Comments (8)
Perhaps i misunderstood the paper but doesnt the discriminator suppose to updated as well in the second atep?
from cyclegan-vc2.
i'd fixed the problem in master branch, thanks all of you.
from cyclegan-vc2.
Hi, I am also wondering that. I think the implementation of adversarial loss is indeed missing.
from cyclegan-vc2.
yes, it indeed missed the second step adverserial loss.
I add the second step adverserial loss in the branch "2nd-step-adverserial-loss"
from cyclegan-vc2.
@Jeffery-zhang-nfls Thank you for the contribution! Will look at this later.
from cyclegan-vc2.
Hi @Dannynis and @Jeffery-zhang-nfls,
I am also wondering that...I thought this second step is only happening for updating the discriminator loss?
Or am i misunderstanding as well?
from cyclegan-vc2.
Hi all,
I thought the 2-step loss is only happening in discriminator based on paper, but the discriminator became too strong based on my experiments.
Anyway, just for anyone who want to try 2-step loss....The followings are for your reference.
Here I only put one side of code for depicting clearly. You can finish another side on your own, and remember to update final generator and discriminator loss, too.
Generator 2-step loss part 1
d_cycle_A = self.discriminator_A(cycle_A)
Generator 2-step loss part 2
generator_2step_BAB = torch.mean((1 - d_cycle_B) ** 2)
Discriminator 2-step loss part 1
two_step_A = self.generator_B2A(self.generator_A2B(real_A)) d_two_step_A = self.discriminator_A(two_step_A)
Discriminator 2-step loss part 2
d_loss_A_two_step = (torch.mean((d_real_A - 1)**2) + torch.mean(d_two_step_A**2))
from cyclegan-vc2.
I think we are supposed to introduce two more networks and . Paper clearly says in Sec 3.1 "we introduce an additional discriminator". The code currently re-uses main discriminators.
from cyclegan-vc2.
Related Issues (20)
- RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. HOT 2
- 是否数据量越多,转换的语音质量越好呢? HOT 2
- Not compatible with librosa 0.8.0
- 请问该模型需要大概多长时间就能得到比较好的效果 HOT 1
- a pre-trained model is necessary?
- 怎么推理啊
- 关于模型ASSERT复现的一些问题
- model中的checkpoint HOT 1
- 训练之后是否可以将文本转为某个人音色的语音? HOT 1
- how to run a demo with a new speech HOT 6
- train loss
- How to do the inference of the model?
- Problem with using my own data HOT 2
- How to infenrence?
- Any way to re-synthesis audio? HOT 1
- 有没有兴趣复现CycleGAN-VC3? HOT 3
- FileNotFoundError: [Errno 2] No such file or directory: './model_checkpoint/_CycleGAN_CheckPoint' HOT 6
- how long will the training part take HOT 1
- torch.cuda.is_available() is False but check the python cmd torch.cuda.is_available() is true HOT 7
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 cyclegan-vc2.