模型加速：WAE-Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks

时间 2021-01-02

标签 WAE 模型加速繁體版

原文原文链接

WAE(Wavelet-like Auto-Encoder) 是由来自中大、哈工大、桂电等多机构的多名研究人员合作提出的，发表于AAAI-2018(论文地址： https://arxiv.org/pdf/1712.07493.pdf github 创新点： 1. WAE借助小波分解得思想，将原图分解成两个低分辨率图像，以达到网络加速的目。（PS：整体思路：下采样的方法达到网络加速，但是下采样会导

>>阅读原文<<

1. 论文笔记：Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
2. 模型加速--Slimmable neural networks
3. Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
4. 神经网络压缩（9） WAE-Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
5. Neural Networks and Deep Learning -- Class 4: Deep Neural Networks
6. Improving Deep Neural Networks
7. Neural Networks and Deep Learning -- Class 3: Shallow neural networks
8. [paper]Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
9. Neural Networks and Deep Learning
10. Improving Deep Neural Networks [1]
更多相关文章...
• Docker 镜像加速 - Docker教程
• ASP.NET MVC - 模型 - ASP.NET 教程
• 使用阿里云OSS+CDN部署前端页面与加速静态资源
• 委托模式

最新文章

1. 升级Gradle后报错Gradle‘s dependency cache may be corrupt (this sometimes occurs
2. Smarter, Not Harder
3. mac-2019-react-native 本地环境搭建(xcode-11.1和android studio3.5.2中Genymotion2.12.1 和VirtualBox-5.2.34 )
4. 查看文件中关键字前后几行的内容
5. XXE萌新进阶全攻略
6. Installation failed due to: ‘Connection refused: connect‘安卓studio端口占用
7. zabbix5.0通过agent监控winserve12
8. IT行业UI前景、潜力如何？
9. Mac Swig 3.0.12 安装
10. Windows上FreeRDP-WebConnect是一个开源HTML5代理，它提供对使用RDP的任何Windows服务器和工作站的Web访问

本站公众号

欢迎关注本站公众号,获取更多信息

1. 论文笔记：Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
2. 模型加速--Slimmable neural networks
3. Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
4. 神经网络压缩（9） WAE-Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
5. Neural Networks and Deep Learning -- Class 4: Deep Neural Networks
6. Improving Deep Neural Networks
7. Neural Networks and Deep Learning -- Class 3: Shallow neural networks
8. [paper]Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
9. Neural Networks and Deep Learning
10. Improving Deep Neural Networks [1]

>>更多相关文章<<