Skip to content

cnzeki/FeatherCNN-windows

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

license Release Version PRs Welcome

Introduction

FeatherCNN, developed by Tencent TEG AI Platform, is a high-performance lightweight CNN inference library. FeatherCNN is currently targeting at ARM CPUs, and is capable to extend to other devices in the future.

More detail can be found in the original project FeatherCNN. This project port the original codes to the Windows platform, makes it much easier to use.

Build native so for Android

Install Android NDK and run

build_scripts\build_ndk.bat

If everything goes well, headers and so file will be in a new feather directory.

Build model conversion tool

Depends

  • Visual Studio 2015
  • CMake (>3.2)

Environment Setup

Open the appropriate Command Prompt from the Start menu.

For example VS2015 x64 Native Tools Command Prompt:

C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC>

Change to your working directory:

> cd /to/project/dir

If cmake command is not available from Command Prompt, add it to system PATH variable:

> set PATH=%PATH%;C:\Program Files (x86)\CMake\bin

Good. Now you are ready to continue.

Build tool

cd tools
build.bat

feather_convert_caffe.exe will be generated in the tools directory.

Packages

No packages published

Languages

  • C++ 92.6%
  • C 3.6%
  • CMake 1.9%
  • Shell 0.8%
  • Python 0.4%
  • Makefile 0.4%
  • Batchfile 0.3%