Where2comm

Where2comm copied to clipboard

I have solved a problem by following these steps： Download the dair-v2x(cooperative-vehicle-infrastructure )dataset and the new annotation data as mentioned in the github homepage of where2comm Organize your dataset file...

xmccl

How to prepare the CoPerception-UAVs dataset for training?

3

Hi, thanks for your great work! I want to reproduce this model on the Coperception-UAVs dataset. How can I get the yaml and build_dataset.py?

RanTT1996

A question about the implementation of communication mask generation.

2

Happy rabbit year! Can you please explain why we need reset the communication mask to ones **with a stride of 2** in the following line (https://github.com/MediaBrain-SJTU/Where2comm/blob/5ea31dcc4e102fc45a3dfcc5bff0339ee06543ac/opencood/models/comm_modules/where2comm.py#L71)? I cannot find anything...

Little-Podi

x_fuse.append(self.fuse_modules[i](neighbor_feature)) if you use Transformer as the fusion model. You need to input four parameters, so why just one neighbor_feature ?

sidiangongyuan

Questions about the camera branch

1

I have already reproudced your result in DAIR-V2X and received expected results. However, in your paper you claimed to use both camera and LiDAR as input, while in this repository...

chensiweiTHU

Hi, thanks for sharing the code for your excellent work. In the current README, it seems that the dataset support does not include the OPV2V dataset, can you provide more...

ry4nzhu