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
8.61k stars 1.48k forks source link

请问下，数据集中的label图像是非黑即白的2色图像，还是在dataloader中会自动处理 #273

Open Testhjf opened 2 years ago

Testhjf commented 2 years ago

hello ,@xuebinqin , 请问下，数据集中的label图像是非黑即白的2色图像，还是原始的背景为白色的rgb图像，然后在dataloader中会自动处理吗？

darrenzhang1007 commented 2 years ago

我也想问

xuebinqin commented 2 years ago

The label (ground truth) should be binarized image masks with shape of H x W x 1 (or H x W x 3) and the background pixels are all black while the foreground pixels are all white.

"还是原始的背景为白色的rgb图像", These type of images are usually with shape of H x W x 4, the last channel is alpha channel, which makes the background region transparent, looks white. If you have this type of data, you need to extract the last channel and output them as separate ground truth masks with shape of HxWx1 or (x3). We don't provide preprocesses to them.

On Tue, Dec 14, 2021 at 6:47 AM YongpengZhang @.***> wrote:

我也想问

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/xuebinqin/U-2-Net/issues/273#issuecomment-993104198, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORK4WIZOPZXJNVELCZDUQ2V5PANCNFSM5JM2CEUA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/