ArtyZe

> @ArtyZe How did you manage to export to ONNX model? When I try to export to onnx, I get `RuntimeError: No Op registered for Plugin with domain_version of 9`...

> @ArtyZe DCN's onnx is a custom op not listed on ONNX standard, your visualization result might not accurate. For validation, you can check your onnx inference result using onnx-runtime....

@phamdinhkhanh Hello, have you solved this problem succesffuly?

@ZhxJia @JeasonUESTC 请问你们在voc上训练map值低的问题解决了吗？ :(

> @ArtyZe 这个版本的模型训练不收敛 建议换一个版本的yolo 请问是为啥呀？训练其他的数据集是ok的，只有voc不行。请问您那边训练其他的数据集也不行吗

> @ArtyZe Same observation. Came up with any idea ? No better way but change to another repo :( https://github.com/Peterisfar/YOLOV3.git This one works well in voc dataset. I have trained...

@MichaelSunEngineer Hello, have you solved this problem?

@abhigoku10 recently maybe not, I saw a paper to merge boundingbox detection and image segmentation, I think it's awesome. But first, I need to use yolo realize instance segmentation, maybe...

I have updated my cfg and weights file, now you can try it again. If there are still some problems, please let me know

You can contact me with E-mail, I have tried, it's ok