Closed xevolesi closed 4 years ago
Try to:
remove stopbackward=1
and add max_delta=10
for each [yolo]
layer
If it doesn't help try to
or remove mosaic=1
or use iou_loss=mse
instead of iou_loss=ciou
Thanks!
I'll try both options and will notice you.
Hi, @AlexeyAB !
Your first suggestion worked well.
Here is final chart:
Do you think this is the effect of max_delta or stopbackward removal?
Do you think this is the effect of max_delta or stopbackward removal?
I don't know what did you do
Hi, @AlexeyAB !
Try to:
* remove `stopbackward=1` * and add `max_delta=10` for each `[yolo]` layer
i did this
Hi @AlexeyAB !
I trained YOLOv3 with custom data set. Classes:
I used YOLOv3 .cfg file with 416x416 input and added "good hyperparameters" from #4430
Here is my chart.png
Here is my yolov3.cfg: yolov3-default-416-mosaic-scale-ciou.cfg.txt
Some image examples from training and validation sets:
I checked my labels - it seems like it's correct, because earlier i trained default YOLOv3 and it gave me about 77% mAP. Could you, please, tell me what could happen with my training?
Thanks!