Object counter is toolkit uses YOLO V3(you only look once version 3) algorithm. this toolkit not only make object detection on images/videos but also count the number of objects presents in the image/video.
Hi @DiaaZiada
I'm trying to train Yolov3 on a custom dataset for object counting but I'm running into this issue (ZeroDivisionError: division by zero) in the first epoch of training.
yolo-obj.cfg (Made changes in this file as mentioned in the medium.com link shared above)
Full stack trace:
Traceback (most recent call last):
File "train.py", line 89, in
loss = model(imgs, targets)
File "C:\Users\++\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 722, in _call_impl
result = self.forward(*input, *kwargs)
File "C:\Users\++\Object-Counter-YOLOV3\util\model.py", line 73, in forward
print(module[0](x, targets))
File "C:\Users\++\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 722, in _call_impl
result = self.forward(input, **kwargs)
File "C:\Users\++\Object-Counter-YOLOV3\util\moduler.py", line 128, in forward
precision = float(nCorrect / nProposals)
ZeroDivisionError: division by zero
Hi @DiaaZiada I'm trying to train Yolov3 on a custom dataset for object counting but I'm running into this issue (ZeroDivisionError: division by zero) in the first epoch of training.
Data folder structure is as mentioned in the README and as followed from here: https://medium.com/@anirudh.s.chakravarthy/training-yolov3-on-your-custom-dataset-19a1abbdaf09
data/
config/
Any idea what could be going wrong?