Yonghye Kwon

@yjh0410 Hi! I recently developed and distributed python package [plotbbox](https://github.com/developer0hye/plotbbox) that is the tool to plot pretty bounding box. I share this with you!

@yjh0410 Thanks a lot! what object detection algorithm do you study now? Do you have recommendations?

@yjh0410 Thanks! Their Idea looks so simple in terms of implementation, but effect is great!

@Broad-sky We only calculate the class loss for positive samples. If we dived its the output of the loss function by the number of all samples, the class loss will...

I also got the same results.

@pogevip In my case, this problem was solved when training the model with lower batch size like 4, 8, and 16.

@lordbutters I used pytorch version 1.0 >= and 1.2

@AI-Passionner Have you ever tested with PP-YOLOE on your custom dataset?

Hi @glenn-jocher ! I found an interesting issue and I tested it with YOLOv5. Recent detection models predicting localization accuracy for detection scores have weak performance in case many objects...

@mornfairy @Annbless @seaman1900 @AK391 1. Split weights with [this modification](https://github.com/ViTAE-Transformer/ViTPose/pull/117/files) 2. Load a model with splitted weights You can properly inference an image after the above steps with wholebody weights....