Comments (4)
可行,我做过,是可以训练出来的。
单风格做起来比较简单,直接用cyclegan训练就能到PSNR 22左右,但是多风格训练并不容易,需要加一些对于颜色的正则,不然最后效果不太理想。
我论文里没写这部分,一方面是因为GAN训练出来效果并不好,比监督差很多。另一方面是,我提出的方法就是为了解决训练数据集收集困难的问题,再用GAN就画蛇添足了。
from starenhancer.
非常感谢您的回答!单一的判别器也许无法很好的学到风格,那么如果将明度色度分开,用两个鉴别器,分别学习,这样也许可以提高效果,这只是一个简单的想法,您对此有什么看法呢?
from starenhancer.
我训练的时候,比较类似StarGAN的思路,风格分类器+单个D,效果比较一般,你可以做参考。
多个D分别监督不同的分量,算是一种引入人为先验的方式,应该会有一定效果,但是效果不会明显。我认为可以作为正则,但是想要以此取得明显进步,可能不太可行。
from starenhancer.
谢谢您的解答!
from starenhancer.
Related Issues (11)
- Have you tried image retouching with StarEnhancer? HOT 6
- The results are not the same as the paper
- About pretrain model HOT 1
- One question about the code under the setting of sigle-style enhancement HOT 1
- How can I use style encoder to train classification on my dataset?
- Questions about dataset preparation HOT 4
- Is it possible to use a network such as VGG19 for the style encoder? HOT 4
- Dataset processing HOT 2
- Multi-style, unpaired setting HOT 4
- How to test with my own style HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from starenhancer.