ayooshkathuria / YOLO_v3_tutorial_from_scratch

Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"
https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/
2.32k stars 724 forks source link

bounding boxes not enclosing object #24

Open prachigarg23 opened 6 years ago

prachigarg23 commented 6 years ago

Hi, thanks for the amazing tutorial! I followed each part of your tutorial but when i use it to predict bounding boxes, the boxes aren't enclosing the objects well. Infact the performance is really poor. Can you suggest why this might be happening? I am attaching an image. Also it seems as if the IOU isn't working properly. det_dog-cycle-car

jayden199012 commented 5 years ago

Did you multiple the coordinates with the stride in the yolo layer?

prachigarg23 commented 5 years ago

Yes I did. It was resolved thanks!

On Tue, 16 Oct 2018 at 02:37, pengbo ma notifications@github.com wrote:

Did you multiple the coordinates with the stride in the yolo layer?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/ayooshkathuria/YOLO_v3_tutorial_from_scratch/issues/24#issuecomment-430013399, or mute the thread https://github.com/notifications/unsubscribe-auth/AXhi3fiAc8epv5kH2xUoiZadreBDMvgqks5ulPj7gaJpZM4WXtVf .

anjanaouseph commented 4 years ago

det_dog Same issue, I am getting the bounding boxes all wrong. Can anyone please help!