cydiachen

Using MMDet version of VFNet with the lastest backbone (e,g. Poolformer S36, ConvNeXt Small) with Inf Issues on Varifocal loss

1

Thank you for your excellent work. I am now experiment on improving VFNet with the latest model backbone. (e,g. Poolformer S36, ConvNeXt Small) The network works fine on the first...

Any idea of implement on MMDetection codebase?

6

Thx for your excellent job. I am free to provide you with 4 * 3090 gpus to reproduce the PPYoloE results. But most of my work is based on MMDetection...

[Feature] Add flag for output labelImg label file in image_demo

2

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

[Feature] Add visdrone dataset

2

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

Tensor mismatch on infer an image for gradio.

14

Hello. When I tried to deploy the gradio demo locally, It came up with the error that "ape/modeling/backbone/utils_eva02.py", line 346, in forward def forward(self, t): return t * self.freqs_cos +...