Caffe for Windows配置和测试【流程】

Caffe Installation官方介绍：http://caffe.berkeleyvision.org/installation.html
Caffe for Windows 介绍：https://github.com/niuzhiheng/caffe

1、下载Caffe for Windows开源包：https://github.com/niuzhiheng/caffe

2、按照网页介绍步骤配置

配置中的关键步骤截图

下载dependencies

解压，复制粘贴到开源包根目录，覆盖：

• Download the dependency file and extract the folders inside to project root directory.

切换到x64：

• Include any .cpp you want to build in the ./tools directory to MainCaller.cpp.
• Open the solution file in ./build/MSVC

• Switch build target to x64 platform (Both debug and release are OK).

• Build the code and you may find the ./bin/MainCaller.exe

Train MNIST dataset

Suppose you choose to build train_net.cpp which is the default one in MainCaller.cpp

If you do not have GPU, please change it to CPU in lenet_solver.prototxt

Goto directory ./examples/mnist

Double click get_mnist_leveldb.bat to download the dataset in leveldb format.(这一步如果不能成功下载就自己手动复制链接下载)

下载后文件

Double click train_lenet.bat to see the training progress .下面进行测试：按照以下步骤进行（前提是按照Windows Installation中的Build Steps正常编译生成了MainCaller.exe,这个过程有可能会很久）

可能需要修改的部分在/examples/mnist/lenet_solver.prototxt中，根据自己情况修改。

训练过程：