This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 37
mAP predicted by student_model is sometimes higher than teacher #42
Comments
@firekeepers 请问你训练自己的数据集修改了什么参数,我用cityscapes的yaml配置训练自己的数据集,metrics.json中的结果比faster-RCNN source-only的结果差距20%左右,这个结果肯定不对,想请教一下哪些参数可以修改? |
@firekeepers 还有一个问题,我用VGG16训练可行,但是换为R101的时候,训练中总是会出现total_loss, loss_cls, loss_box_reg都为Nan,learning rate 从0.02,0.002,0.0002,0.00002都试过,训练时还是total_loss, loss_cls, loss_box_reg都为Nan |
主要调整burn-in阶段的训练时常吧,我也不确定根据你的数据集如何调整 |
好的,谢谢 |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
I train the model with my dataset,but the ap50 is instable, I may get vary different result by same parameters.
Moreover,the teacher' AP50 sometimes lower than student'AP50.
Is this phenomenon normal in DAOD?
The text was updated successfully, but these errors were encountered: