YouLookv6: Shame On You

[m00nLi]

The so call "YOLOv6":

https://github.com/ultralytics/yolov5:

[gachiemchiep]

@m00nLi What made you so mad? From your image, I can see some improvements in inference speed, model size, flops.

[m00nLi]

Are you sure? 田忌赛马吗？

[gachiemchiep]

@m00nLi Yes I am. I clean up their report numbers a little bit. I only take the inference speed of Speed of (V100, fp32, batch=32). The input size is set into 640

Then the number look like this

I put the number in Excel so you can comment if you want https://docs.google.com/spreadsheets/d/1AA2d6p7emfuh96Trsle33IPdt0YsYY7QtnXtWsArt6o/edit?usp=sharing

I think authors are still doing their experiments, so bashing them right now is not a good option. I am not Chinese so If you can, please write in English.

[ruabliuqiu]

lose face

You can you up. Don't BiBi if you can't

[m00nLi]

Let me show you: "YOLOv6-n": 11.1 GLOPs, YOLOv5n: 4.5 GFLOPs "YOLOv6-tiny": 36.7 GLOPs, YOLOv5s: 16.5 GFLOPs "YOLOv6-s": 44.2GLOPs, YOLOv5m: 49 GFLOPs Is that clear enough?

[m00nLi]

GFLOPs

Let me show you: "YOLOv6-n": 11.1 GLOPs, YOLOv5n: 4.5 GFLOPs "YOLOv6-tiny": 36.7 GLOPs, YOLOv5s: 16.5 GFLOPs "YOLOv6-s": 44.2GLOPs, YOLOv5m: 49 GFLOPs Is that clear enough?

就你眼尖

I regret your inability

[ruabliuqiu]

GFLOPs

Let me show you: "YOLOv6-n": 11.1 GLOPs, YOLOv5n: 4.5 GFLOPs "YOLOv6-tiny": 36.7 GLOPs, YOLOv5s: 16.5 GFLOPs "YOLOv6-s": 44.2GLOPs, YOLOv5m: 49 GFLOPs Is that clear enough?

就你眼尖

I regret your inability

你若是有能力的话，岂不应该先跑通代码，弄清楚改进点，总结出值得学习的地方，然后再客观评价该算法吗？而不是一上来就喷

[gachiemchiep]

Let me show you: "YOLOv6-n": 11.1 GLOPs, YOLOv5n: 4.5 GFLOPs "YOLOv6-tiny": 36.7 GLOPs, YOLOv5s: 16.5 GFLOPs "YOLOv6-s": 44.2GLOPs, YOLOv5m: 49 GFLOPs Is that clear enough?

That is clear for me. I get your point. They're still in work. Let's them continue your work. If their work still sucks. I will apologize you.