-1

I'm trying to train my YOLOv5 to recognize car

That's a simple image in training folder enter image description here

and inside my label i put this bounding box

enter image description here

i resize image and bounding box from 1000x750 to 640x640 and i start training my yolov5 with

!python train.py --img-size 640 --batch 16 --epochs 10 --data ../dataset.yaml --weights yolov5s.pt --freeze 10

but the result from validation is this one enter image description here

seems that all the coordinates of detected cars are shift to left

Any ideas?

Tiru
  • 57
  • 1
  • 6
  • Maybe i found a solution, i have to normalize my bounding box from (x,y,w,h) to (centerx,centery,w,h) – Tiru Dec 29 '22 at 11:51

1 Answers1

0

i think you used bounding box in labeling tools.how about use labelme program. It is using outline instead of bounding box. if you detect car behind the tree, you should use outline instead of bounding box. beacause bounding box is more accuracy than outline. but,The detection is more contouring.

정회준
  • 1
  • 1
  • As it’s currently written, your answer is unclear. Please [edit] to add additional details that will help others understand how this addresses the question asked. You can find more information on how to write good answers [in the help center](/help/how-to-answer). – Community Feb 01 '23 at 15:44