Comments (6)
@sleglaive coming back to this, I am not sure how this can be fixed at the dataloader stage, when nb_channels=1
and a stereo file is loaded as we want the downmix to be done in the magnitude spectrogram domain. If we downmix in the waveform domain already the downmix in the spectrogram layer would never be called.
Instead, for heterogenous datasets, I would propose an upmix_to_stero=True
switch for the dataloaders that would always upmix to stereo by copying the channels and later downmix in the spectrogram domain
@aliutkus additional thoughts?
from open-unmix-pytorch.
Hi Simon, thanks for the issue. This is actually something that we could address as part of #33. I will leave this open until it's fixed.
Regarding a fix, do you agree that the downmix should be done in the magnitude spectrum domain?
from open-unmix-pytorch.
Hi Fabian,
Yes it seems ok to me. Naturally, I would have done the downmix in the waveform domain, but actually I guess you chose the magnitude spectrum domain to avoid phase problems? It is then a good idea, and maybe better than selecting only one channel.
from open-unmix-pytorch.
@sleglaive this is now addressed by #56 and merged into the dev branch. Maybe you can comment on this before we release the new version
from open-unmix-pytorch.
@faroit sorry for the late reply, the solution you propose sounds great to me, thanks a lot!
from open-unmix-pytorch.
Great. I will close this when the dev branch is merged
from open-unmix-pytorch.
Related Issues (20)
- Running umxhq on a large test track (Georgia Wonder - Siren) blows up memory >64GB HOT 11
- SDR performance regression since version 1.0.0 HOT 6
- --help option seems to be broken in v1.2.1 HOT 3
- Error when training. HOT 1
- RuntimeError: "reflection_pad1d_out_template" not implemented for 'Short' : when using separate(...) method HOT 7
- Training Hardware and Issue HOT 11
- Use of Transformers/Attention
- Validation Error HOT 3
- Model download is very slow HOT 2
- multichannel generalized Wiener filter question HOT 1
- Gaps in the resulting audio file in the umxse model HOT 20
- TypeError: umx() got an unexpected keyword argument 'target'
- There was a problem running the openunmix tutorial in colab!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! HOT 1
- How VRAM-hungry is umx supposed to be? HOT 2
- Size difference between umxhq and umxl HOT 2
- Training by trackfolder_fix dataset with bad result HOT 7
- Cannot download 'umx' or 'umxhq' model HOT 6
- AttributeError: module 'openunmix' has no attribute 'Separator' HOT 2
- Cannot Figure Out How to Use without CLI, Docs Do Not Help HOT 2
- ζ沑ζε―δΎmatlabδ½Ώη¨ηηζ¬ HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from open-unmix-pytorch.