Jianhua Yang

@luyuanmeng It seems that the model you trained achieves a better results.

@luyuanmeng Your [email protected] is 51.23%, better than mine (50% V-mAP). Since the model will be saved after each epoch, you could evaluate the model saved after 3, 4, and 5...

@JULYLH Could you please provide more information about the error? In my device, I can train the model without any errors.

You should check the version of your torch. My torch is 1.9.1, and torchvision is 0.10.1. This error haven't occurred in my environment.

@hdjghjb pull这份代码就ok，项目已经更新，性能请看README

@futureflsl 您好，支持TensorRT的部署，只是最近忙得没时间写这方面的代码，抱歉~

@Student-Wang-wenjie 这些只是在测试flops和模型参数量时的warning信息，不是error，没有影响的～

@luoh226 是的，这个不是原版的YOLOv1，而是我按照YOLOv1的理念重新设计的，是为了配合我的专栏（README中已给出）来入门目标检测用的。

@amartyacodes Hi, this project has been abandoned. I sincerely suggest that you use my other project: https://github.com/yjh0410/PyTorch_YOLO_Tutorial

@r09921135 Hi, Thanks for for your affirmation of my work. JHMDB is a very small-scale dataset, which means that it is easily over fitted. This dilemma requires us to carefully...