VS2015+caffe+matlab+python+CPU

最新推荐文章于 2024-04-15 07:19:26 发布

机器学习的小学生

最新推荐文章于 2024-04-15 07:19:26 发布

阅读量7.9k

点赞数 6

分类专栏：工具 Caffe

本文链接：https://blog.csdn.net/raby_gyl/article/details/60955545

版权

Caffe 同时被 2 个专栏收录

47 篇文章 2 订阅

订阅专栏

工具

20 篇文章 0 订阅

订阅专栏

实验平台：

Win7 64bit, VS 2015(Professional), matlab 2016b(64bit), python2.7.12, Eclipse IDE for Java Developers（Version: Neon.1a Release (4.6.1)），Cmake 3.8.0，
protoc-3.1.0-windows-x86_64 ，boost_1_61_0-msvc-14.0-64

资料下载

百度云：

链接：http://pan.baidu.com/s/1gfyvVQb 密码：t9xw

可以下载到下面所用到的文件。

GPU-Z 参看自己电脑GPU是否支持CUDA.

这里写图片描述

caffe-windows 下载地址：

https://github.com/BVLC/caffe/tree/windows

caffe-master 下载地址：

https://github.com/Microsoft/caffe

caffe-windows 和 caffe-master 的区别和联系：

在caffe-windows文件下，我们可以看到有个windows文件夹，其组织形式类似于caffe-master文件，并说其是旧版本，以后将抛弃。因此，caffe-windows 是caffe-master 的新版本。并且caffe-windows 支持VS2015 和VS2013 ，caffe-master 仅支持VS2013。因此，我们下载caffe-windows 即可。

Anaconda是管理和下载Python, R and Scala 语言包的工具。Miniconda是其简化版本，仅支持Python。我们使用Miniconda下载Python包，Miniconda在安装的时候会将其自动添加到环境变量中，因此我们可以通过cmd命令在dos下直接使用conda命令进行下载包。

Miniconda下载地址：
https://mirrors.tuna.tsinghua.edu.cn/anaconda/miniconda/

conda命令在下载python包的时候很慢，因此，我们清华大学的镜像：

https://mirrors.tuna.tsinghua.edu.cn/help/anaconda/

添加三个镜像网址：

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge 
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/msys2/

想要删除清华源把add改成remove就行。

显示URL

conda config --set show_channel_urls yes

参考：https://www.zhihu.com/question/38252144

通过下面的指令可以参看是否添加成功:

> conda config --get channels

镜像中拥有的python包(for windows)：

https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/win-64/

如果里面没有，我们可以去官网：

https://pypi.python.org/pypi

下载需要的包，通过pip.exe进行安装。

python接口依赖：

> conda install --yes numpy scipy matplotlib scikit-image pip six

> conda install --yes --channel willyd protobuf==3.1.0

注意：
在使用上面安装的时候，可能会因为一个安装错误，出现回滚到原状态，那么可以一个库，一个库的安装。

protobuf如何下载很慢，可以通过手动安装：
https://pypi.python.org/pypi/protobuf

补充：

.whl文件的安装，例如下载的为protobuf.whl文件。那么利用pip.exe进行安装，进入cmd命令行，切换到:

D:\python\python2.7.12\Scripts

执行:

pip install protobuf.whl

切记，指令中一定要带有.whl扩展名。

Caffe 安装

0. 前期工作

VS 2015, Matlab, Python, Eclispe ,Cmake都安装好，利用Miniconda将上面python依赖的包都下载好，确定 VS,Matlab,Python,Cmake都在环境变量中。
如下：

Path=D:\python\python2.7.12;
E:\cmake-3.8.0-rc2-win64-x64\bin;
D:\Program Files\MATLAB\R2016b\bin;
D:\Program Files\MATLAB\R2016b\runtime\win64;
D:\Program Files\MATLAB\R2016b\polyspace\bin;
D:\Program Files (x86)\Microsoft Visual Studio 14.0\SDK;
D:\Program Files (x86)\Microsoft Visual Studio 14.0


VCROOT=D:\Program Files (x86)\Microsoft Visual Studio 14.0

VS140COMNTOOLS=D:\Program Files (x86)\Microsoft Visual Studio 14.0\Common7\Tools\

D:\Miniconda2
D:\Miniconda2\Scripts
D:\Miniconda2\Library\bin

安装Miniconda的时候，过程中，我选择将python整合到miniconda中，在miniconda中也会用python解析器,环境变量中含有两个，不晓得在后面是否冲突（可测试）。这样的话只安装miniconda就可以了其自带python，就不用额外的装python了，并且环境变量值D:\python\python2.7.12可去掉。

1.build_win文件的编辑

编辑：E:\caffe-windows\scripts\build_win.cmd

这里写图片描述

因为对cmd文件中的执行流程不太清楚。因此将
if DEFINED APPVEYOR 条件语句中的与上图对应的处也进行了设置。
并也设置了Miniconda的路径。

 :: Set python 2.7 with conda as the default python
    if !PYTHON_VERSION! EQU 2 (
        set CONDA_ROOT=D:\Miniconda2
    )

注释：

一个合理的理解是，就像.cmd文件中在if DEFINED APPVEYOR语句给出在注释为：:: Default values，因此if DEFINED APPVEYOR语句中的并不需要修改，只需要修改截图中红色的标识处以及miniconda的路径。（即需要修改的地方cmd文件中都给出注释。）

在cmd命令行中运行(确定cmake在环境变量中，如E:\cmake-3.8.0-rc2-win64-x64\bin)：

E:\caffe-windows\scripts\build_win.cmd

该命令会在E:\caffe-windows\scripts\目录下创建一个build文件夹，并且会将额外的库libraries_v140_x64_py27_1.0.1.tar下载到该文件夹，由于通过命令行下载很慢，我们可以中断命令的执行，手动下载该库文件到build目录下，然后再重新运行上面的指令。指令执行完之后，在build文件下形成Caffe.sln。

注释：
在运行bulid_win.cmd时候经常会碰到两个问题：
(1) the C compiler identification is unknown… （首先检查一下VS的环境变量），如果环境变量都搭配好了。那么进入bulid/CMakeFiles/CMakeError.txt。进行参考：

LINK : fatal error LNK1104: 无法打开文件“ucrtd.lib”

利用everything搜索，发现该文件在：

C:\Program Files (x86)\Windows Kits\10\Lib\10.0.10150.0\ucrt\x64

目录下，将该目录下的4个库文件，全部拷贝到：

C:\Program Files (x86)\Windows Kits\8.1\Lib\winv6.3\um\x64

即可解决问题。可能还会碰到“corecrt.h”文件无法找到，同样的道理，将：

C:\Program Files (x86)\Windows Kits\10\Include\10.0.10150.0\ucrt

所有头文件拷贝到：

D:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\include

(2). the dependency target “pycaffe’ of target “pytest” does not exist。
是因为python中检测不到numpy库的原因(检测build_win.cmd中miniconda的路径是否配置正确)，第二个方法是直接利用pip 安装numpy库。

每次修改，请记得清理build文件夹中生成的文件，在重新执行build_win.cmd命令

(3)Could NOT find Matlab (missing :Matlab_MEX_EXTENSION) (find version “9.1”。在部分电脑上将Matlab装在D盘，结果会出现这个问题。解决方法是将Matlab装在C盘就好了。

2 .环境变量的添加：

我们通过 RapidEE添加三个环境变量，其在后面的程序执行时调用：

E:\caffe-windows\scripts\build\libraries\bin
E:\caffe-windows\scripts\build\libraries\lib
E:\caffe-windows\scripts\build\libraries\x64\vc14\bin

添加完后，记得一定要重启电脑。如果忘记添加环境变量或者未重启的话，在matlab测试caffe时，会提示:

caffe_.mexw64 无效的mex文件。

3 编译caffe,matlab,pycaffe项目

这里写图片描述
用VS2015打开build文件夹下的Caffe.sln，会在VS的资源管理器目录看到: caffe,matlab,pycaffe 三个项目，其默认是编译release版本，我们依次进行编译，可以通过选中项目，右键属性的方式，看到三个项目的配置，以及编译生成的文件保存的路径：

E:\caffe-windows\scripts\build\lib\Release\caffe.lib
E:\caffe-windows\matlab+caffe\private\Release\caffe_.mexw64
E:\caffe-windows\scripts\build\lib\Release_caffe.pyd

4. matlab 使用caffe

在上面的保存生成路径中，我们可以看到，caffe_.mexw64在E:\caffe-windows\matlab+caffe\private\Release目录下，我们将其拷贝到:上一层目录下，即private目录下。然后打开matlab，将工具路径设置为：
E:\caffe-windows\matlab\demo ，然后新建一个test_caffe.m,即如下的matlab测试代码拷贝，运行即可。(+caffe是matlab类,对接口进行了封装).

注意：编译完后，所有东西感觉都设置好了，有时候还会提示，

Invalid MEX-file ‘*matlab/+caffe/private/.mexw64

使用depends.exe工具（网上自己下载），打开.mexw64 它会告诉你缺少什么，然后或者把什么添加到环境变量或者缺少其他库等等。

5. python 使用caffe

将 E:\caffe-windows\python 下的caffe文件夹，拷贝到：python的site-packages 文件夹下，我们这里是：

D:\python\python2.7.12\Lib\site-packages

其实我们会看到，编译生成的_caffe.pyd 也会在E:\caffe-windows\python\caffe 目录下生成一份。

注意!!!：在进行matlab和python测试前，请确保需要模型文件放置到访问到的目录下，如将bvlc_reference_caffenet.caffemodel 文件放到：

E:\caffe-windows\models\bvlc_reference_caffenet\

以及synset_words.txt(for matlab)放在同test_caffe.m的目录下。

6. VS2015 使用Caffe

Caffe给出了一个测试用例classification.cpp，在E:\caffe-windows\examples\cpp_classification下（具体根据自己当前Caffe位置）
。为了运行例子。需要搭配运行环境。
1. 先进一个VS控制台应用程序，参考caffe 21天，配置工程的包含目录，库目录和环境变量,自己可以选择是Debug模式还是Release模式。
2. 输入命令参数：

eploy.prototxt bvlc_reference_caffenet.caffemodel imagenet_mean.binaryproto synset_words.txt cat.jpg

注：缺少的文件都可以通过上面分享的百度云中找到。

这里写图片描述

补充：

Miniconda 安装的python包是在一个单独目录下,如我的是

C:\Users\***\Miniconda2\Lib\site-packages

在Eclipse中，我们将该目录添加进去即可。

matlab测试code:

% test_caffe.m
close all;clear all;
im = imread('../../examples/images/cat.jpg');%读取图片
figure;imshow(im);%显示图片
[scores, maxlabel] = classification_demo(im, 0);%获取得分第二个参数0为CPU，1为GPU
maxlabel %查看最大标签是谁
figure;plot(scores);%画出得分情况
axis([0, 999, -0.1, 0.5]);%坐标轴范围
grid on %有网格

fid = fopen('synset_words.txt', 'r');
i=0;
while ~feof(fid)
    i=i+1;
    lin = fgetl(fid);
    lin = strtrim(lin);
    if(i==maxlabel)
        fprintf('the label of %d is %s\n',i,lin)
        break
    end
end

结果：
这里写图片描述

python测试code:

# coding=gbk
'''
Created on 2017年3月9日
'''
#安装Python环境、numpy、matplotlib
import numpy as np
import matplotlib.pyplot as plt

#设置默认显示参数
plt.rcParams['figure.figsize'] = (10, 10)        # 图像显示大小
plt.rcParams['image.interpolation'] = 'nearest'  # 最近邻差值: 像素为正方形
plt.rcParams['image.cmap'] = 'gray'  # 使用灰度输出而不是彩色输出

import sys
caffe_root = 'E:/caffe-windows/'  #该文件要从路径{caffe_root}/examples下运行，否则要调整这一行。
sys.path.insert(0, caffe_root + 'python')

import caffe

import os
if os.path.isfile(caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'):
    print 'CaffeNet found.'
else:
    print 'Downloading pre-trained CaffeNet model...'
# !../scripts/download_model_binary.py ../models/bvlc_reference_caffenet

caffe.set_mode_cpu()

model_def = caffe_root + 'models/bvlc_reference_caffenet/deploy.prototxt'
model_weights = caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'

net = caffe.Net(model_def,      # 定义模型结构
                    model_weights,  # 包含了模型的训练权值
                    caffe.TEST)     # 使用测试模式(不执行dropout)
 # 加载ImageNet图像均值 (随着Caffe一起发布的)
mu = np.load(caffe_root + 'python/caffe/imagenet/ilsvrc_2012_mean.npy')
mu = mu.mean(1).mean(1)  #对所有像素值取平均以此获取BGR的均值像素值
print 'mean-subtracted values:', zip('BGR', mu)

# 对输入数据进行变换
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})

transformer.set_transpose('data', (2,0,1))  #将图像的通道数设置为outermost的维数
transformer.set_mean('data', mu)            #对于每个通道，都减去BGR的均值像素值
transformer.set_raw_scale('data', 255)      #将像素值从[0,255]变换到[0,1]之间
transformer.set_channel_swap('data', (2,1,0))  #交换通道，从RGB变换到BGR

# 设置输入图像大小
net.blobs['data'].reshape(50,        # batch 大小
                              3,         # 3-channel (BGR) images
                              227, 227)  # 图像大小为:227x227
image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg')
transformed_image = transformer.preprocess('data', image)
plt.imshow(image)
plt.show()

# 将图像数据拷贝到为net分配的内存中
net.blobs['data'].data[...] = transformed_image

### 执行分类
output = net.forward()  
output_prob = output['prob'][0]  #batch中第一张图像的概率值   
print 'predicted class is:', output_prob.argmax()
# 加载ImageNet标签
labels_file = caffe_root + 'data/ilsvrc12/synset_words.txt'
# if not os.path.exists(labels_file):
#    !../data/ilsvrc12/get_ilsvrc_aux.sh

labels = np.loadtxt(labels_file, str, delimiter='\t')

print 'output label:', labels[output_prob.argmax()]

结果：

CaffeNet found.
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0309 15:43:33.012079  8740 _caffe.cpp:172] DEPRECATION WARNING - deprecated use of Python interface
W0309 15:43:33.012079  8740 _caffe.cpp:173] Use this instead (with the named "weights" parameter):
W0309 15:43:33.012079  8740 _caffe.cpp:175] Net('E:/caffe-windows/models/bvlc_reference_caffenet/deploy.prototxt', 1, weights='E:/caffe-windows/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel')
I0309 15:43:33.026078  8740 net.cpp:53] Initializing net from parameters: 
name: "CaffeNet"
state {
  phase: TEST
  level: 0
}
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 10
      dim: 3
      dim: 227
      dim: 227
    }
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  top: "conv2"
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "norm2"
  top: "conv3"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc8"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8"
  inner_product_param {
    num_output: 1000
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "fc8"
  top: "prob"
}
I0309 15:43:33.026078  8740 layer_factory.cpp:58] Creating layer data
I0309 15:43:33.026078  8740 net.cpp:86] Creating Layer data
I0309 15:43:33.026078  8740 net.cpp:382] data -> data
I0309 15:43:33.026078  8740 net.cpp:124] Setting up data
I0309 15:43:33.026078  8740 net.cpp:131] Top shape: 10 3 227 227 (1545870)
I0309 15:43:33.026078  8740 net.cpp:139] Memory required for data: 6183480
I0309 15:43:33.026078  8740 layer_factory.cpp:58] Creating layer conv1
I0309 15:43:33.026078  8740 net.cpp:86] Creating Layer conv1
I0309 15:43:33.026078  8740 net.cpp:408] conv1 <- data
I0309 15:43:33.026078  8740 net.cpp:382] conv1 -> conv1
I0309 15:43:33.026078  8740 net.cpp:124] Setting up conv1
I0309 15:43:33.026078  8740 net.cpp:131] Top shape: 10 96 55 55 (2904000)
I0309 15:43:33.026078  8740 net.cpp:139] Memory required for data: 17799480
I0309 15:43:33.026078  8740 layer_factory.cpp:58] Creating layer relu1
I0309 15:43:33.026078  8740 net.cpp:86] Creating Layer relu1
I0309 15:43:33.026078  8740 net.cpp:408] relu1 <- conv1
I0309 15:43:33.026078  8740 net.cpp:369] relu1 -> conv1 (in-place)
I0309 15:43:33.026078  8740 net.cpp:124] Setting up relu1
I0309 15:43:33.026078  8740 net.cpp:131] Top shape: 10 96 55 55 (2904000)
I0309 15:43:33.026078  8740 net.cpp:139] Memory required for data: 29415480
I0309 15:43:33.026078  8740 layer_factory.cpp:58] Creating layer pool1
I0309 15:43:33.026078  8740 net.cpp:86] Creating Layer pool1
I0309 15:43:33.026078  8740 net.cpp:408] pool1 <- conv1
I0309 15:43:33.026078  8740 net.cpp:382] pool1 -> pool1
I0309 15:43:33.026078  8740 net.cpp:124] Setting up pool1
I0309 15:43:33.026078  8740 net.cpp:131] Top shape: 10 96 27 27 (699840)
I0309 15:43:33.026078  8740 net.cpp:139] Memory required for data: 32214840
I0309 15:43:33.026078  8740 layer_factory.cpp:58] Creating layer norm1
I0309 15:43:33.026078  8740 net.cpp:86] Creating Layer norm1
I0309 15:43:33.026078  8740 net.cpp:408] norm1 <- pool1
I0309 15:43:33.026078  8740 net.cpp:382] norm1 -> norm1
I0309 15:43:33.026078  8740 net.cpp:124] Setting up norm1
I0309 15:43:33.026078  8740 net.cpp:131] Top shape: 10 96 27 27 (699840)
I0309 15:43:33.026078  8740 net.cpp:139] Memory required for data: 35014200
I0309 15:43:33.026078  8740 layer_factory.cpp:58] Creating layer conv2
I0309 15:43:33.026078  8740 net.cpp:86] Creating Layer conv2
I0309 15:43:33.027079  8740 net.cpp:408] conv2 <- norm1
I0309 15:43:33.027079  8740 net.cpp:382] conv2 -> conv2
I0309 15:43:33.027079  8740 net.cpp:124] Setting up conv2
I0309 15:43:33.027079  8740 net.cpp:131] Top shape: 10 256 27 27 (1866240)
I0309 15:43:33.027079  8740 net.cpp:139] Memory required for data: 42479160
I0309 15:43:33.027079  8740 layer_factory.cpp:58] Creating layer relu2
I0309 15:43:33.027079  8740 net.cpp:86] Creating Layer relu2
I0309 15:43:33.027079  8740 net.cpp:408] relu2 <- conv2
I0309 15:43:33.027079  8740 net.cpp:369] relu2 -> conv2 (in-place)
I0309 15:43:33.027079  8740 net.cpp:124] Setting up relu2
I0309 15:43:33.027079  8740 net.cpp:131] Top shape: 10 256 27 27 (1866240)
I0309 15:43:33.027079  8740 net.cpp:139] Memory required for data: 49944120
I0309 15:43:33.027079  8740 layer_factory.cpp:58] Creating layer pool2
I0309 15:43:33.027079  8740 net.cpp:86] Creating Layer pool2
I0309 15:43:33.027079  8740 net.cpp:408] pool2 <- conv2
I0309 15:43:33.027079  8740 net.cpp:382] pool2 -> pool2
I0309 15:43:33.027079  8740 net.cpp:124] Setting up pool2
I0309 15:43:33.028079  8740 net.cpp:131] Top shape: 10 256 13 13 (432640)
I0309 15:43:33.028079  8740 net.cpp:139] Memory required for data: 51674680
I0309 15:43:33.028079  8740 layer_factory.cpp:58] Creating layer norm2
I0309 15:43:33.028079  8740 net.cpp:86] Creating Layer norm2
I0309 15:43:33.028079  8740 net.cpp:408] norm2 <- pool2
I0309 15:43:33.028079  8740 net.cpp:382] norm2 -> norm2
I0309 15:43:33.028079  8740 net.cpp:124] Setting up norm2
I0309 15:43:33.028079  8740 net.cpp:131] Top shape: 10 256 13 13 (432640)
I0309 15:43:33.028079  8740 net.cpp:139] Memory required for data: 53405240
I0309 15:43:33.028079  8740 layer_factory.cpp:58] Creating layer conv3
I0309 15:43:33.028079  8740 net.cpp:86] Creating Layer conv3
I0309 15:43:33.028079  8740 net.cpp:408] conv3 <- norm2
I0309 15:43:33.028079  8740 net.cpp:382] conv3 -> conv3
I0309 15:43:33.030079  8740 net.cpp:124] Setting up conv3
I0309 15:43:33.030079  8740 net.cpp:131] Top shape: 10 384 13 13 (648960)
I0309 15:43:33.030079  8740 net.cpp:139] Memory required for data: 56001080
I0309 15:43:33.030079  8740 layer_factory.cpp:58] Creating layer relu3
I0309 15:43:33.030079  8740 net.cpp:86] Creating Layer relu3
I0309 15:43:33.030079  8740 net.cpp:408] relu3 <- conv3
I0309 15:43:33.030079  8740 net.cpp:369] relu3 -> conv3 (in-place)
I0309 15:43:33.030079  8740 net.cpp:124] Setting up relu3
I0309 15:43:33.030079  8740 net.cpp:131] Top shape: 10 384 13 13 (648960)
I0309 15:43:33.030079  8740 net.cpp:139] Memory required for data: 58596920
I0309 15:43:33.030079  8740 layer_factory.cpp:58] Creating layer conv4
I0309 15:43:33.030079  8740 net.cpp:86] Creating Layer conv4
I0309 15:43:33.030079  8740 net.cpp:408] conv4 <- conv3
I0309 15:43:33.030079  8740 net.cpp:382] conv4 -> conv4
I0309 15:43:33.031080  8740 net.cpp:124] Setting up conv4
I0309 15:43:33.031080  8740 net.cpp:131] Top shape: 10 384 13 13 (648960)
I0309 15:43:33.031080  8740 net.cpp:139] Memory required for data: 61192760
I0309 15:43:33.031080  8740 layer_factory.cpp:58] Creating layer relu4
I0309 15:43:33.031080  8740 net.cpp:86] Creating Layer relu4
I0309 15:43:33.031080  8740 net.cpp:408] relu4 <- conv4
I0309 15:43:33.031080  8740 net.cpp:369] relu4 -> conv4 (in-place)
I0309 15:43:33.031080  8740 net.cpp:124] Setting up relu4
I0309 15:43:33.031080  8740 net.cpp:131] Top shape: 10 384 13 13 (648960)
I0309 15:43:33.031080  8740 net.cpp:139] Memory required for data: 63788600
I0309 15:43:33.031080  8740 layer_factory.cpp:58] Creating layer conv5
I0309 15:43:33.031080  8740 net.cpp:86] Creating Layer conv5
I0309 15:43:33.031080  8740 net.cpp:408] conv5 <- conv4
I0309 15:43:33.031080  8740 net.cpp:382] conv5 -> conv5
I0309 15:43:33.032079  8740 net.cpp:124] Setting up conv5
I0309 15:43:33.032079  8740 net.cpp:131] Top shape: 10 256 13 13 (432640)
I0309 15:43:33.032079  8740 net.cpp:139] Memory required for data: 65519160
I0309 15:43:33.032079  8740 layer_factory.cpp:58] Creating layer relu5
I0309 15:43:33.032079  8740 net.cpp:86] Creating Layer relu5
I0309 15:43:33.032079  8740 net.cpp:408] relu5 <- conv5
I0309 15:43:33.032079  8740 net.cpp:369] relu5 -> conv5 (in-place)
I0309 15:43:33.032079  8740 net.cpp:124] Setting up relu5
I0309 15:43:33.032079  8740 net.cpp:131] Top shape: 10 256 13 13 (432640)
I0309 15:43:33.032079  8740 net.cpp:139] Memory required for data: 67249720
I0309 15:43:33.032079  8740 layer_factory.cpp:58] Creating layer pool5
I0309 15:43:33.032079  8740 net.cpp:86] Creating Layer pool5
I0309 15:43:33.032079  8740 net.cpp:408] pool5 <- conv5
I0309 15:43:33.032079  8740 net.cpp:382] pool5 -> pool5
I0309 15:43:33.032079  8740 net.cpp:124] Setting up pool5
I0309 15:43:33.032079  8740 net.cpp:131] Top shape: 10 256 6 6 (92160)
I0309 15:43:33.032079  8740 net.cpp:139] Memory required for data: 67618360
I0309 15:43:33.032079  8740 layer_factory.cpp:58] Creating layer fc6
I0309 15:43:33.032079  8740 net.cpp:86] Creating Layer fc6
I0309 15:43:33.032079  8740 net.cpp:408] fc6 <- pool5
I0309 15:43:33.032079  8740 net.cpp:382] fc6 -> fc6
I0309 15:43:33.130084  8740 net.cpp:124] Setting up fc6
I0309 15:43:33.130084  8740 net.cpp:131] Top shape: 10 4096 (40960)
I0309 15:43:33.130084  8740 net.cpp:139] Memory required for data: 67782200
I0309 15:43:33.130084  8740 layer_factory.cpp:58] Creating layer relu6
I0309 15:43:33.130084  8740 net.cpp:86] Creating Layer relu6
I0309 15:43:33.130084  8740 net.cpp:408] relu6 <- fc6
I0309 15:43:33.130084  8740 net.cpp:369] relu6 -> fc6 (in-place)
I0309 15:43:33.130084  8740 net.cpp:124] Setting up relu6
I0309 15:43:33.130084  8740 net.cpp:131] Top shape: 10 4096 (40960)
I0309 15:43:33.130084  8740 net.cpp:139] Memory required for data: 67946040
I0309 15:43:33.130084  8740 layer_factory.cpp:58] Creating layer drop6
I0309 15:43:33.130084  8740 net.cpp:86] Creating Layer drop6
I0309 15:43:33.130084  8740 net.cpp:408] drop6 <- fc6
I0309 15:43:33.130084  8740 net.cpp:369] drop6 -> fc6 (in-place)
I0309 15:43:33.130084  8740 net.cpp:124] Setting up drop6
I0309 15:43:33.130084  8740 net.cpp:131] Top shape: 10 4096 (40960)
I0309 15:43:33.130084  8740 net.cpp:139] Memory required for data: 68109880
I0309 15:43:33.130084  8740 layer_factory.cpp:58] Creating layer fc7
I0309 15:43:33.130084  8740 net.cpp:86] Creating Layer fc7
I0309 15:43:33.130084  8740 net.cpp:408] fc7 <- fc6
I0309 15:43:33.130084  8740 net.cpp:382] fc7 -> fc7
I0309 15:43:33.166087  8740 net.cpp:124] Setting up fc7
I0309 15:43:33.166087  8740 net.cpp:131] Top shape: 10 4096 (40960)
I0309 15:43:33.166087  8740 net.cpp:139] Memory required for data: 68273720
I0309 15:43:33.166087  8740 layer_factory.cpp:58] Creating layer relu7
I0309 15:43:33.166087  8740 net.cpp:86] Creating Layer relu7
I0309 15:43:33.166087  8740 net.cpp:408] relu7 <- fc7
I0309 15:43:33.166087  8740 net.cpp:369] relu7 -> fc7 (in-place)
I0309 15:43:33.166087  8740 net.cpp:124] Setting up relu7
I0309 15:43:33.166087  8740 net.cpp:131] Top shape: 10 4096 (40960)
I0309 15:43:33.166087  8740 net.cpp:139] Memory required for data: 68437560
I0309 15:43:33.166087  8740 layer_factory.cpp:58] Creating layer drop7
I0309 15:43:33.166087  8740 net.cpp:86] Creating Layer drop7
I0309 15:43:33.166087  8740 net.cpp:408] drop7 <- fc7
I0309 15:43:33.166087  8740 net.cpp:369] drop7 -> fc7 (in-place)
I0309 15:43:33.166087  8740 net.cpp:124] Setting up drop7
I0309 15:43:33.166087  8740 net.cpp:131] Top shape: 10 4096 (40960)
I0309 15:43:33.166087  8740 net.cpp:139] Memory required for data: 68601400
I0309 15:43:33.166087  8740 layer_factory.cpp:58] Creating layer fc8
I0309 15:43:33.166087  8740 net.cpp:86] Creating Layer fc8
I0309 15:43:33.166087  8740 net.cpp:408] fc8 <- fc7
I0309 15:43:33.166087  8740 net.cpp:382] fc8 -> fc8
I0309 15:43:33.175087  8740 net.cpp:124] Setting up fc8
I0309 15:43:33.175087  8740 net.cpp:131] Top shape: 10 1000 (10000)
I0309 15:43:33.176087  8740 net.cpp:139] Memory required for data: 68641400
I0309 15:43:33.176087  8740 layer_factory.cpp:58] Creating layer prob
I0309 15:43:33.176087  8740 net.cpp:86] Creating Layer prob
I0309 15:43:33.176087  8740 net.cpp:408] prob <- fc8
I0309 15:43:33.176087  8740 net.cpp:382] prob -> prob
I0309 15:43:33.176087  8740 net.cpp:124] Setting up prob
I0309 15:43:33.176087  8740 net.cpp:131] Top shape: 10 1000 (10000)
I0309 15:43:33.176087  8740 net.cpp:139] Memory required for data: 68681400
I0309 15:43:33.176087  8740 net.cpp:202] prob does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] fc8 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] drop7 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] relu7 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] fc7 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] drop6 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] relu6 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] fc6 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] pool5 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] relu5 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] conv5 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] relu4 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] conv4 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] relu3 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] conv3 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] norm2 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] pool2 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] relu2 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] conv2 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] norm1 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] pool1 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] relu1 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] conv1 does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:202] data does not need backward computation.
I0309 15:43:33.176087  8740 net.cpp:244] This network produces output prob
I0309 15:43:33.176087  8740 net.cpp:257] Network initialimean-subtracted values: [('B', 104.0069879317889), ('G', 116.66876761696767), ('R', 122.6789143406786)]
predicted class is: 281
output label: n02123045 tabby, tabby cat
zation done.
I0309 15:43:43.999706  8740 upgrade_proto.cpp:44] Attempting to upgrade input file specified using deprecated transformation parameters: E:/caffe-windows/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel
I0309 15:43:43.999706  8740 upgrade_proto.cpp:47] Successfully upgraded file specified using deprecated data transformation parameters.
W0309 15:43:43.999706  8740 upgrade_proto.cpp:49] Note that future Caffe releases will only support transform_param messages for transformation fields.
I0309 15:43:43.999706  8740 upgrade_proto.cpp:53] Attempting to upgrade input file specified using deprecated V1LayerParameter: E:/caffe-windows/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel
I0309 15:43:44.619742  8740 upgrade_proto.cpp:61] Successfully upgraded file specified using deprecated V1LayerParameter
I0309 15:43:44.827754  8740 net.cpp:746] Ignoring source layer loss

exe应用程序的生成

caffe.exe compute_image_mean.exe convert_imageset.exe

这里写图片描述
1. 参考文献：
http://blog.csdn.net/jnulzl/article/details/52077915 [Caffe for Python 官方教程(翻译)]

机器学习的小学生

关注

6
点赞
踩
12

收藏

觉得还不错? 一键收藏
5
评论
VS2015+caffe+matlab+python+CPU

实验平台：Win7 64bit, VS 2015(Professional), matlab 2016b(64bit), python2.7.12, Eclipse IDE for Java Developers（Version: Neon.1a Release (4.6.1)），Cmake 3.8.0， protoc-3.1.0-windows-x86_64 ，boost_1_61_0-m...
复制链接

扫一扫