EmbCaffe---基于Caffe的优化前向计算的框架

See project in github : https://github.com/FreeApe/EmbCaffe

Embedded Caffe

  Make the depth learning model running on Embedded Systems and multi-platform.

Features

• Based on caffe
• Compact，Only forward calculation
• Support faster rcnn
• Support ssd
• Support GPU/CPU model(Windows only support CPU model now)
• Cross-platform
• Small
• Remove the gtest
• Remove the test
• Remove the python wrapper

Requirements

Linux

System              : Linux / Ubuntu 14.04Cmake               : 3.4+C++ compiler        : 4.8+BLAS                : AtlasBoost               : 1.54glog                : Ygflags              : Yprotobuf            : 2.6.1CUDA                : 7.5cuDNN               : 5.0.5OpenCV              : N (for examples)

Windows

System              : WindowsCmake-gui           : 3.8+C++ compiler        : vc140(VS2015)embcaffe_3rdparty   : https://github.com/FreeApe/embcaffe_3rdparty

Build

Build EmbCaffe on Linux

• Way 1

# Note: Test examples with this way$ cd EmbCaffe$ mkdir cmake_build$ cd cmake_build$ cmake ..$ make all -j

• Way 2

$ cd EmbCaffe$ make all -j

Build EmbCaffe on Windows

1. with CMake-gui3.8+2. git clone https://github.com/FreeApe/embcaffe_3rdparty(You can also compile these third-party libraries yourself)2. Configure and Generate(You should configure CMAKE_INCLUDE_PATH and CMAKE_LIBRARY_PATH)3. Open Caffe.sln with VS20154. build solutions

Build examples

  Linux:

$ cd examples$ mkdir build$ cd build$ cmake ..$ make -j

  Windows:

1. with CMake-gui3.8+2. Configure and Generate3. Open Caffe-example.sln with VS20154. build solutions5. run demos

  Running the examples, the results show as :

Build Errors

1. error ‘type name’ declared as function returning an array escape    Make sure the CUDA version is 7.5

TODO / Targets

• Remove Backward calculation
• Support GPU model on windows
• Optimize the calculation
• ……

Thanks

• https://github.com/BVLC/caffe
• https://github.com/intel/caffe
• http://blog.csdn.net/zxj942405301/article/details/72775463