaml/dair-v2x/dair_early.yaml Dataset Building Traceback (most recent call last): File "opencood/tools/train.py", line 190, in main() File "opencood/tools/train.py", line 44, in...
``` opencood/models/sub_modules/pillar_vfe.py", line 151, in forward features = pfn(features) RuntimeError: mat1 and mat2 shapes cannot be multiplied (1600000x9 and 10x64) ```
