"Caffe-windows" Caffe-master matlab interface configuration

Platform Environment: WIN10 64-bit caffe-master vs2013 matlab2016a

The first step:

Open a Commonsettings.props file under \caffe-master\windows,

Change the Matlabsupport to True (that is, the MATLAB interface is supported).

Step Two:

Change the path of MATLAB,

Step Three:

Add a path to the Includepath, and if not, the following error will appear at compile time: gpu/mxgpuarray.h "not Found

Copy this code:

<includepath>$ (Matlabdir) \extern\include;$ (matlabdir) \toolbox\distcomp\gpu\extern\include;$ (IncludePath) </IncludePath>

Fourth Step:

Open Caffe-master\windows under the Caffe.sln, find Matcaffe, select released (Do not use Debug), and then right-click Matcaffe, tap Generate.

PS: I don't know what the cause is wrong

Error 1 Error:nuget error:unable to find version ' 2.4.10 ' of the package ' opencv.overlay-x64_v120_release '. D:\NugetPackages\OpenCV.2.4.10\build\native\OpenCV.targets 772 5 Libcaffe

Select Regenerate to resolve. Of course, the students who did not make mistakes are ignored.

After the build is complete, there will be files under Caffe-master\build\x64\release\matcaffe\+caffe\private: Caffe_.mexw64

Fifth Step:

Open matlab, add path

Sixth step:

Add the system environment variable and put the. \caffe-master\build\x64\release is added to the system environment variable,

The following error occurs when running DEMO.M:

Invalid mex-file ' d:\caffe-master\build\x64\release\matcaffe\+caffe\private\caffe_.mexw64 ': The specified module could not be found.

Error CAFFE.SET_MODE_CPU (line 5)

Caffe_ (' set_mode_cpu ');

Error Classification_demo (line 71)

Caffe.set_mode_cpu ();

Seventh Step:

Copy all DLL files in Caffe-master\build\x64\debug to Caffe-master\matlab\+caffe\private

Eighth Step:

Download the model file (Bvlc_reference_caffenet.caffemodel) into the Caffe-master\models\bvlc_reference_caffenet folder

Link: http://pan.baidu.com/s/1geUv01l Password: yp9p (source: http://blog.csdn.net/zb1165048017/article/details/51702686)

Nineth Step:

Download tag file: Synset_words.txt, placed in the same folder as CLASSIFICATION_DEMO.M

Link: Http://pan.baidu.com/s/1c24ty6W Password: 3z7y (source: http://blog.csdn.net/zb1165048017/article/details/51702686)

Tenth step:

Open CLASSIFICATION_DEMO.M, run. If it appears

No function or variable ' caffe_ ' is defined.

Error CAFFE.SET_MODE_CPU (line 5)

Caffe_ (' set_mode_cpu ');

Error Classification_demo (line 71)

Caffe.set_mode_cpu ();

Please modify the second statement

Addpath ('.. /.. /build/x64/release/matcaffe ');

11th Step:

Running a test file test_mat.m, File source (source: http://blog.csdn.net/zb1165048017/article/details/51702686)

Download Link: Http://pan.baidu.com/s/1nvtwoBJ Password: t71u

stored in the same folder as CLASSIFICATION_DEMO.M

TEST_MAT.M source code is as follows:

2. % Reference http://www.aichengxu.com/view/2422137
4. Clear
6. Clc
10. im = Imread ('.. /.. /examples/images/cat.jpg ');% read picture
12. Figure;imshow (IM);% Display Picture
14. [Scores, Maxlabel] = Classification_demo (IM, 0);% get score the second parameter 0 is cpu,1 for the GPU
16. Maxlabel% View Max tags yes who
18. Figure;plot (scores);% draw a scoring situation
20. Axis ([0, 999,-0.1, 0.5]),% axis range
22. Grid on% with mesh
26. FID = fopen (' synset_words.txt ', ' R ');
28. i=0;
30. While ~feof (FID)
32. i=i+1;
34. Lin = Fgetl (FID);
36. Lin = Strtrim (Lin);
38. if (I==maxlabel)
40. fprintf (' The label of%d is%s\n ', I,lin)
42. Break
44. End

. end

Run results

"Caffe-windows" Caffe-master matlab interface configuration