10000 GitHub - XueqiaoPeng/DSXplore: DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions [IPDPS-2021]
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions [IPDPS-2021]

License

Notifications You must be signed in to change notification settings

XueqiaoPeng/DSXplore

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions

Accepted at IPDPS-2021 [arxiv]

Author: Yuke Wang, Boyuan Feng, and Yufei Ding
Email: yuke_wang@cs.ucsb.edu

Install

  • Dependency: Python 3.7, nvcc 11.1.
  • Install Conda to set up an virtual environment Toturial.
  • Install Pytorch with GPU support Toturial.
  • Go to SCC_conv/, then python setup.py install.

Run

  • Avaiable Models [model name]: VGG11, VGG13, VGG16, VGG19, ResNet18, ResNet34, ResNet50, MobileNet.
  • Avaiable groups [num_group]: 1,2,4,8.
  • Avaiable overlap [overlap_ratio]: 0.25,0.33,0.50,0.75.
  • Then execute python main.py --model [Model Name] --groups [num_group] --overlap [overlap_ratio] .
  • A detailed example of changing backend convolution implementation is illustrated in models/vgg.py.

Reference

Train CIFAR10 with PyTorch

About

DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions [IPDPS-2021]

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 67.3%
  • Cuda 27.6%
  • C++ 5.1%
0