search

xuebinqin / U-2-Net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Apache License 2.0
8.67k stars 1.5k forks source link

Did u2net face generation was trained with the same loss function? #97

Open shgidi opened 4 years ago

xuebinqin commented 4 years ago

Yes， it is also trained with BCE.

On Nov 21, 2020, at 11:12 PM, shgidi notifications@github.com wrote:

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/NathanUA/U-2-Net/issues/97, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORLT4WU3XJZFTOAMGDLSRCTVHANCNFSM4T6ITCQA.

shgidi commented 4 years ago

Thanks @NathanUA . One more question: did you use the same small dataset of 70 images?

xuebinqin commented 4 years ago

We didn’t include the small set of 70 images in training. We only trained with their around 400 pairs of images in training without pretrained weights.

On Nov 22, 2020, at 4:29 AM, shgidi notifications@github.com wrote:

Thanks @NathanUA https://github.com/NathanUA . One more question: did you use the same small dataset of 70 images?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/NathanUA/U-2-Net/issues/97#issuecomment-731733367, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORLM5AZ5DLLA364DSPTSRDYYFANCNFSM4T6ITCQA.