# SMU激活函数-Pytorch

**Repository Path**: luokai-dandan/smu-activation-function

## Basic Information

- **Project Name**: SMU激活函数-Pytorch
- **Description**: SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE
github原作者链接 https://github.com/iFe1er/SMU_pytorch，
对原作者SMU.py添加绘图，使得SMU更容易理解，且绘图和原论文一致。
希望能够帮助到大家，一起”快乐“地学习深度学习！
- **Primary Language**: Python
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: https://gitee.com/luokai1997
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-11-18
- **Last Updated**: 2022-07-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: Python, PyTorch, 深度学习, 神经网络, 激活函数

## README

# SMU_pytorch
A Pytorch Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE

## The original author's link
https://github.com/iFe1er/SMU_pytorch

## arXiv
https://arxiv.org/abs/2111.04682

## Requirements
Pytorch 1.7

Matplotlib

Numpy

## Tensorflow version of SMU activation
Please check https://github.com/iFe1er/SMU for tensorflow 2.x implementation.


## Reference:
>@ARTICLE{2021arXiv211104682B,
>       author = {{Biswas}, Koushik and {Kumar}, Sandeep and {Banerjee}, Shilpak and {Pandey}, Ashish Kumar},
>        title = "{SMU: smooth activation function for deep networks using smoothing maximum technique}",
>      journal = {arXiv e-prints},
>     keywords = {Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Neural and Evolutionary Computing},
>         year = 2021,
>        month = nov,
>          eid = {arXiv:2111.04682},
>        pages = {arXiv:2111.04682},
>archivePrefix = {arXiv},
>       eprint = {2111.04682},
> primaryClass = {cs.LG},
>       adsurl = {https://ui.adsabs.harvard.edu/abs/2021arXiv211104682B},
>      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
>}