EmbCaffe---基于Caffe的优化前向计算的框架
来源:互联网 发布:华西附二院抢号软件 编辑:程序博客网 时间:2024/05/16 05:48
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
阅读全文
0 0
- EmbCaffe---基于Caffe的优化前向计算的框架
- caffe源码学习:softmaxWithLoss前向计算
- Caffe源码解读: SoftmaxLayer的前向与反向传播
- Caffe源码解读: Softmax_loss_Layer的前向与反向传播
- (Caffe,LeNet)前向计算(五)
- caffe代码解读-mnist例子-前向计算
- 基于 SSM框架的前后端分离
- 基于RTP的FEC前向丢错算法简介
- 基于RTP的FEC前向丢错算法
- 基于RTP的FEC前向丢错算法简介
- 【云计算虚拟化】基于docker的caffe环境搭建
- Caffe中的优化方法:SGD、ADAGRAD、NAG,loss的计算
- Caffe源码解读:conv_layer的前向传播与反向传播
- Caffe源码解读:pooling_layer的前向传播与反向传播
- caffe安装前的准备工作
- Windows平台基于Caffe框架的LeNet网络训练
- 使用SSD基于caffe框架训练自己的数据
- CAffe框架的结构
- java中if与switch-case语句的使用及一些注意事项
- Java内存模型
- Java代理模式
- 设计模式——命令模式
- 素数判断 Miller_Rabin算法-hoj1356和51nod1186质数检测V2
- EmbCaffe---基于Caffe的优化前向计算的框架
- 演讲实录|唐刘:Rust in TiKV
- Android-系统启动过程
- zabbix触发器表达式详解
- Ta-lib学习笔记01--成交量指标
- 并行定律
- windows资源文件管理应用图标与管理员权限
- Android笔记-AudioSystem与AudioService
- 一道js面试题的深入~