David Yang

About multi-code texture visualization

2

I am trying to reproduce the code visualization part of your paper, and successfully generate reconstructed texture under the single code cases., which I referred to this code snippet: ...

the normal training loss profile

1

hi, author. I have tried training MapTRv2 with the given three auxiliary tasks: depth, pv_seg, bev_seg. However, after training for 24 epochs, I observed that the loss of these auxiliary...

Testing AUC on Ped2 Unmatched

27

I had run the testing script on Ped2 dataset and got an auc of only around 85.1%.

关于作者原文的可视化结果

17

 纯讨论，有木有感觉作者原文给的这个Learnable Mask的可视化结果太细节太规整了？

Carla pre-trained weights

5

is there a release plan for Carla pre-trained weights?

What is the average tokens per second for MiniGPT-4, InstructBLIP-2 and BLIP-2?

Hi ,thanks for the great work. In the paper there is a noise experiment to evaluate the robustness of GKT. However, I cant locate its implementation in the repo. Could...

is by default the second line of label files being the annotations for ego vehicle?

No requirement or environment config file?

1

### Search before asking - [x] I have searched the RF-DETR [issues](https://github.com/roboflow/rf-detr/issues) and found no similar feature requests. ### Description No one reported the environment issue, i try hours of...

[Feature] Request for implementation of VideoMamba

1

### What is the problem this feature will solve? video recognition ### What is the feature? efficient and better precision -> [VideoMamba ](https://github.com/OpenGVLab/VideoMamba?tab=readme-ov-file) ### What alternatives have you considered? Implementation...