I’m trying to train a YOLOv8 model on my custom dataset. Each time I export the model, the output shape is (1, 15, 8400). Since I have 11 classes, the expected output shape should be (x, y, w, h, objectness score, 11 labels). With the same dataset, when I train a YOLOv5 model, it correctly outputs (1, 25200, 16). Why is YOLOv8 giving an unexpected output shape?

[The all classes are also in here and you can see the tflite exported shape](https://i.sstatic.net/nSZFFsAP.png)

I tried to check my dataset with yolov5 model and it seems good to me. I tried to change the names of classes made all of them different and also I removed the names. I tried some training parameters I found from internet but it is not working. I can not get the objectness score from the model or is there any way I can get conf score.