Non-official BandSplit implementation as a TF 2.0 layer
Implementation of the BandSplit technique used in "Music Source Separation with Band-split RNN".
Installlation
pip install bandsplit_tensorflow
Usage
import tensorflow as tf
from bandsplit_tensorflow import BandSplitLayer
# Input parameters
input_time_dim = 100
input_freq_dim = 257
batch_size = 100
sr = 16000
# Hyperparameters
sub_band_feature_dim = 128
# Define layer
band_split_layer = BandSplitLayer(input_freq_dim=input_freq_dim, sr=sr, sub_band_feature_dim=sub_band_feature_dim)
# Use layer
random_spectrogram = tf.random.normal((batch_size, input_time_dim, input_freq_dim))
result = band_split_layer(random_spectrogram)
print(result)
Notes:
- The implementation is only designed for a sample rate of 16 kHz
1 maintainer
Metadata
1 maintainer
Release files for bandsplit-tensorflow 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| bandsplit_tensorflow-0.1.2.tar.gz | 4.1 kB | Without provenance | Details for bandsplit_tensorflow-0.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| bandsplit_tensorflow-0.1.2-py3-none-any.whl | Python 3 | none | any | Details for bandsplit_tensorflow-0.1.2-py3-none-any.whl |
Total release size: 8.3 kB
Release files / bandsplit_tensorflow-0.1.2.tar.gz
| Download URL | bandsplit_tensorflow-0.1.2.tar.gz |
|---|---|
| Size | 4.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d872f4648223366a6cbceff66ea2d29b4e4cfa2dbda98a6cb4cd493462d872da
|
|
BLAKE2b-256 checksum How to use checksums |
c8e64ff26d0a5e4d1e113d457e8c9a6ed0e72cb087502c06a7918451d4074a47
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.4
|
Release files / bandsplit_tensorflow-0.1.2-py3-none-any.whl
| Download URL | bandsplit_tensorflow-0.1.2-py3-none-any.whl |
|---|---|
| Size | 4.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e1ed379b029b695825834024d490745f2df4e2a0996ea4cece3b54f4a61ddce3
|
|
BLAKE2b-256 checksum How to use checksums |
49956f605d3c0f4c5d5d9dfe9cf8234f30c60e3b7b3b96ba9b8e5a5a113b462b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.4
|
Security for bandsplit-tensorflow 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
