EdSong
EdSong
https://github.com/clovaai/WCT2 use this to transform
it is a arbitrary style transfer 发自我的iPhone ------------------ Original ------------------ From: Minami ***@***.***> Date: 周三,10月 19,2022 7:30 下午 To: mousecpn/DG-YOLO ***@***.***> Cc: EdSong ***@***.***>, Comment ***@***.***> Subject: Re: [mousecpn/DG-YOLO] Could...
这是一个很生草的处理，因为数据集定义的时候第一个type是type1不是type0。 如果我把type1的一拿出来制作domain_labels，然后只定义7个type，然后你就会发现domain_labels[:,7]报错了QvQ。 我觉得你应该懂我啥意思。
> Hello, What are used as the training conten and style images? Are coco_2014_train dataset are used as the content images? How's your performance? In original paper, content and style...
> Thans for you reply. There are two questions that confused me. > First, in the reimplement of laplacian loss function, I found it seems diffferent from the original paper....
> > > Thans for you reply. There are two questions that confused me. > > > First, in the reimplement of laplacian loss function, I found it seems diffferent...
> Hello, I re-trained your network using the following images: > > 1. coco_2014 as content images, 9821 landscapes as style images. > 2. random select 50K image pairs in...
> Thank you for sharing the program, it helps a lot. BTW, I found several detail that are different from the paper in this implementation: > > 1. The VGG...
> 你好，这篇利用HDRNET来做样式迁移的应用，我也在复现。目前有一些效果。文章细节缺失，代码也没有公开。复现挺难的。从文章看，要用6次AdaIN，然后如果正则损失过小，也会产生很多偏色。所以regW我设置为100000。最后的效果其实更像是整体颜色的迁移，因为hdrnet本身就是保边滤波，无法迁移样式。 可以分享一下您的结果吗，谢谢