Skip to content

Build a deep learning inference framework from scratch

License

Notifications You must be signed in to change notification settings

masteryi-0018/MiniNN

Repository files navigation

MiniNN

Build a deep learning inference framework from scratch

download

# https
git clone --recursive https://github.com/masteryi-0018/MiniNN.git

# ssh
git clone --recursive git@github.com:masteryi-0018/MiniNN.git

build

windows

  1. cmake
.\build.ps1
  1. bazel
.\bazel.ps1

更多请查看:https://github.com/masteryi-0018/MiniNN/blob/main/docs/README.md

linux

  1. cmake
./build.sh
  1. bazel
./bazel.sh

更多请查看:https://github.com/masteryi-0018/MiniNN/blob/main/docs/README.md

quick start

windows

  1. cmake
.\build\mininn\test-main.exe
.\build\mininn\test\gtest-main.exe
  1. bazel
.\bazel-bin\mininn\test-main.exe
.\bazel-bin\mininn\gtest-main.exe

linux

  1. cmake
./build/mininn/test-main
./build/mininn/test/gtest-main
  1. bazel
./bazel-bin/mininn/test-main
./bazel-bin/mininn/gtest-main

TODO

  1. mininn convertor
  • 支持将onnx模型转换为gynn格式
  • 支持将pytorch模型转换为gynn格式
  • 支持将tensorflow模型转换为gynn格式
  1. mininn IR
  • 支持多算子构图
  1. mininn kernel
  • 增加opencl后端
  • 增加cuda后端
  1. 工具类
  • 增加示例程序,链接mininn.so
  1. 构建系统
  • 引入flatbuffers头文件,集成到bazel脚本中
  • Windows使用bazel构建
  • Windows使用msvc编译问题解决
  • 使用clang编译器
  1. 疑问
  • 堆上申请内存的示意图

About

Build a deep learning inference framework from scratch

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published