学习参考资料
  1. caffe_intro-高翔
  2. Caffe Tutorial
  3. Caffe Model Zoo
  4. Awesome-Caffe
  5. 《深度学习：21天实战Caffe》

安装Caffe

安装依赖项
  • ProtoBuffer：实现内存与非易失存储介质交换的协议接口
  • Boost：“C++准标准库”
  • GFLAGS：命令行参数解析
  • GLOG：记录应用程序日志
  • BLAS：Basic Linear Algebra Subprograms
  • HDF5：一种高效存储和分发科学数据的新型数据格式
  • OpenCV
  • LMDB & LEVELDB：内存映射型数据库管理器，统一为 Key-Value 存储
  • Snappy：用于压缩和解压缩

《深度学习：21天实战Caffe》的作者曾将 Caffe 层层外表剥离，只保留最小的必需的代码，运行一个完整的 AlexNet 模型只需不到 500 行 C++ 代码。这部分代码可以轻松移植到除 x86 外的其他平台 (GPU、ARM、DSP、Power8、FPGA等)。

下载Caffe源码，编译安装
git clone https://github.com/BVLC/caffe.git
cd caffe
mkdir build
cd build
cmake ..
make all
make install
make runtest

我在 macOS 10.14 平台上编译时出错，提示与 C++11 有关，安装如下方式修改 CMakeList.txt 后通过编译：

# ---[ Flags
if(UNIX OR APPLE)
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fPIC -Wall")
endif()if()

改为

# ---[ Flags
if(UNIX OR APPLE)
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fPIC -Wall -std=c++11")
endif()if()
Caffe使用方法
caffe: command line brew
usage: caffe <command> <args>

commands:
  train           train or finetune a model
  test            score a model
  device_query    show GPU diagnostic information
  time            benchmark model execution time

  Flags from /Users/zhangjixiang/Documents/GitHub/caffe/tools/caffe.cpp:
    -gpu (Optional; run in GPU mode on given device IDs separated by ','.Use
      '-gpu all' to run on all available GPUs. The effective training batch
      size is multiplied by the number of devices.) type: string default: ""
    -iterations (The number of iterations to run.) type: int32 default: 50
    -level (Optional; network level.) type: int32 default: 0
    -model (The model definition protocol buffer text file.) type: string
      default: ""
    -phase (Optional; network phase (TRAIN or TEST). Only used for 'time'.)
      type: string default: ""
    -sighup_effect (Optional; action to take when a SIGHUP signal is received:
      snapshot, stop or none.) type: string default: "snapshot"
    -sigint_effect (Optional; action to take when a SIGINT signal is received:
      snapshot, stop or none.) type: string default: "stop"
    -snapshot (Optional; the snapshot solver state to resume training.)
      type: string default: ""
    -solver (The solver definition protocol buffer text file.) type: string
      default: ""
    -stage (Optional; network stages (not to be confused with phase), separated
      by ','.) type: string default: ""
    -weights (Optional; the pretrained weights to initialize finetuning,
      separated by ','. Cannot be set simultaneously with snapshot.)
      type: string default: ""

安装和训练 Faster-RCNN 的 bug 很多，不过大部分可以通过 Google 解决。

Faster-RCNN+ZF用自己的数据集训练模型(Python版本)

Fast rcnn cpu 训练自己的数据

针对只使用 CPU 训练 Faster-RCNN 的情况，需要把默认的 GPU 设置为 CPU。还需要添加 4 个 C++ 源文件用 CPU 实现 GPU 的功能。需要修改的文件包括：