BigDong

LGTM

基本上 google scholar 就可以，只不过有一些arxiv 的需要改一下，例如： ``` @electronic{rtmdet, title = {RTMDet: An Empirical Study of Designing Real-Time Object Detectors}, url = {https://arxiv.org/abs/2212.07784}, author = {Lyu, Chengqi and Zhang, Wenwei and Huang,...

During inference time, DiffusionDet will randomly generate noisy boxes, which may affect the AP results.

data_preprocessor.mean and data_preprocessor.std is not trainable parameter, seems can ignore this warning

Seems this PR is not a new feature or bug fix, closed

What does your RLE read structure look like?

The logic of these lines: https://github.com/open-mmlab/mmdetection/blob/6e9cfd4166840a2dff45aa4134a97b9168177ac3/mmdet/datasets/transforms/loading.py#L348-L355 Is to make sure the mask is in a format that can be handled. If your mask is directly an `RLE`, it will not...

You are right, it seems this is a logic error, if you have already fixed this error, PR is welcomed, else, we will fix ASAP

wb, ce, gc images should get from matlab code

Seem this error may be because `DCPDehazeSimple` has registered two times in the code.