iumyx2612

[Reimplementation] YOLOX bbox pred using t,l,r,b format always produce loss_bbox: 5.0

13

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection/issues) and [Discussions](https://github.com/open-mmlab/mmdetection/discussions) but cannot get the expected help. - [X] I have read the [FAQ documentation](https://mmdetection.readthedocs.io/en/latest/faq.html) but cannot get the expected help....

I have 2 relatively weak GPUs, how do I toggle Model Parallel training in `qlora.py`?

Attention vs Add in LKA

1

In table 3, changing attention (mul) to add reduces VAN performance from 75.4 to 74.6. I think this is really huge. However, in the ablation study, you stated that "Besides,...

About decomposed large kernel DWConv

2

I found similar decompose idea from [SegNeXt](https://arxiv.org/pdf/2209.08575.pdf). In that paper, authors stated that: "On the other hand, there are some strip-like objects, such as human and telephone pole in the...