Comments (5)
Oh, okay. That's a bit weird to me, but if it works and the original UMX also did it that way I guess it's better to keep it like that.
Thanks,
David
from asteroid.
Hello !
I don't master this architecture, people from Sony do : @r-sawata WDYT ?
from asteroid.
Sorry to have kept you waiting. I was busy due to CVPR deadline, and it has finally gone yesterday. I'll check this in a few days.
from asteroid.
The easiest solution would be using requires_grad=False
as done with the STFT window, but this can generate problems if people try to do transfer learning or fine-tuning and start freezing/unfreezing parts of the model without being aware of this (I've recently gone through this problem and was the reason I found this bug).
I would suggest registering both the scalers and the STFT window as buffers instead of as parameters since that's the general recommendation in Pytorch for model's tensors that are not being optimized. Doing this with the STFT window is quite straightforward (I can do a PR with a fix I've been testing that works well and is backward compatible with pre-trained models) but I'm unsure about how to do this with the scales since Pytorch doesn't have a nn.BufferDict function to replace nn.ParameterDict.
from asteroid.
Sorry for being so late. I confirmed it carefully, and found that mean and scale with requires_grad=True
is fine. Namely, optimizing them during training is our intention.
As you may know, this X-UMX is the extended version of the original one, Open-Unmix (UMX). As shown in the initialization of their implementation, input_mean and input_scale should be learned during training. Please see here:
https://github.com/sigsep/open-unmix-pytorch/blob/4318fb278e1863f4cf8556b513987faf14a15832/openunmix/model.py#L84-L95
from asteroid.
Related Issues (20)
- X-UMX: lr_scheduler_step() missing 1 required positional argument: 'metric' HOT 4
- About the usage HOT 1
- torchmetrics>=0.11.0 HOT 2
- HOW TO USE OTHER DATASET TO TRAIN Multi-Decoder-DPRNN MODEL HOT 3
- val loss in distribute training HOT 2
- refer to asteroid/dsp/overlap_add.py:31 LambdaOverlapAdd model use file_separate output audio file is All noise HOT 2
- KeyError while evaluating musdb18 (X-UMX) HOT 2
- RunTimeError related with NCCL when training librimix recipe HOT 3
- how to train the dataset HOT 3
- Transfer learning of pretrained model on custom dataset HOT 2
- Inference script to hear samples from AVSpeech Model ?
- Support for mobile development (Android)? HOT 3
- PIT Loss for multichannel audio for speech separation HOT 1
- test model
- mossFormer2 & sepTDA models HOT 2
- KeyError: 'source_2_path' when training ConvTasNet using enh_single mode HOT 3
- ConvTasNet pretrained huggingface model inference setup
- How to use GPU rather than CPU
- Separation with sound event time stamps 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 asteroid.