Skip to content

Tensorflow2 implementation of Data-driven Harmonic Filters for Audio Representation Learning

Notifications You must be signed in to change notification settings

jaehwlee/tf2-harmonic-cnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Tensorflow2 implementation of Data-driven Harmonic Filters for Audio Representation Learning

Data-driven Harmonic Filters for Audio Representation Learning

Minz Won, Sanghyuk Chun, Oriol Nieto, and Xavier Serra

ICASSP, 2020

Reference

Prerequisited

Usage

  • Requirements

$ conda env create -n {ENV_NAME} --file environment.yaml
$ conda activate {ENV_NAME}

  • Preprocessing

$ python -u preprocess.py run ../dataset
$ python -u split.py run ../dataset

  • Training

$ python train.py

  • Options

'--conv_channels', type=int, default=128
'--sample_rate', type=int, default=16000
'--n_fft', type=int, default=512
'--n_harmonic', type=int, default=6
'--semitone_scale', type=int, default=2
'--learn_bw', type=str, default='only_Q', choices=['only_Q', 'fix']
'--input_legnth', type=int, default=80000
'--batch_size', type=int, default=16
'--log_step', type=int, default=19
'--model_save_path', type=str, default='./../saved_models'
'--gpu', type=str, default='0'
'--data_path', type=str, default='./../../tf-harmonic-cnn/dataset'

To be changed

tf.keras.optimizers.adam -> tfa.optimizers.AdamW
tf.keras.optimizers.sgd -> tfa.optimizers.SGDW

Author

About

Tensorflow2 implementation of Data-driven Harmonic Filters for Audio Representation Learning

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages