QSPARSE

QSPARSE provides the open source implementation of the quantization and pruning methods proposed in Learning Low-Precision Structured Subnetworks Using Joint Layerwise Channel Pruning and Uniform Quantization. This library was developed to support and demonstrate strong performance and flexibility among various experiments.

Full Precision	Joint Quantization _4bit and Channel Pruning _75%
import torch.nn as nn net = nn.Sequential( nn.Conv2d(3, 32, 5), nn.ReLU(), nn.ConvTranspose2d(32, 3, 5, stride=2) )	import torch.nn as nn from qsparse import prune, quantize, convert net = nn.Sequential( quantize(nn.Conv2d(3, 32, 5), bits=4), nn.ReLU(), prune(sparsity=0.75, dimensions={1}), quantize(bits=8), quantize(nn.ConvTranspose2d(32, 3, 5, stride=2), bits=4) ) # Automatic conversion is available via `convert`. # Please refer to documentation for more details.

Full Precision

Joint Quantization _4bit and Channel Pruning _75%

import torch.nn as nn
net = nn.Sequential(
    nn.Conv2d(3, 32, 5),
    nn.ReLU(),
    nn.ConvTranspose2d(32, 3, 5, stride=2)
)

import torch.nn as nn
from qsparse import prune, quantize, convert
net = nn.Sequential(
    quantize(nn.Conv2d(3, 32, 5), bits=4), 
    nn.ReLU(),
    prune(sparsity=0.75, dimensions={1}), 
    quantize(bits=8),  
    quantize(nn.ConvTranspose2d(32, 3, 5, stride=2), bits=4)
)
# Automatic conversion is available via `convert`.
# Please refer to documentation for more details.

Installation

QSPARSE can be installed from PyPI:

pip install qsparse

Usage

Documentation can be accessed from Read the Docs.

Examples of applying QSPARSE to different tasks are provided at examples and mdpi2022.

Citing

If you find this open source release useful, please reference in your paper:

Zhang, X.; Colbert, I.; Das, S. Learning Low-Precision Structured Subnetworks Using Joint Layerwise Channel Pruning and Uniform Quantization. Appl. Sci. 2022, 12, 7829. https://doi.org/10.3390/app12157829

@Article{app12157829,
	AUTHOR = {Zhang, Xinyu and Colbert, Ian and Das, Srinjoy},
	TITLE = {Learning Low-Precision Structured Subnetworks Using Joint Layerwise Channel Pruning and Uniform Quantization},
	JOURNAL = {Applied Sciences},
	VOLUME = {12},
	YEAR = {2022},
	NUMBER = {15},
	ARTICLE-NUMBER = {7829},
	URL = {https://www.mdpi.com/2076-3417/12/15/7829},
	ISSN = {2076-3417}
}

Metadata

Release files for qsparse 2.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for qsparse 2.0.1
File	Size	Uploaded
qsparse-2.0.1.tar.gz	97.5 kB	Sep 19, 2022	Details

Release files / qsparse-2.0.1.tar.gz

Download URL	qsparse-2.0.1.tar.gz
Size	97.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`4c597b525347f7c13fdb97f36d8fd0f4fd18111d86868d2f7f516fc703ce9689`
BLAKE2b-256 checksum How to use checksums	`c5bbde1f84ea41a5fe08deddcf672bde073cf3db73a071296058e324c5ab1d18`
Upload date	Sep 19, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.5`