Perceptual loss network
Closed this issue · 7 comments
tkone2018 commented
感谢你的分享，请我我可以在Perceptual loss network里将vgg16模型换成resnet?
proteus1991 commented
可以的,任何backbone其实都可以用来作为perceptual loss的supervision.
tkone2018 commented
好的，谢谢
tkone2018 commented
还有一个问题就是，代码模块中是如何体现Feature Fusion with Channel-Wise Attention的？可以简单的解答一下吗？谢谢！
proteus1991 commented
@tkone2018 请看一下对应的文章吧, 写的很详细了.
tkone2018 commented
好的
proteus1991 commented
那是因为有些图是rgba格式,所以需要转换成rgb. 请在issue里面提问吧, 这样大家都能看到.
谢谢,
Xiaohong
…On Sun, 12 Jul 2020 at 03:24, tkone2018 ***@***.***> wrote:
gt.shape torch.Size([4, 240, 240])
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#12 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AF2V4GRVT3JFASE2GYTWXZLR3FQL3ANCNFSM4OQFIG3Q>
.
tkone2018 commented
@proteus1991 我昨天自己改好了，我就给撤销了，我下次碰到问题我就单独写出来哈