-
Notifications
You must be signed in to change notification settings - Fork 7.9k
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
Add GIoU loss into this repo? ~+3 AP@[.5, .95] #3249
Comments
I will think about it: |
@AlexeyAB this is used for training or inference ? |
@tdurand |
@tdurand thanks and sorry for this other question, I went through the paper and the website but failed to understand if those trained weight published here: https://github.com/generalized-iou/g-darknet#pre-trained-models improves inference speed / accuracy ? Or is it just a method to train faster ? |
@tdurand As they said, the MS COCO AP@[.5, .95] was increased: https://arxiv.org/pdf/1902.09630v2.pdf It means that by training with GIoU:
Checking mAP on MS COCO 2014 validation dataset Yolo v3 (not spp) Using these weights-files: https://github.com/generalized-iou/g-darknet#pre-trained-models mAP@0.75 - (IoU_threshold = 75%)
Result is slightly different than in Pycoco-tool, since Pycoco-tool takes into account parameters mAP@0.50 (IoU_threshold = 50%)
Result is slightly different than in Pycoco-tool, since Pycoco-tool takes into account parameters |
many thanks ! |
Explanation of AP(GIoU)-metric: generalized-iou/g-darknet#12 (comment) |
Is it possible to evaluation the GIoU metric with this repo? |
Do you mean mAP@GIoU_treshold instead of mAP@IoU_treshold ?
correct classifications are slightly less likely but the bounding boxes are tighter |
@AlexeyAB |
@yrc08 Yes. |
@AlexeyAB
Thank you very much for your prompt reply.
…------------------ 原始邮件 ------------------
发件人: "Alexey"<notifications@github.com>;
发送时间: 2019年10月23日(星期三) 晚上6:47
收件人: "AlexeyAB/darknet"<darknet@noreply.github.com>;
抄送: "洋葱"<2990064358@qq.com>;"Mention"<mention@noreply.github.com>;
主题: Re: [AlexeyAB/darknet] Add GIoU loss into this repo? ~+3 AP@[.5,.95] (#3249)
@yrc08 Yes.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
YoloV3 with GIoU loss implemented in original Darknet as https://github.com/generalized-iou/g-darknet
Will GIoU loss be supported in this version of Darknet?
The text was updated successfully, but these errors were encountered: