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% | ||||
---|---|---|---|---|---|
|
|
Installation¶
QSPARSE can be installed from PyPI:
1 |
|
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
1 2 3 4 5 6 7 8 9 10 11 |
|