AlessandroMondin / YOLOV5m

A personal implementation of YOLOv5 (v6.0)
46 stars 12 forks source link

code question #5

Open xjyisok opened 5 months ago

xjyisok commented 5 months ago

Dear author it seems that in loss.py the YOLO_LOSS can only accept just one image's tensor like[3,H,W],but in train_utils.py the trainloop accept a batch of images,so the YOLO_LOSS can't get the loss of the whole batch

AlessandroMondin commented 5 months ago

Hi are you getting an error or something? I haven't used this repo in the last 18 months, feel free to open a PR :)