Ziqi Pang

Ahhh sorry. I moved to other datasets for my research and have not tried converting a Vector format ever since. However, you may look at two papers called HDMapNet and...

FYI I just put two more references to the reply above with editing; not sure if they are helpful. Good luck!

I have encountered this before. It might be an installation error. You may try the following steps: 1. Install the right versions of tensorflow. 2. Install waymo_open_dataset from source, instead...

@MaureenZOU Thank you so much for the prompt reply! It is good to know that my current speed is normal, but it is also quite long to train a model...

@z-x-yang Thanks for the quick answer! I previously tried `enable_corr=false` for inference on DAVIS using your provided checkpoints, and the performance is lower than reported in MODEL_ZOO.md. Just double-check that...

@z-x-yang Thanks for the reply! I forgot to update that I figured this out. However, I believe that [this line](https://github.com/yoxu515/aot-benchmark/blob/ada8a3cbf0ba6dde563a49e78e56dbbcde01d143/networks/layers/attention.py#L523) in `MultiHeadLocalAttentionv3` needs to add `.permute(2, 0, 1, 3).reshape(h *...

@manikamakam I haven't used KITTI before. But I think you can start from imitating the style in [data preprocessing](https://github.com/TRI-ML/PF-Track/blob/main/documents/preprocessing.md). If you have finished this and want to proceed, we can...

@hibernationT Thanks for your question! It is unfortunate that I don't have GPU resources to run PF-Track right now. So I might request more information from you to debug. As...

Thank you for the reply! I have some incomplete list of IDs on the sample tracking sequence. Please check on the following objects: 6c5faf3e-04ed-4f45-94e9-bb57b345f6eb 2af61a36-20b0-4bfe-b341-dc4d03548ead f0ccac2d-4dd6-44a8-9d18-feb030186149 371947d1-c28c-415a-924b-e39500b4f961 e7297ebe-a5af-4be3-ae61-bc28ec3fcdfa 26731792-9dc0-483f-8b08-63e50b19f85a Thank...

They are all from the sample point cloud sequence, and the IDs above are the track_id, belonging to different objects (tracklets). Hopefully, this time my expression is rigorous lol.