Tsinghua-MARS-Lab/DenseTNT

result on AV2

weihuaLi1 opened this issue · 7 comments

weihuaLi1 commented

Argoverse 2 dataset has been released. Have you ever tried to use DenseTNT on it? And what about the result?

GentleSmile commented

We haven't tested it on Argoverse 2 yet. If it goes well, we will update results on Argoverse 2 in August.

yanwu-ge commented

Hello, I am also interested in the results on Argoverse 2. Have you finished the work yet ? When will it be released ? Looking forward to your reply.

GentleSmile commented

We are tuning DenseTNT on Argoverse 2. We add the training code of Argoverse 2 for reference: https://github.com/Tsinghua-MARS-Lab/DenseTNT/tree/argoverse2

Xinchengzelin commented

We are tuning DenseTNT on Argoverse 2. We add the training code of Argoverse 2 for reference: https://github.com/Tsinghua-MARS-Lab/DenseTNT/tree/argoverse2

Hi, do you have plans for updating the Argoverse2 result?
Have you finished the branch argoverse2? I mean the code could run

GentleSmile commented

We are tuning DenseTNT on Argoverse 2. We add the training code of Argoverse 2 for reference: https://github.com/Tsinghua-MARS-Lab/DenseTNT/tree/argoverse2

Hi, do you have plans for updating the Argoverse2 result? Have you finished the branch argoverse2? I mean the code could run

Hi, we have just added evaluation metrics for Argoverse2.

Xinchengzelin commented

We are tuning DenseTNT on Argoverse 2. We add the training code of Argoverse 2 for reference: https://github.com/Tsinghua-MARS-Lab/DenseTNT/tree/argoverse2

Hi, do you have plans for updating the Argoverse2 result? Have you finished the branch argoverse2? I mean the code could run

Hi, we have just added evaluation metrics for Argoverse2.

Could I ask a simple question? If we use Argeverse2 dataset, do we also need Argoverse1 API? Or we just need av2-api?

GentleSmile commented

We are tuning DenseTNT on Argoverse 2. We add the training code of Argoverse 2 for reference: https://github.com/Tsinghua-MARS-Lab/DenseTNT/tree/argoverse2

Hi, do you have plans for updating the Argoverse2 result? Have you finished the branch argoverse2? I mean the code could run

Hi, we have just added evaluation metrics for Argoverse2.

Could I ask a simple question? If we use Argeverse2 dataset, do we also need Argoverse1 API? Or we just need av2-api?

We only need to install av2 using pip