Huanyu Wang

or you should rename DCN-1.0-py3.7-linux-x86_64.egg to DCN or dcn

Tips: You should change the codes before make. so, first git clone the repo, then make sure your gcc version >=4.9, and change the code as mentioned @xvjiarui , last...

I don't know the details, but the `resource.setrlimit(resource.RLIMIT_NOFILE, (20480, rlimit[1]))` should be like this: 20480 < rlimit[1] so, you should print the rlimit before this line, and make sure rlimit[1]...

Hi, I test weights from DarkNet project, and still a small amount margin between yours (u3_preview) and https://github.com/AlexeyAB/darknet. Details: test2017: weights from AB, tested with u3_preview, image resolution 416x416 ![138491607954857_...

thx for your answer, but i wonder what is the implementation of scale_x_y, I'm not that familiar with YOLOv4 🙏

set batch_size=1 will bring new problem, the solution list here https://github.com/eriklindernoren/PyTorch-YOLOv3/pull/163/commits/83c3d8b2f440f78715fb674b3d318c63ffe3eb16

same mAP: 0.5145

what if I don't build with opencv?

> It should be work if you change the code in ./tf_extended/metrics.py Line 51. > "return variables.Variable" =>> "return variables.VariableV1" Actually, it works!

maybe something wrong with your model, training from scratch is hard to get high result according to other issues.