Comments (4)
With the iteration of training, the loss of the discriminator is gradually reduced, which is the optimal convergence of its discriminative ability. The generator loss will gradually converge to an equilibrium position following the discriminator loss. In the process of style transfer, the content loss will definitely increase gradually, because the initialized generator generates realistic pictures. Then, with the stylization training, the generated pictures will no longer be so realistic, so the content loss will gradually increase . Regarding the style loss, its decrease indicates that the stylized training is making progress, which is consistent with the training goal. The color reconstruction loss is essentially a part of the content loss. It is the calculation of the pixel-level difference between the generated image and the input photo, but it is processed through different color formats.
from animeganv2.
Thanks for the quick response and your clarification makes it crystal clear lol!
b.t.w, I noticed that the color loss and tv_loss are negligible comparing with other losses, (in my training, they are both less than 1 even after multiplied by their weights), is this normal or did I miss something important?
from animeganv2.
Actually, color reconstruction loss and tv_loss do not need more weights, they are just auxiliary functions. If the color reconstruction loss is too great, the generated image will appear very real. If tv_loss is too large, the resulting image will become very blurry. As shown in the screenshot below (from AnimeGANv3), the tv_loss weight on the left picture is 100, and the tv_loss weight on the right picture is 10. The weight of tv_loss in the third image is 1000. In fact, they still look blurry. The tv_loss is generally used as a regularization term of the objective function to smooth the generated image. Its goal is to punish the difference between adjacent pixels in the horizontal and vertical directions, so that the difference between pixels in the entire picture is smaller and the image will be smoother. It has certain resistance to noise and artifacts, but when the weight of this regularization term is too large, the generated image will become very blurry due to excessive smoothing.
from animeganv2.
Got it! Thanks for your explanation and really appreciate your time to collect those amazing demo images. I am closing this issue and looking forward to seeing AnimeGANv3 comes out.
from animeganv2.
Related Issues (20)
- the generated pictures are some vague
- Where to download the paper of AnimeGANv2? HOT 1
- ImportError: cannot import name 'trace' HOT 2
- 使用项目里自带的模型转换完和原图差别很小?如何增强动漫效果呢? HOT 4
- 在nvidia A4000显卡上无法训练
- Exception has occurred: OperatorNotAllowedInGraphError HOT 5
- How to train face model? HOT 1
- 商业产品合作怎么联系你们 HOT 1
- Could you share how you get the improvements that you mentioned in the readme?
- NFT creator
- Failed to save model
- How to use 512 x 512 or higher-definition pictures for training
- 直接运行代码存在问题 HOT 1
- Requirement file HOT 6
- Why are all the pictures in the sample_dir file_b.jpg black HOT 2
- Is it possible to use AnimeGANv2 without GPU? Only with Intel CPU? HOT 1
- tensorflow-gpu 1.15.0 可以替换成相应的 cpu版本吗 HOT 1
- Anime the picture
- Can this be used without a GPU, on a Mac M1?
- Inference with pre-trained model and sample data is not working. HOT 4
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 animeganv2.