Metadata-Version: 2.1
Name: tqt
Version: 1.0.2
Summary: torch implement of TQT
Home-page: https://github.com/PannenetsF/TQT
Author: Pannenets F
Author-email: pannenets.f@foxmail.com
License: BSD-3-Clause License
Keywords: quantization NN torch
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: GPU
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Requires-Python: >=3.7.*
Description-Content-Type: text/markdown
License-File: LICENSE

# TQT
TQT's pytorch implementation.

## Notice

Now availabel at `pip install tqt`!

Networks quantized via this package could be find at [https://github.com/PannenetsF/QuantizationPool](https://github.com/PannenetsF/QuantizationPool).

# Contributing 

It will be great of you to make this project better! There is some ways to contribute!

1. To start with, issues and feature request could let maintainers know what's wrong or anything essential to be added. 
2. If you use the package in you work/repo, just cite the repo and add a dependency note! 
3. You can add some function in `torch.nn` like `HardTanh` and feel free to open a pull request! The code style is simple as [here](style.md).

# Acknowledgment 

The initial version of tqt-torch is developed by [Jinyu Bai](https://github.com/buaabai). 

The beta version was tested by [Jinghan Xu](https://github.com/Xu-Jinghan), based on whose feedback a lot of bugs were fixed.

The original papar could be find at [Arxiv, Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks](https://arxiv.org/abs/1903.08066).

