New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
about [Gaussian_yolo] #4190
Comments
@Code-Fight Hi, yes.
|
Hi @AlexeyAB ,Thanks for your reply. |
@AlexeyAB Hi, Is Gaussian_yolo layer support for the all cfg's? |
@zpmmehrdad Yes. |
Hi @AlexeyAB ,Thanks |
Try to set |
Hi @AlexeyAB I got it , I will train again |
@AlexeyAB Hi, I just changed [Yolo] to [Gussian_Yolo] and When I use [Gussian_Yolo] for Yolov3_Tiny, I got this error: Thanks |
@zpmmehrdad For instead of (for [yolo]): |
HI ,@AlexeyAB What is the reason? Thanks |
This is normal for [Gaussian_yolo] layer. Check the mAP. |
@AlexeyAB Thanks , I will try again |
Hi @AlexeyAB ,I train again with "map" . |
@Code-Fight I don't know, may be delta of uncertainty is increasing https://github.com/AlexeyAB/darknet/blob/master/src/gaussian_yolo_layer.c#L182-L185 |
@AlexeyAB I got it |
@Code-Fight Hi, What cfg did you use? |
Hi @zpmmehrdad |
@Code-Fight Thanks, Did you check [Gussian_Yolo] with SPP? |
@zpmmehrdad no, i didn't |
@Code-Fight Hi, Could you share the mAP and FPS with [Gussian_Yolo] and with [Yolo] on your dataset? |
@AlexeyAB Have you tried gaussian with yolov2? |
hi @Code-Fight would you show me your final learning rate, thx~ |
@lq0104 Hi,this is my cfgbatch=64 |
Yesterday I train my dataset with gaussian layer, as a result after hundreds of iterators the loss diverge to nan with learning rate=0.001, thanks again and i will try the new learning rate. :) |
@zpmmehrdad HI,sorry,my reply too late. |
Hi, @AlexeyAB
Thanks for you share.
I found you add "[Gaussian_yolo]"
Can I train now?Any precautions?
Trhanks
The text was updated successfully, but these errors were encountered: