Comments (12)
anicolson
commented on May 24, 2024
it seems that there is a problem with your validation set, can you check the size of args.val_s, args.val_s_len, args.val_d, args.val_d_len, and args.val_snr?
from deepxi.
rishabh-ojha98
commented on May 24, 2024
Shape of the validation set parameters are as follows:
args.val_s
(1000, 273520)
args.val_s_len
(1000,)
args.val_snr
(1000,)
args.val_d
(1000, 4832000)
args.val_d_len
(1000,)
Note: I have also added few of the noises of my use case in training as well as in validation set, if that is a problem or not?
from deepxi.
anicolson
commented on May 24, 2024
this should solve your problems: https://github.com/anicolson/DeepXi/blob/master/set/info.txt
from deepxi.
rishabh-ojha98
commented on May 24, 2024
I have followed this info.txt
But given SNR values randomly as [5, 10]
The file name in val_clean_speech are as follows:
1001-134707-0015_noise-free-sound-0210_10dB.wav
1081-125237-0001_noise-free-sound-0531_10dB.wav
1224-121064-0078_noise-free-sound-0768_10dB.wav
1335-163935-0006_noise-free-sound-0592_5dB.wav
1001-134707-0021_uspolo_10dB.wav
1081-125237-0002_noise-free-sound-0365_10dB.wav
1224-121064-0107_noise-free-sound-0157_10dB.wav
1335-163935-0011_noise-free-sound-0768_5dB.wav
The file name in val_noise are as follows:
1001-134707-0015_noise-free-sound-0210_5dB.wav
1081-125237-0001_noise-free-sound-0531_10dB.wav
1224-121064-0078_noise-free-sound-0768_10dB.wav
1335-163935-0006_noise-free-sound-0592_5dB.wav
1001-134707-0021_uspolo_5dB.wav
1081-125237-0002_noise-free-sound-0365_10dB.wav
1224-121064-0107_noise-free-sound-0157_10dB.wav
1335-163935-0011_noise-free-sound-0768_10dB.wav
Is there any issue with randomly generating SNR values? so let me know.
from deepxi.
anicolson
commented on May 24, 2024
does each pair have the same number of samples?
Get Outlook for iOS<https://aka.ms/o0ukef>
…________________________________
From: rishabh-ojha98 <[email protected]>
Sent: Monday, September 9, 2019 8:06:56 PM
To: anicolson/DeepXi <[email protected]>
Cc: Aaron Nicolson <[email protected]>; Comment <[email protected]>
Subject: Re: [anicolson/DeepXi] Training Error? (#8)
I have followed this info.txt
But given SNR values randomly as [5, 10]
The file name in val_clean_speech are as follows:
1001-134707-0015_noise-free-sound-0210_10dB.wav
1081-125237-0001_noise-free-sound-0531_10dB.wav
1224-121064-0078_noise-free-sound-0768_10dB.wav
1335-163935-0006_noise-free-sound-0592_5dB.wav
1001-134707-0021_uspolo_10dB.wav
1081-125237-0002_noise-free-sound-0365_10dB.wav
1224-121064-0107_noise-free-sound-0157_10dB.wav
1335-163935-0011_noise-free-sound-0768_5dB.wav
The file name in val_noise are as follows:
1001-134707-0015_noise-free-sound-0210_5dB.wav
1081-125237-0001_noise-free-sound-0531_10dB.wav
1224-121064-0078_noise-free-sound-0768_10dB.wav
1335-163935-0006_noise-free-sound-0592_5dB.wav
1001-134707-0021_uspolo_5dB.wav
1081-125237-0002_noise-free-sound-0365_10dB.wav
1224-121064-0107_noise-free-sound-0157_10dB.wav
1335-163935-0011_noise-free-sound-0768_10dB.wav
Is there any issue with randomly generating SNR values? so let me know.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#8?email_source=notifications&email_token=AGHGZ7TK2CWX2ZDCGCXECS3QIYN4BA5CNFSM4IUXJD32YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD6G7QXY#issuecomment-529397855>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AGHGZ7STGR2Y6XVINC3GQU3QIYN4BANCNFSM4IUXJD3Q>.
from deepxi.
rishabh-ojha98
commented on May 24, 2024
Got it!!
Thanks @anicolson
Issue is solved now, will let you know if encountered any problem.
from deepxi.
anicolson
commented on May 24, 2024
glad to hear
Get Outlook for iOS<https://aka.ms/o0ukef>
…________________________________
From: rishabh-ojha98 <[email protected]>
Sent: Monday, September 9, 2019 8:28:26 PM
To: anicolson/DeepXi <[email protected]>
Cc: Aaron Nicolson <[email protected]>; Mention <[email protected]>
Subject: Re: [anicolson/DeepXi] Training Error? (#8)
Closed #8<#8>.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub<#8?email_source=notifications&email_token=AGHGZ7VVIBK2WOUTH5ELUCLQIYQMVA5CNFSM4IUXJD32YY3PNVWWK3TUL52HS4DFWZEXG43VMVCXMZLOORHG65DJMZUWGYLUNFXW5KTDN5WW2ZLOORPWSZGOTQHCTVA#event-2618173908>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AGHGZ7V2RUDM3HKQ5EXZFLDQIYQMVANCNFSM4IUXJD3Q>.
from deepxi.
rishabh-ojha98
commented on May 24, 2024
does each pair have the same number of samples?
~ Do we need to have equal number of sampled in each pairs??
from deepxi.
anicolson
commented on May 24, 2024
yea, so for example, you can have a clean speech waveform with 30,000 samples and a noise waveform with 100,000 samples. just extract a section of the noise waveform that is of length 30,000 (and save it). This is done so that the validation set is identical each time. Otherwise the code will mix the clean speech with a random section of the noise signal, meaning that the validation set will be different each time. Does that make sense?
Get Outlook for iOS<https://aka.ms/o0ukef>
…________________________________
From: rishabh-ojha98 <[email protected]>
Sent: Tuesday, September 10, 2019 6:59:58 PM
To: anicolson/DeepXi <[email protected]>
Cc: Aaron Nicolson <[email protected]>; Mention <[email protected]>
Subject: Re: [anicolson/DeepXi] Training Error? (#8)
Reopened #8<#8>.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub<#8?email_source=notifications&email_token=AGHGZ7TSA2PDF3FNDVF5PZTQI5OY5A5CNFSM4IUXJD32YY3PNVWWK3TUL52HS4DFWZEXG43VMVCXMZLOORHG65DJMZUWGYLUNFXW5KTDN5WW2ZLOORPWSZGOTRAFYII#event-2621463585>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AGHGZ7XI7QD5ZG4GBA2T2G3QI5OY5ANCNFSM4IUXJD3Q>.
from deepxi.
rishabh-ojha98
commented on May 24, 2024
yeah got it, thanks
from deepxi.
rishabh-ojha98
commented on May 24, 2024
Just want to clear my doubt
Is there any significance of having dB value in my inferencing wav file?
CA_CA01_03_voice_babble_5dB.wav
from deepxi.
anicolson
commented on May 24, 2024
no, only matters for val set.
Get Outlook for iOS<https://aka.ms/o0ukef>
…________________________________
From: rishabh-ojha98 <[email protected]>
Sent: Wednesday, September 18, 2019 3:43:32 PM
To: anicolson/DeepXi <[email protected]>
Cc: Aaron Nicolson <[email protected]>; State change <[email protected]>
Subject: Re: [anicolson/DeepXi] Training Error? (#8)
Just want to clear my doubt
Is there any significance of having dB value in my inferencing wav file?
CA_CA01_03_voice_babble_5dB.wav
—
You are receiving this because you modified the open/close state.
Reply to this email directly, view it on GitHub<#8?email_source=notifications&email_token=AGHGZ7S3AZQQH7ORY6ILBFTQKG5YJA5CNFSM4IUXJD32YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD663WSA#issuecomment-532527944>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AGHGZ7UXK7L36R7ND4NDTL3QKG5YJANCNFSM4IUXJD3Q>.
from deepxi.
Related Issues (20)
- Multi gpu trainin HOT 4
- Understanding the loss implementation HOT 9
- can i train this model without gpu? HOT 1
- How to run version resnet-1.0n? HOT 1
- Errors during training HOT 2
- What is the major consideration when choosing Hamming window with no periodic? HOT 11
- Clarity on file format reqruired in '/set' folder HOT 1
- no deepxi.network.attention.py file thus no MHANet class HOT 2
- Running Inference/Testing on Multiple GPUs HOT 7
- Training on other noise dataset gives resuts worse than unprocessed noisy HOT 5
- Denoise Live Microphone Feed HOT 1
- I can't find the implementation of addnoise function from deep_xi_test_set.m HOT 4
- Some questions about the data and the training process HOT 5
- Error loading pretrain model during inference HOT 3
- i can not find the freesound packs. does it mean Sound Ids HOT 2
- Some questions HOT 2
- Additional questions HOT 7
- mhanet loss results
- Can the MHANet run in real time HOT 4
- ValueError: No sample.npz file exists. (Inference)
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 deepxi.