Training Contribution

[lucasjinreal]

If you have spare GPU or spare time, please help YOLOv7 training models! Currently we are planned to train models on:

• YOLOX with Keypoints head;
• YOLOv7 with NASVit as backbone;

If you want contribute, please leave a message below. I'll guide you how to train.

[PeterSmith1]

我有两张空闲的1080ti，您要是有需要，我可以试着去训练

[lucasjinreal]

@PeterSmith1 我们可以在这个thread跟进，协同起一波训练任务：https://github.com/jinfagang/yolov7/discussions/46

[shoujilywork]

你好, 我领第二项ViDet 或者和SwinTrans2相关的

[lucasjinreal]

@shoujilywork Hi, thanks for contribution, if you wanna track on ViDet, you can following this steps:

1. Create a dicussion issue to track ViDet training thread;
2. fork this repo, and adding ViDet related model code and PR, I will guid you how to train and modify.

I think ViDet can be adopt from official repo, but we can test it on a more wide backbone range in yolov7 framework.