Comments (4)
Cheers for the tips! :) Soon getting back to resuming progress on this project, so I'll be sure to check this out.
I've actually managed to overcome the mode collapse issue I was facing - mainly changing the MSE loss to L1 loss for the reconstruction error was what made the difference (the prior to the KLD loss for the VAE).
Right now it seems to be much more effective - but the training is a bit unstable and sometimes it regresses to learning how to reconstruct the input rather than transfer style to a diff melspectrogram type. But Ive only tested it with a BCE adversarial loss and yet to try out MSE and potentially WSE so! We'll see how things go :) - will nonetheless keep my eyes on these repos. Seriously, thanks for sharing.
Kind regards,
Russell
from tt-vae-gan.
do you have any sample / demo / google drive link?
from tt-vae-gan.
Sure! Here are some demo files I organised with the version of a month ago https://drive.google.com/file/d/1ZHzYvfN_dvZaKuRAdnKUyZ5TL3_JNtxY/view?usp=sharing
This was when the model was configured with 2 residual blocks. At this state, only B2A mappings with BCE worked. Now with 3 residual blocks, A2B also works., and MSE seems to achieve better results that BCE.
More or less the added residual block avoids an error case where it focuses too much on the reconstruction. The sound quality atm is currently like what you hear for B2A BCE in the above.
I'm planning to see if changing resblock designs may improve things. Like to what extent I can stack on more resblocks - given my computation budget - while still avoiding significant vanishing gradients
from tt-vae-gan.
Thanks 🙏
from tt-vae-gan.
Related Issues (14)
- Request to transfer 2 voices over another HOT 6
- Loss evolution for pre-trained models?
- Exploding loss during voice-conversion training HOT 1
- ValueError: Buffer has wrong number of dimensions (expected 1, got 2)
- KeyError: 2 HOT 1
- How to resume training?
- Quick Question regarding convert mel_spectrogram to wav HOT 3
- about calculate KLD HOT 2
- KeyError: 2 HOT 2
- problem with tutorial steps, short files from wavenet HOT 11
- Is this correct? Griffin Lim output almost unintelligible HOT 6
- Two small issues in the script for training the WaveNet vocoder (run.sh) HOT 2
- Improvements to results
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 tt-vae-gan.