rbgirshick / rcnn Goto Github PK

Hello everyone,

I used the up-to-date CAFFE and got the R-CNN source code by cloning the repository: git clone https://github.com/rbgirshick/rcnn.git. I successfully finished the RCNN startup, rcnn_build() and got the key -2 after running key = caffe(‘get_init_key’). But when I run the rcnn_demo, I got the ERROR in MATLAB:

Welcome to the PASCAL demo
Running in GPU mode
(To run in CPU mode, call rcnn_demo(demo_choice, 0) instead)
Press any key to continue
Initializing R-CNN model (this might take a little while)
Error using caffe
Expected 3 arguments, got 2

Error in rcnn_load_model (line 27)
rcnn_model.cnn.init_key = ...

Error in rcnn_demo (line 59)
rcnn_model = rcnn_load_model(rcnn_model_file, use_gpu);

Need your help. THANKS！

Best,
siqin

Hello,

I have a task of setting up r-cnn along with matlab.
Hence I will buy Matlab licence I was wondering which matlab packages are needed for r-cnn to recognize a bicycle.

Thanks

Hi,

Not sure if this is the right place for asking a question, if not, please direct me to the right place.

I am trying to build rcnn and by following the instructions, I did rcnn_build() and it throws warnings & errors below:

>> rcnn_build()
Compiling the anisotropic gauss filtering of:
   J. Geusebroek, A. Smeulders, and J. van de Weijer
   Fast anisotropic gauss filtering
   IEEE Transactions on Image Processing, 2003
Source code/Project page:
   http://staff.science.uva.nl/~mark/downloads.html#anigauss


Warning: You are using gcc version "4.8.2".  The version
         currently supported with MEX is "4.7.x".
         For a list of currently supported compilers see: 
         http://www.mathworks.com/support/compilers/current_release/


    mex:  selective_search/SelectiveSearchCodeIJCV/Dependencies/anigaussm/anigauss_mex.c  not a normal file or does not exist.

Unable to complete successfully.

Error in rcnn_build (line 13)
    mex -outdir bin ...

>> 

What goes wrong here? it is the gcc version?
how could I solve it? my caffe configuration is definitely right, so it should`t be related to that.
any enlightenment would be highly appreciated.

Thank you!

I am trying to study the detection result of R-CNN based on VOC2007, I got a detection accuracy of 64.2% for class "aero" based on output of fc7, that is exactly the same value as the paper shows. However, when I use the output of pool5, I only got 24.6% , expected value is 58.2% according to the paper. I have examined the codes carefully, still confused, could anybody tell me why?

I was trying to extract features from PASCAL VOC 2007 datasets according to the tutorial, everything is normal until matlab throwed a System Error: 'MATLAB has encountered an internal problem and needs to close'. I use ubuntu 14.04 and the matlab edition is 2013a. The R-CNN is runned in CPU mode.

The error was thrown while excuting line 36: 'rcnn_model.cnn.layers = caffe('get_weights')' in rcnn_load_model.m:

Some details of the error:

MATLAB crash file:/root/matlab_crash_dump.4529-1:

        Abort signal detected at Wed Aug 27 18:56:28 2014

Configuration:
Crash Decoding : Disabled
Current Visual : 0x23 (class 4, depth 24)
Default Encoding : UTF-8
GNU C Library : 2.19 stable
MATLAB Architecture: glnxa64
MATLAB Root : /usr/local/MATLAB/R2013a
MATLAB Version : 8.1.0.604 (R2013a)
Operating System : Linux 3.13.0-34-generic #60-Ubuntu SMP Wed Aug 13 15:45:27 UTC 2014 x86_64
Processor ID : x86 Family 6 Model 58 Stepping 9, GenuineIntel
Virtual Machine : Java 1.6.0_17-b04 with Sun Microsystems Inc. Java HotSpot(TM) 64-Bit Server VM mixed mode
Window System : The X.Org Foundation (11501000), display :0

Fault Count: 1

Abnormal termination:
Abort signal

Register State (from fault):
RAX = 0000000000000000 RBX = 00007ff6f1389660
RCX = ffffffffffffffff RDX = 0000000000000006
RSP = 00007ff7e7a7f788 RBP = 00007ff6f1389660
RSI = 00000000000011e4 RDI = 00000000000011b1

R8 = 0000000000000000 R9 = 0000000000000000
R10 = 0000000000000008 R11 = 0000000000000206
R12 = 00007ff6f13896c0 R13 = 00007ff6f1389980
R14 = 00007ff7e7a7faa0 R15 = 000000000000003c

RIP = 00007ff7f95d9f89 EFL = 0000000000000206

CS = 0033 FS = 0000 GS = 0000

Stack Trace (from fault):
[ 0] 0x00007ff7f95d9f89 /lib/x86_64-linux-gnu/libc.so.6+00225161 gsignal+00000057
[ 1] 0x00007ff7f95dd398 /lib/x86_64-linux-gnu/libc.so.6+00238488 abort+00000328
[ 2] 0x00007ff6f11753b9 /usr/local/lib/libglog.so.0+00041913
[ 3] 0x00007ff6f11769fd /usr/local/lib/libglog.so.0+00047613
[ 4] 0x00007ff6f117889d /usr/local/lib/libglog.so.0+00055453 _ZN6google10LogMessage9SendToLogEv+00000589
[ 5] 0x00007ff6f11765ec /usr/local/lib/libglog.so.0+00046572 _ZN6google10LogMessage5FlushEv+00000156
[ 6] 0x00007ff6f11791be /usr/local/lib/libglog.so.0+00057790 _ZN6google15LogMessageFatalD2Ev+00000014
[ 7] 0x00007ff6f14267f0 /rcnn/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00575472
[ 8] 0x00007ff6f140bdf2 /rcnn/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00466418
[ 9] 0x00007ff6f13b6af9 /rcnn/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00117497
[ 10] 0x00007ff6f13b61c3 /rcnn/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00115139 mexFunction+00000203
[ 11] 0x00007ff7f1c3cf8a /usr/local/MATLAB/R2013a/bin/glnxa64/libmex.so+00110474 mexRunMexFile+00000090
[ 12] 0x00007ff7f1c390f9 /usr/local/MATLAB/R2013a/bin/glnxa64/libmex.so+00094457
[ 13] 0x00007ff7f1c39f1c /usr/local/MATLAB/R2013a/bin/glnxa64/libmex.so+00098076
[ 14] 0x00007ff7fb56b6b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 15] 0x00007ff7faff5bf6 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04262902
[ 16] 0x00007ff7faff637a /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04264826
[ 17] 0x00007ff7faff6eea /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04267754
[ 18] 0x00007ff7fae59bbd /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02575293
[ 19] 0x00007ff7fae85412 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02753554
[ 20] 0x00007ff7fae8553f /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02753855
[ 21] 0x00007ff7fafa2500 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+03921152
[ 22] 0x00007ff7fadbe8ac /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01939628
[ 23] 0x00007ff7fadba993 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01923475
[ 24] 0x00007ff7fadbb797 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01927063
[ 25] 0x00007ff7fae26e50 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02367056
[ 26] 0x00007ff7fb56b6b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 27] 0x00007ff7fae09256 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02245206
[ 28] 0x00007ff7fadb9a86 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01919622
[ 29] 0x00007ff7fadbe374 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01938292
[ 30] 0x00007ff7fadba993 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01923475
[ 31] 0x00007ff7fadbb797 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01927063
[ 32] 0x00007ff7fae26e50 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02367056
[ 33] 0x00007ff7fb56b6b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 34] 0x00007ff7fae09256 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02245206
[ 35] 0x00007ff7fadb9a86 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01919622
[ 36] 0x00007ff7fadbe374 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01938292
[ 37] 0x00007ff7fadba993 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01923475
[ 38] 0x00007ff7fadbb797 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01927063
[ 39] 0x00007ff7fae26e50 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02367056
[ 40] 0x00007ff7fb56b6b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 41] 0x00007ff7fae09256 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02245206
[ 42] 0x00007ff7fad9509d /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01769629
[ 43] 0x00007ff7fadbdb0e /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01936142
[ 44] 0x00007ff7fadba993 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01923475
[ 45] 0x00007ff7fadbb797 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01927063
[ 46] 0x00007ff7fae26e50 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02367056
[ 47] 0x00007ff7fb56b6b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 48] 0x00007ff7fadf5dcb /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02166219
[ 49] 0x00007ff7fadb37cc /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01894348
[ 50] 0x00007ff7fadafe1d /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01879581
[ 51] 0x00007ff7fadb0255 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01880661
[ 52] 0x00007ff7f1e65fae /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00139182
[ 53] 0x00007ff7f1e66111 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00139537
[ 54] 0x00007ff7f1e66ce5 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00142565 _Z8mnParserv+00000725
[ 55] 0x00007ff7fb8033d2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00447442 _ZN11mcrInstance30mnParser_on_interpreter_threadEv+00000034
[ 56] 0x00007ff7fb7e29ac /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00313772
[ 57] 0x00007ff7fb7e2b88 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00314248
[ 58] 0x00007ff7ef37a5c6 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwuix.so+00480710
[ 59] 0x00007ff7ef387df2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwuix.so+00536050
[ 60] 0x00007ff7fbecd862 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwservices.so+01845346
[ 61] 0x00007ff7fbece50f /usr/local/MATLAB/R2013a/bin/glnxa64/libmwservices.so+01848591 _Z25svWS_ProcessPendingEventsiib+00001615
[ 62] 0x00007ff7fb7e35ef /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00316911
[ 63] 0x00007ff7fb7e3f5c /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00319324
[ 64] 0x00007ff7fb7dd592 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00292242
[ 65] 0x00007ff7f9971182 /lib/x86_64-linux-gnu/libpthread.so.0+00033154
[ 66] 0x00007ff7f969e38d /lib/x86_64-linux-gnu/libc.so.6+01029005 clone+00000109

This error was detected while a MEX-file was running. If the MEX-file
is not an official MathWorks function, please examine its source code
for errors. Please consult the External Interfaces Guide for information
on debugging MEX-files.

If this problem is reproducible, please submit a Service Request via:
http://www.mathworks.com/support/contact_us/

A technical support engineer might contact you with further information.

Thank you for your help.

Anyone can tell me how I should solve the problem?

I encountered the follow error when I tried to use my trained network and do feedforward propagation on my dataset. Anyone can help?

        Abort signal detected at Mon Dec  8 20:09:07 2014

Configuration:
Crash Decoding : Disabled
Current Visual : 0x21 (class 4, depth 24)
Default Encoding : UTF-8
GNU C Library : 2.19 stable
MATLAB Architecture: glnxa64
MATLAB Root : /usr/local/MATLAB/R2013a
MATLAB Version : 8.1.0.604 (R2013a)
Operating System : Linux 3.13.0-40-generic #69-Ubuntu SMP Thu Nov 13 17:53:56 UTC 2014 x86_64
Processor ID : x86 Family 6 Model 26 Stepping 5, GenuineIntel
Virtual Machine : Java 1.6.0_17-b04 with Sun Microsystems Inc. Java HotSpot(TM) 64-Bit Server VM mixed mode
Window System : The X.Org Foundation (11501000), display :0

Fault Count: 1

Abnormal termination:
Abort signal

Register State (from fault):
RAX = 0000000000000000 RBX = 00007fbd0e9e8620
RCX = ffffffffffffffff RDX = 0000000000000006
RSP = 00007fbdb3ff3ce8 RBP = 00007fbdb3ff3e20
RSI = 0000000000000f80 RDI = 0000000000000f44

R8 = 000000000000ff08 R9 = ffffffffffff1150
R10 = 0000000000000008 R11 = 0000000000000206
R12 = 0000000000000000 R13 = 00007fbdb3ff49d8
R14 = 00007fbd0ed309c0 R15 = 00007fbdb8e4f120

RIP = 00007fbdca0a6bb9 EFL = 0000000000000206

CS = 0033 FS = 0000 GS = 0000

Stack Trace (from fault):
[ 0] 0x00007fbdca0a6bb9 /lib/x86_64-linux-gnu/libc.so.6+00224185 gsignal+00000057
[ 1] 0x00007fbdca0a9fc8 /lib/x86_64-linux-gnu/libc.so.6+00237512 abort+00000328
[ 2] 0x00007fbd0e7c2d81 /usr/lib/x86_64-linux-gnu/libglog.so.0+00068993 _ZN6google22InstallFailureFunctionEPFvvE+00000000
[ 3] 0x00007fbd0e7c2daa /usr/lib/x86_64-linux-gnu/libglog.so.0+00069034 _ZN6google10LogMessage10SendToSinkEv+00000000
[ 4] 0x00007fbd0e7c2ce4 /usr/lib/x86_64-linux-gnu/libglog.so.0+00068836 _ZN6google10LogMessage9SendToLogEv+00001224
[ 5] 0x00007fbd0e7c26e6 /usr/lib/x86_64-linux-gnu/libglog.so.0+00067302 _ZN6google10LogMessage5FlushEv+00000414
[ 6] 0x00007fbd0e7c5687 /usr/lib/x86_64-linux-gnu/libglog.so.0+00079495 _ZN6google15LogMessageFatalD1Ev+00000025
[ 7] 0x00007fbd0ea0aa48 /home/johnny5550822/Dropbox/ML/DeepLearning/mii-stroke-deeplearn/tumor_cnn_102114/caffe_matlab/caffe.mexa64+00133704
[ 8] 0x00007fbd0ea0a7f4 /home/johnny5550822/Dropbox/ML/DeepLearning/mii-stroke-deeplearn/tumor_cnn_102114/caffe_matlab/caffe.mexa64+00133108 mexFunction+00000246
[ 9] 0x00007fbdc2709f8a /usr/local/MATLAB/R2013a/bin/glnxa64/libmex.so+00110474 mexRunMexFile+00000090
[ 10] 0x00007fbdc27060f9 /usr/local/MATLAB/R2013a/bin/glnxa64/libmex.so+00094457
[ 11] 0x00007fbdc2706f1c /usr/local/MATLAB/R2013a/bin/glnxa64/libmex.so+00098076
[ 12] 0x00007fbdcc0436b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 13] 0x00007fbdcbacdbf6 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04262902
[ 14] 0x00007fbdcbace37a /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04264826
[ 15] 0x00007fbdcbaceeea /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04267754
[ 16] 0x00007fbdcb931bbd /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02575293
[ 17] 0x00007fbdcb95d412 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02753554
[ 18] 0x00007fbdcb95d53f /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02753855
[ 19] 0x00007fbdcba7a500 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+03921152
[ 20] 0x00007fbdcb8968ac /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01939628
[ 21] 0x00007fbdcb892993 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01923475
[ 22] 0x00007fbdcb893797 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01927063
[ 23] 0x00007fbdcb8fee50 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02367056
[ 24] 0x00007fbdcc0436b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 25] 0x00007fbdcbacdbf6 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04262902
[ 26] 0x00007fbdcbace37a /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04264826
[ 27] 0x00007fbdcbaceeea /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+04267754
[ 28] 0x00007fbdcb931bbd /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02575293
[ 29] 0x00007fbdcb95d412 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02753554
[ 30] 0x00007fbdcb95d53f /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02753855
[ 31] 0x00007fbdcba7a500 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+03921152
[ 32] 0x00007fbdcb8968ac /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01939628
[ 33] 0x00007fbdcb892993 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01923475
[ 34] 0x00007fbdcb893797 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01927063
[ 35] 0x00007fbdcb8fee50 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02367056
[ 36] 0x00007fbdcc0436b2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_dispatcher.so+00562866 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000594
[ 37] 0x00007fbdcb8cddcb /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+02166219
[ 38] 0x00007fbdcb88b7cc /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01894348
[ 39] 0x00007fbdcb887e1d /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01879581
[ 40] 0x00007fbdcb888255 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01880661
[ 41] 0x00007fbdcb88a5d0 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwm_interpreter.so+01889744
[ 42] 0x00007fbdc3544f13 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwiqm.so+03284755 _ZNK3iqm18InternalEvalPlugin24inEvalCmdWithLocalReturnERKSbItSt11char_traitsItESaItEEP15inWorkSpace_tag+00000147
[ 43] 0x00007fbdc35458b8 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwiqm.so+03287224 _ZN3iqm18InternalEvalPlugin7executeEP15inWorkSpace_tagRN5boost10shared_ptrIN14cmddistributor17IIPCompletedEventEEE+00000120
[ 44] 0x00007fbd8dbd0a04 /usr/local/MATLAB/R2013a/bin/glnxa64/libnativejmi.so+00694788 _ZN9nativejmi21JmiInternalEvalPlugin7executeEP15inWorkSpace_tagRN5boost10shared_ptrIN14cmddistributor17IIPCompletedEventEEE+00000132
[ 45] 0x00007fbd8dbfafe5 /usr/local/MATLAB/R2013a/bin/glnxa64/libnativejmi.so+00868325 _ZN3mcr3mvm27McrSwappingIqmPluginAdapterIN9nativejmi21JmiInternalEvalPluginEE7executeEP15inWorkSpace_tagRN5boost10shared_ptrIN14cmddistributor17IIPCompletedEventEEE+00000645
[ 46] 0x00007fbdc34c64fa /usr/local/MATLAB/R2013a/bin/glnxa64/libmwiqm.so+02766074
[ 47] 0x00007fbdc34b3e24 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwiqm.so+02690596
[ 48] 0x00007fbdc292d3fd /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00115709 _Z10ioReadLinebP8_IO_FILERKN5boost8optionalIKP15inWorkSpace_tagEEb+00000429
[ 49] 0x00007fbdc292da84 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00117380
[ 50] 0x00007fbdc293349d /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00140445
[ 51] 0x00007fbdc293359e /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00140702
[ 52] 0x00007fbdc2933c7f /usr/local/MATLAB/R2013a/bin/glnxa64/libmwbridge.so+00142463 _Z8mnParserv+00000623
[ 53] 0x00007fbdcc2db3d2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00447442 _ZN11mcrInstance30mnParser_on_interpreter_threadEv+00000034
[ 54] 0x00007fbdcc2ba9ac /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00313772
[ 55] 0x00007fbdcc2bab88 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00314248
[ 56] 0x00007fbdbfe475c6 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwuix.so+00480710
[ 57] 0x00007fbdbfe54df2 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwuix.so+00536050
[ 58] 0x00007fbdcc9a5862 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwservices.so+01845346
[ 59] 0x00007fbdcc9a650f /usr/local/MATLAB/R2013a/bin/glnxa64/libmwservices.so+01848591 _Z25svWS_ProcessPendingEventsiib+00001615
[ 60] 0x00007fbdcc2bb5ef /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00316911
[ 61] 0x00007fbdcc2bbf5c /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00319324
[ 62] 0x00007fbdcc2b5592 /usr/local/MATLAB/R2013a/bin/glnxa64/libmwmcr.so+00292242
[ 63] 0x00007fbdca43e182 /lib/x86_64-linux-gnu/libpthread.so.0+00033154
[ 64] 0x00007fbdca16aefd /lib/x86_64-linux-gnu/libc.so.6+01027837 clone+00000109

This error was detected while a MEX-file was running. If the MEX-file
is not an official MathWorks function, please examine its source code
for errors. Please consult the External Interfaces Guide for information
on debugging MEX-files.

If this problem is reproducible, please submit a Service Request via:
http://www.mathworks.com/support/contact_us/

A technical support engineer might contact you with further information.

Thank you for your help.

I want to train my own R-CNN detector on my own database .I must prepare my files like VOC database. Anyone can give me some ideas? Thanks!

After running key = caffe('get_init_key'), problem like this:
Invalid MEX-file '/path/to/rcnn/external/caffe/matlab/caffe/caffe.mexa64': libcudart.so.6.0: cannot open shared object file: No such file or directory

but i already add /usr/local/cuda-6.0/lib64 to LD_LIBRARY_PATH.
Why this issue still happen? BTW, I use the newest version caffe, and the "make runtest" of caffe passed.

I'm using the latest version of Caffe and Matlab R2014a in Ubuntu 14.04.

It seems that everything works fine until I met this error:

and I located this error in rcnn_load_model.m

I've searched it on Google but it seems nothing helps... :-(

I'm really a newbie to Caffe and rcnn.Should I use an earlier version of Caffe or Matlab? If not, What should I do to fix this problem?

Thanks.

Dear everyone, Dr. Girshick,

I'm trying to run the rcnn_demo. Running using CPU is OK, but when I run using gpu mode there is an error.

"Check failed: error == cudaSuccess (2 vs. 0) out of memory"

I have a GTX 750 gpu card with 1GB memory (using as VGA card to display 2 monitors).

Please help me to adjust the model like changing the batch size or anything so that I can run the demo.

Thanks in advance,

what i only do is to produce files like 'window_file_voc_2012_train.txt";
/path/to/VOC2012/VOCdevkit/VOC2012/JPEGImages/2008_000008.jpg -> picture's name
3 channels
442 ->rows
500 ->cols
2753 -> the number of the boxes
13 1.000 52 86 470 419 -> label, overlap rate,x1,y1,x2,y2
15 1.000 157 43 288 166
Anyone can tell me wheather the explansion is right or any other files I must need?

My matlab crash (segmentation fault) when I call it from rcnn folder.
It looks like the problem is because I haven't included /opt/intel/mkl/lib/intel64 into LD_LIBRARY_PATH.
However, my caffe installation is using openblas. Is there a way to run rcnn using this library?

I am using the latest stable release of caffe, Matlab 2013a, and Ubuntu 14.04.

Thanks.

I want to run RCNN demo ,but i can't get pre-computed models with the following error:

The server has encountered a problem because the resource was not found.
Your request was :
http://www.cs.berkeley.edu/~rbg/$r-cnn-releasel-data.tgz

Hi, guys

Does anyone notice that the selective search data for pascal voc 2007 cannot be downloaded? Anyone knows how can I get the data? Thanks for your help.

I could run RCNN demo only on Matlab R2012b. Matlab 2013a failed with the following error:

Invalid MEX-file '/home/felix/Projects/rcnn/external/caffe/matlab/caffe/caffe.mexa64': /usr/lib/x86_64-linux-gnu/libharfbuzz.so.0: undefined symbol:

FT_Face_GetCharVariantIndex

And even with Matlab R2012b I had to change its simlink for libstdc++ to my default system one to make the demo run.

Hi,
I am a bit confusing about finetuning step. In your paper there are different evaluation results for finetuning of different full-connected layers (fc5, fc6 and fc7). However, in the prototext of this repository, you just changed the name of last layer (softmax) from 'fc80 to 'fc8_pascal' and its parameters, especially, the output parameters: from 1000 to 21 classes. So, if I am not wrong, the finetuning is performed in this layer (fc8) rather than fc5, fc6, and fc7, right?

Best

Hi dear fellas,
I am new to rcnn. Now I want to extract features of my own database. I have read the readme, but stay confused about how to do it. (The feature extraction part is specific for VOC) Can some one shed some light on it?
Best,
Harry

I was trying to extract features from PASCAL VOC 2007 datasets according to the tutorial, everything is normal until matlab throwed a System Error: 'MATLAB has encountered an internal problem and needs to close'. I use ubuntu 14.04 and the matlab edition is 2013b. The R-CNN is runned in CPU mode.

The error was thrown while excuting line 36: 'rcnn_model.cnn.layers = caffe('get_weights')' in rcnn_load_model.m:

Some details of the error:

          abort() detected at Mon Oct  6 22:23:35 2014

Configuration:
Crash Decoding : Disabled
Current Visual : 0x21 (class 4, depth 24)
Default Encoding : UTF-8
GNU C Library : 2.19 stable
MATLAB Architecture: glnxa64
MATLAB Root : /usr/local/MATLAB/R2013b
MATLAB Version : 8.2.0.701 (R2013b)
Operating System : Linux 3.13.0-36-generic #63-Ubuntu SMP Wed Sep 3 21:30:07 UTC 2014 x86_64
Processor ID : x86 Family 6 Model 60 Stepping 3, GenuineIntel
Virtual Machine : Java 1.7.0_11-b21 with Oracle Corporation Java HotSpot(TM) 64-Bit Server VM mixed mode
Window System : The X.Org Foundation (11501000), display :0

Fault Count: 1

Abnormal termination:
abort()

Register State (from fault):
RAX = 0000000000000000 RBX = 00007f6036652620
RCX = ffffffffffffffff RDX = 0000000000000006
RSP = 00007f60799f0b68 RBP = 00007f60799f0ca0
RSI = 0000000000002a9a RDI = 0000000000002a67

R8 = 000000000000ff08 R9 = 00007f604d342fa0
R10 = 0000000000000008 R11 = 0000000000000202
R12 = 00007f5fff3a7660 R13 = 0000000000000000
R14 = 0000000000000000 R15 = 00007f606f65a980

RIP = 00007f608c91fbb9 EFL = 0000000000000202

CS = 0033 FS = 0000 GS = 0000

Stack Trace (from fault):
[ 0] 0x00007f608c91fbb9 /lib/x86_64-linux-gnu/libc.so.6+00224185 gsignal+00000057
[ 1] 0x00007f608c922fc8 /lib/x86_64-linux-gnu/libc.so.6+00237512 abort+00000328
[ 2] 0x00007f603642cd81 /usr/lib/x86_64-linux-gnu/libglog.so.0+00068993 _ZN6google22InstallFailureFunctionEPFvvE+00000000
[ 3] 0x00007f603642cdaa /usr/lib/x86_64-linux-gnu/libglog.so.0+00069034 _ZN6google10LogMessage10SendToSinkEv+00000000
[ 4] 0x00007f603642cce4 /usr/lib/x86_64-linux-gnu/libglog.so.0+00068836 _ZN6google10LogMessage9SendToLogEv+00001224
[ 5] 0x00007f603642c6e6 /usr/lib/x86_64-linux-gnu/libglog.so.0+00067302 _ZN6google10LogMessage5FlushEv+00000414
[ 6] 0x00007f603642f687 /usr/lib/x86_64-linux-gnu/libglog.so.0+00079495 _ZN6google15LogMessageFatalD1Ev+00000025
[ 7] 0x00007f60366d4650 /home/teruun/Documents/rcnn-master/external/caffe/matlab/caffe/caffe.mexa64+00525904
[ 8] 0x00007f603669f872 /home/teruun/Documents/rcnn-master/external/caffe/matlab/caffe/caffe.mexa64+00309362
[ 9] 0x00007f603666f849 /home/teruun/Documents/rcnn-master/external/caffe/matlab/caffe/caffe.mexa64+00112713
[ 10] 0x00007f603666ef13 /home/teruun/Documents/rcnn-master/external/caffe/matlab/caffe/caffe.mexa64+00110355 mexFunction+00000203
[ 11] 0x00007f6084d5efca /usr/local/MATLAB/R2013b/bin/glnxa64/libmex.so+00118730 mexRunMexFile+00000090
[ 12] 0x00007f6084d5b2f4 /usr/local/MATLAB/R2013b/bin/glnxa64/libmex.so+00103156
[ 13] 0x00007f6084d5b464 /usr/local/MATLAB/R2013b/bin/glnxa64/libmex.so+00103524
[ 14] 0x00007f6084193643 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_dispatcher.so+00669251 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000691
[ 15] 0x00007f60821bb154 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04333908
[ 16] 0x00007f60821bcaa9 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04340393
[ 17] 0x00007f60821bd33c /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04342588
[ 18] 0x00007f6082041543 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02786627
[ 19] 0x00007f60820525ce /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02856398
[ 20] 0x00007f60820526b3 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02856627
[ 21] 0x00007f608217c762 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04077410
[ 22] 0x00007f6081fb3139 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02203961
[ 23] 0x00007f6081fb5e67 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02215527
[ 24] 0x00007f6081fb3f4f /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02207567
[ 25] 0x00007f6081fb4ba4 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02210724
[ 26] 0x00007f608201a5bb /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02627003
[ 27] 0x00007f6084193643 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_dispatcher.so+00669251 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000691
[ 28] 0x00007f6081ffbaee /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02501358
[ 29] 0x00007f6081fb0e50 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02195024
[ 30] 0x00007f6081fb2caa /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02202794
[ 31] 0x00007f6081fb5e67 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02215527
[ 32] 0x00007f6081fb3f4f /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02207567
[ 33] 0x00007f6081fb4ba4 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02210724
[ 34] 0x00007f608201a5bb /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02627003
[ 35] 0x00007f6084193643 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_dispatcher.so+00669251 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000691
[ 36] 0x00007f6081ffbaee /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02501358
[ 37] 0x00007f6081fb0e50 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02195024
[ 38] 0x00007f6081fb2caa /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02202794
[ 39] 0x00007f6081fb5e67 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02215527
[ 40] 0x00007f6081fb3f4f /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02207567
[ 41] 0x00007f6081fb4ba4 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02210724
[ 42] 0x00007f608201a5bb /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02627003
[ 43] 0x00007f6084193643 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_dispatcher.so+00669251 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000691
[ 44] 0x00007f60821bb154 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04333908
[ 45] 0x00007f60821bcaa9 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04340393
[ 46] 0x00007f60821bd33c /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04342588
[ 47] 0x00007f6082041543 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02786627
[ 48] 0x00007f60820525ce /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02856398
[ 49] 0x00007f60820526b3 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02856627
[ 50] 0x00007f608217c762 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+04077410
[ 51] 0x00007f6081fb4ad8 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02210520
[ 52] 0x00007f608201a5bb /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02627003
[ 53] 0x00007f6084193643 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_dispatcher.so+00669251 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+00000691
[ 54] 0x00007f6081fe69a5 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02415013
[ 55] 0x00007f6081fabc49 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02174025
[ 56] 0x00007f6081fa88d7 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02160855
[ 57] 0x00007f6081fa8c33 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwm_interpreter.so+02161715
[ 58] 0x00007f6084f8808c /usr/local/MATLAB/R2013b/bin/glnxa64/libmwbridge.so+00139404
[ 59] 0x00007f6084f886d9 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwbridge.so+00141017 _Z8mnParserv+00000697
[ 60] 0x00007f608dd1e4ff /usr/local/MATLAB/R2013b/bin/glnxa64/libmwmcr.so+00468223 _ZN11mcrInstance30mnParser_on_interpreter_threadEv+00000031
[ 61] 0x00007f608dd0297d /usr/local/MATLAB/R2013b/bin/glnxa64/libmwmcr.so+00354685
[ 62] 0x00007f608dd02a00 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwmcr.so+00354816
[ 63] 0x00007f60812bc836 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwuix.so+00346166
[ 64] 0x00007f60812c4862 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwuix.so+00378978
[ 65] 0x00007f608e45aac1 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwservices.so+02271937
[ 66] 0x00007f608e45acfc /usr/local/MATLAB/R2013b/bin/glnxa64/libmwservices.so+02272508
[ 67] 0x00007f608e45668f /usr/local/MATLAB/R2013b/bin/glnxa64/libmwservices.so+02254479
[ 68] 0x00007f608e45b845 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwservices.so+02275397
[ 69] 0x00007f608e45bd34 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwservices.so+02276660
[ 70] 0x00007f608e45c370 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwservices.so+02278256 _Z25svWS_ProcessPendingEventsiib+00000080
[ 71] 0x00007f608dd02c47 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwmcr.so+00355399
[ 72] 0x00007f608dd03408 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwmcr.so+00357384
[ 73] 0x00007f608dcfd538 /usr/local/MATLAB/R2013b/bin/glnxa64/libmwmcr.so+00333112
[ 74] 0x00007f608ccb7182 /lib/x86_64-linux-gnu/libpthread.so.0+00033154
[ 75] 0x00007f608c9e3fbd /lib/x86_64-linux-gnu/libc.so.6+01028029 clone+00000109

This error was detected while a MEX-file was running. If the MEX-file
is not an official MathWorks function, please examine its source code
for errors. Please consult the External Interfaces Guide for information
on debugging MEX-files.

If this problem is reproducible, please submit a Service Request via:
http://www.mathworks.com/support/contact_us/

A technical support engineer might contact you with further information.

Any help or suggestion is very approciated. Thanks.

Hi Ross,
Please, could you tell me how do you computed the binary models such as (finetune_ilsvrc13_val1+train1k_iter_50000,finetune_voc_2007_trainval_iter_70k,...) ? did you use caffe or Alex code ?
because I am using Alex code to generate the binary model so when I use rcnn_model.cnn.layers = caffe('get_weights'); after initialization with binary model computed by Alex code but it does not give the computed final weights learned from the trained model.

Hi,

I am trying to train voc_2007 data as per the example in readme. I created the make window file and executed the following fine-tuning code

GLOG_logtostderr=1 ../../build/tools/finetune_net.bin pascal_finetune_solver.prototxt /home/rajee/rcnn-master/data/caffe_nets/ilsvrc_2012_train_iter_310k 2>&1 | tee log.txt

but i am getting the following error -
WARNING: Logging before InitGoogleLogging() is written to STDERR
F0129 11:33:52.821279 4667 finetune_net.cpp:4] Deprecated. Use caffe train --solver=... [--weights=...] instead.

Can you please help me with this.

Thanks in advance.

I got the following errors when I try to run rcnn training and testing on PASCAL VOC 2012 dataset.
test_results = rcnn_exp_train_test();

Error using *
Inputs must be 2-D, or at least one input must be scalar.
To compute elementwise TIMES, use TIMES (.*) instead.

Error in rcnn_pool5_to_fcX (line 32)
feat = max(0, bsxfun(@plus, feat*rcnn_model.cnn.layers(i).weights{1}, ...

Error in rcnn_train (line 101)
X_pos{i} = rcnn_pool5_to_fcX(X_pos{i}, opts.layer, rcnn_model);

Error in rcnn_exp_train_and_test (line 24)
[rcnn_model, rcnn_k_fold_model] = ...

It seems to me that dimensions of feat and weights{1} are not compatible.
It my program, the dimensions of

size(feat) = 954 9216
size(rcnn_model.cnn.layers(i).weights{1}) = 1 1 9216 4096
size(rcnn_model.cnn.layers(i).weights{2}) = 1 1 1 4096

running rcnn_demo, error occurred when f = caffe('forward', batches(j));
the full message is :

F1205 14:31:18.047643 17619 relu_layer.cu:27] Check failed: error == cudaSuccess (11 vs. 0) invalid argument

My GPU is Tesla K20 the compute capability is 3.5.
And Caffe have been installed with all the caffe test successfully passed...
the version of caffe is the latest caffe release(the release candidate for Caffe 1.0) with head 737ea5e

don't know what is wrong....
need help.....

how to make a bounding box coordinates of a image?is it some software i can use it,i need to do my dateset of rcnn

I don't want to train a new R-CNN detector.
Can I just test the PASCAL VOC detection performance with pre-computed models? (i.e. getting mAP 58.5% on VOC007)
It seems one must run rcnn_exp_train_and_test() to do that. Any suggestion?

Hi everyone,

I installed RCNN and ran all demos on PASCAL VOC 07 without any error, so I proceed to train and test on my own dataset. I have images, classes and complete bounding box coordinates. Instead of defining my own imdb_from_voc, roidb_from_voc and imdb_eval_voc functions, I reformatted my dataset to be compatible with PASCAL VOC. I generated my own annotation xml files, train/val/test txt files and extracted features using rcnn_exp_cache_features(train/val/test) without any problem. However, when I run rcnn_exp_train_and_test(), it shows:

XXX class has 0 positive instances
cache hold 0 pos example and 2443 neg examples

Where did I go wrong? I hope somebody can share an working example on a new dataset or help me figure out this problem so I can share the code to reformat general bounding box annotations into PASCAL VOC format, and make it easier for those who want to use RCNN on their own dataset/research work.

I noticed similar issues as follows:
#34
#23
#17
#14

Thank you!

Hi all! First of all congratulations for the R-CNN work and his implementation.
In my thesis (computer science) i'm using my approach to detect some boxes in an image containing people. I would use the Pool5 layer of R-CNN to predict the bounding box from my boxes.
I think that I have to use the function "rcnn_predict_bbox_regressor(model, feat, ex_boxes)".
I want to use the pretained model, so I think that the model is in the mat file "bbox_regressor_final.mat" (bbox_reg.models{15} for the person category in voc_2012) and I used the function "rcnn_features(im, boxes, rcnn_model)" to obtain the feat.
In this way it doesn't work because the size of feat is different from the size of variable Beta.
Thanks all.

Hi everyone,
I'm new to rcnn. I want to start using rcnn to train a new dataset and I've read the readme. So there is a question, what is the meaning of bounding box annotation? Does it mean that I need to create some files like *.xml from the annotation directory of PASCAL VOC 2007?

Hello,
i've managed to install everything ok on my computer, including caffe and all its dependecies and running the rcnn_demo just fine.
Now am stuck here:

 "Now to run the training and testing code, use the following experiments script:
        >> test_results = rcnn_exp_train_and_test()

where i get the following error:

Training options:
          bias_mult: 10
         cache_name: 'v1_finetune_voc_2007_trainval_iter_70k'
         checkpoint: 0
          crop_mode: 'warp'
       crop_padding: 16
               imdb: [1x1 struct]
            k_folds: 0
              layer: 7
           net_file: './data/caffe_nets/finetune_voc_2007_trainval_iter_70k'
    pos_loss_weight: 2
              svm_C: 1.0000e-03
       net_def_file: './model-defs/rcnn_batch_256_output_fc7.prototxt'

feature stats: 1/200
Error using  * 
Inner matrix dimensions must agree.
Error in rcnn_pool5_to_fcX (line 21)
    feat = max(0, bsxfun(@plus, feat*rcnn_model.cnn.layers(i).weights{1}, ...

Error in rcnn_feature_stats (line 39)
    X = rcnn_pool5_to_fcX(X, layer, rcnn_model);

Error in rcnn_train (line 78)
opts.feat_norm_mean = rcnn_feature_stats(imdb, opts.layer, rcnn_model);

Error in rcnn_exp_train_and_test (line 19)
[rcnn_model, rcnn_k_fold_model] = ...

IMPORTANT NOTES:
To extract the features, i've changed the value of " input_dim: " from "256" to "50" inside the file ./model-defs/rcnn_batch_256_output_pool5.prototxt so i can prevent matlab from crashing . I don't have a really powerfull GPU (NVIDIA GT 540M ), so i thought maybe that was the problem. I've changed the value from "256" to "50"(it was a random number i choice) because i've read in another forum that it will help and ineed it i managed to make it work around this time and finish all of 4 commands below without any errors or crashing of matlab this time

rcnn_exp_cache_features('train'); % chunk1
rcnn_exp_cache_features('val'); % chunk2
rcnn_exp_cache_features('test_1'); % chunk3
rcnn_exp_cache_features('test_2'); % chunk4

Now am not sure what i really changed there and whether that was important. Please some help by anyone who knows what is wrong with my case will be appreciated.

Thank you.

I am a GitHub newbie but the clone command in your install instructions did not work.
I had to use

"git clone git://github.com/rbgirshick/rcnn.git"

Dear sir! Thank you for your great work. I have read your technial report (http://arxiv.org/abs/1311.2524v3) about RCNN and its excellent performance on ILSVRC detection task. I have downloaded the MATLAB code and even managed to download pre-calculated weights and run the demo.

But alas, I still have a few questions:

1. How did you train the system for ILSVRC detection task? In Readme I can see only the description of PASCAL training. Maybe you still have a script for ILSVRC training?

2. As I understood, you made the training set for the final SVM in the following matter:
   You had a huge amount of known bounding boxes of different pre-marked objects from ILSVRC DET detaset.
   To get the training vectors, you extracted the features from all of them by Caffe-Imagenet network
   To get the training labels, you used their pre-known class marks (given in the dataset)
   Am I right?

Hi,

I checked out the ILSVRC branch, but am unable to figure out how to run the train and test code in it.
The scripts rcnn_exp_cache_features and rcnn_exp_train_and_test still try to use the VOC datasets.

I checked out the vgg-verydeep branch but it seems that the content of caffe_nets/ and rcnn_models/ directories are identical to those in the master branch. How do I run the vgg-verydeep version of RCNN?

Please, I follow your steps to do fine tuning. However, I got the following error

I0414 10:50:46.491077 15725 window_data_layer.cpp:354] Number of images: 1
I0414 10:50:46.491097 15725 window_data_layer.cpp:358] class 0 has 0 samples
I0414 10:50:46.491112 15725 window_data_layer.cpp:362] Amount of context padding: 16
I0414 10:50:46.491145 15725 window_data_layer.cpp:365] Crop mode: warp
I0414 10:50:46.491161 15725 window_data_layer.cpp:376] output data size: 128,0,227,227
I0414 10:50:46.491175 15725 window_data_layer.cpp:388] Loading mean file fromimagenet_mean.binaryproto
F0414 10:50:46.492642 15725 window_data_layer.cpp:394] Check failed: data_mean_.channels() == channels (3 vs. 0)
*** Check failure stack trace: ***
@ 0x7f80191c49fd google::LogMessage::Fail()
@ 0x7f80191c689d google::LogMessage::SendToLog()
@ 0x7f80191c45ec google::LogMessage::Flush()
@ 0x7f80191c71be google::LogMessageFatal::~LogMessageFatal()
@ 0x4bf1c6 caffe::WindowDataLayer<>::SetUp()
@ 0x440e17 caffe::Net<>::Init()
@ 0x4420a5 caffe::Net<>::Net()
@ 0x42df0f caffe::Solver<>::Init()
@ 0x4315db caffe::Solver<>::Solver()
@ 0x40a3d2 main
@ 0x7f801516bec5 (unknown)
@ 0x40c28e (unknown)

Does this code handle datasets (train or test) in which some of the images have no object of interest in them?

If not, do you have any pointers as to what would need to be modified in order to allow for that?

Thanks in advance for your help!

Caffe v0.999 introduced a fair number of changes, so I suspect R-CNN might need a few adjustments. We can update the vetted R-CNN release once it's ready!

Hello,
I have prepared the dataset for my classification, but how should I handle the background class? Do I have to create a random set of background dataset? and why is it necessary? is it just acting as negative images?

Thank you,

Hi all, I am trying to compile Caffe.. But when i Make Runtest, it give me the following error. Can any body guide me whats the problem, as i am totally new, so can't figure it. Help in this regards will be highly appreciated. Regards
Below is the error message:
caffe-0.999$ make runtest build/test/test_all.testbin 0 --gtest_shuffle
Cuda number of devices: 3
Setting to use device 0
Current device id: 0
Note: Randomizing tests' orders with a seed of 41199 .
[==========] Running 401 tests from 74 test cases.
[----------] Global test environment set-up.
[----------] 18 tests from NeuronLayerTest/1, where TypeParam = double
[ RUN ] NeuronLayerTest/1.TestReLUGradientCPU
[ OK ] NeuronLayerTest/1.TestReLUGradientCPU (222 ms)
[ RUN ] NeuronLayerTest/1.TestSigmoidCPU
[ OK ] NeuronLayerTest/1.TestSigmoidCPU (0 ms)
[ RUN ] NeuronLayerTest/1.TestReLUGradientGPU
F0723 14:15:30.579854 8772 relu_layer.cu:29] Check failed: error == cudaSuccess (8 vs. 0) invalid device function
*** Check failure stack trace: ***
@ 0x2ac23ea86b7d google::LogMessage::Fail()
@ 0x2ac23ea88c7f google::LogMessage::SendToLog()
@ 0x2ac23ea8676c google::LogMessage::Flush()
@ 0x2ac23ea8951d google::LogMessageFatal::~LogMessageFatal()
@ 0x63f1ae caffe::ReLULayer<>::Forward_gpu()
@ 0x44ece3 caffe::GradientChecker<>::CheckGradientSingle()
@ 0x45c17a caffe::GradientChecker<>::CheckGradientEltwise()
@ 0x45c449 caffe::NeuronLayerTest_TestReLUGradientGPU_Test<>::TestBody()
@ 0x58d25d testing::internal::HandleExceptionsInMethodIfSupported<>()
@ 0x585081 testing::Test::Run()
@ 0x585166 testing::TestInfo::Run()
@ 0x5852a7 testing::TestCase::Run()
@ 0x5855fe testing::internal::UnitTestImpl::RunAllTests()
@ 0x58cddd testing::internal::HandleExceptionsInMethodIfSupported<>()
@ 0x5846de testing::UnitTest::Run()
@ 0x4434dd main
@ 0x2ac240dfa76d (unknown)
@ 0x4481ad (unknown)
make: *** [runtest] Aborted (core dumped)

I have downloaded rcnn and am using caffe.rc2 ( caffe.099 does not build sucessfully with the latest nvidia cuda driver atleast on my system). When I try running rcnn_demo, I get the below error message, appreciate any info to solve the problem:

Error using caffe
Expected 2 arguments, got 2

Error in rcnn_load_model (line 27)
rcnn_model.cnn.init_key = ...

Error in rcnn_demo (line 59)
rcnn_model = rcnn_load_model(rcnn_model_file, use_gpu);

I am trying to train rccn with my own dataset and am trying to document the steps needed:

1. Identify the classes of detection
2. Use the VOC 07 folders as a template or use as it is to start
3. Label the images in VOC 07 format ie. 000001.jpg, etc. and store them in JPEGImages folder
4. Create bounding box annotation for the objects to be detected with the correct labeled image, etc. and store them in the Annotations folder
5. Create training, validation, test data files, class_train.txt, class_test.txt, class_val.txt, class_trainval.txt (see ImageSets/Main folder for examples)
   -- Use the same format [ imageid -1 (false) or imageid 1 (true) or imageid 0 (not sure but seems to be true)]

Do we need the others ? like ImageSet/Layout, ImageSet/Segmentation ?

Also, do we need the SegmentationClass and SegmentationObjects folders ? Any ideas on how these were created ? Here is an example:

Hi, Ross and everyone
I'm training a new RCNN model on my own data-set. I notice "./data/selective_search_data/" contains some pre-generated selective-search(ss) data. If I didn't miss anything in the code, "selective_search_boxes.m" seems to be used to generate the ss results.
Is there any other inner tricks to generate these ss data?
Charles,
Regards,

Hello,
I have met a strange problem. And I have costed 2 weeks to search for a solution.
My ubuntu always reboot suddenly when rcnn runing. And I have located the error code which
is in the rcnn_features.m with the "f = caffe('forward', batches(j)); ".
Below is my experiments infomation.
1, ubuntu 14.04
2, cuda 6.0
3, Geforce Titan black
Can anyone help me?

I am training the network with a new dataset and everything's been good until I run "attach_proposals" function in the imdb/roidb_from_voc.m script.

Fifth line from the bottom, there is a function named "boxoverlap", but I cannot find it from anywhere. Where does this come from?

the ILSVRC13 model and voc_2012 model is OK,but i have a problem when i ran with voc_2007 model:

Warning: Could not find appropriate function on path loading function
UNKOWN FUNCTION.

Maybe something wrong with the model (voc_2007/rcnn_model_finetuned.mat)?
AND anyone else know this why?

Hi, I want to install it on my Mac OS X 10.7.5 with matlab 2012b. But i am facing an error..
i installed CUDA. I have Opencv, I have matlab 202b. But as i have OS X 10.7.5.
and Caffe Blas is with 10.8 or 9 but i have 10.7.5. so what should i do?
regards

When I run key=caffe('get_init_key') in matlab I get the following:
Undefined function 'caffe' for input arguments of type 'char'.

Unable to track what is the problem. Please help.

Hello,
First of all thank you for providing a well documented tutorial for rcnn.

I followed the tutorial. I got to the point where I executed the command:

key = caffe('get_init_key');

and it returns me -2 as the tutorial says. Everything seemed to be going well until that point. When I tried running rcnn_demo(PASCAL,0); I got this:

I would be very grateful if you can help me with this problem. Thank you

The Matlab crush dump file contains this information:

        Abort signal detected at Mon Jul 21 16:55:41 2014

Configuration:
Crash Decoding : Disabled
Current Visual : 0x20 (class 4, depth 24)
Default Encoding: UTF-8
GNU C Library : 2.15 stable
MATLAB Root : /usr/local/MATLAB/R2012b
MATLAB Version : 8.0.0.783 (R2012b)
Operating System: Linux 3.11.0-26-generic #45~precise1-Ubuntu SMP Tue Jul 15 04:02:35 UTC 2014 x86_64
Processor ID : x86 Family 6 Model 42 Stepping 7, GenuineIntel
Virtual Machine : Java 1.6.0_17-b04 with Sun Microsystems Inc. Java HotSpot(TM) 64-Bit Server VM mixed mode
Window System : The X.Org Foundation (11406000), display :0

Fault Count: 1

Abnormal termination:
Abort signal

Register State (from fault):
RAX = 0000000000000000 RBX = 0000000000030005
RCX = ffffffffffffffff RDX = 0000000000000006
RSP = 00007f5dfb7efba8 RBP = 0000000000000002
RSI = 0000000000001ddb RDI = 0000000000001da0

R8 = 00007f5dfb7fe700 R9 = 2f73746375646f72
R10 = 0000000000000008 R11 = 0000000000000206
R12 = 0000000000000000 R13 = 00007f5e0053b600
R14 = 00007f5dfb7f0018 R15 = 0000000000000000

RIP = 00007f5e11b38425 EFL = 0000000000000206

CS = 0033 FS = 0000 GS = 0000

Stack Trace (from fault):
[ 0] 0x00007f5e146ec1de /usr/local/MATLAB/R2012b/bin/glnxa64/libmwfl.so+00516574 _ZN2fl4diag15stacktrace_base7captureERKNS0_14thread_contextEm+000158
[ 1] 0x00007f5e146ed4b2 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwfl.so+00521394
[ 2] 0x00007f5e146eeffe /usr/local/MATLAB/R2012b/bin/glnxa64/libmwfl.so+00528382 _ZN2fl4diag13terminate_logEPKcRKNS0_14thread_contextE+000174
[ 3] 0x00007f5e139db093 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00557203 _ZN2fl4diag13terminate_logEPKcPK8ucontext+000067
[ 4] 0x00007f5e139d7b9d /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00543645
[ 5] 0x00007f5e139d9835 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00550965
[ 6] 0x00007f5e139d9a55 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00551509
[ 7] 0x00007f5e139da0fe /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00553214
[ 8] 0x00007f5e139da719 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00554777
[ 9] 0x00007f5e11ed1cb0 /lib/x86_64-linux-gnu/libpthread.so.0+00064688
[ 10] 0x00007f5e11b38425 /lib/x86_64-linux-gnu/libc.so.6+00222245 gsignal+000053
[ 11] 0x00007f5e11b3bb8b /lib/x86_64-linux-gnu/libc.so.6+00236427 abort+000379
[ 12] 0x00007f5d50db11b3 /opt/intel/mkl/lib/intel64/../../../compiler/lib/intel64/libiomp5.so+00446899
[ 13] 0x00007f5d50d9c677 /opt/intel/mkl/lib/intel64/../../../compiler/lib/intel64/libiomp5.so+00362103
[ 14] 0x00007f5d50daf76b /opt/intel/mkl/lib/intel64/../../../compiler/lib/intel64/libiomp5.so+00440171
[ 15] 0x00007f5d50db07b2 /opt/intel/mkl/lib/intel64/../../../compiler/lib/intel64/libiomp5.so+00444338
[ 16] 0x00007f5d50d9926e /opt/intel/mkl/lib/intel64/../../../compiler/lib/intel64/libiomp5.so+00348782 omp_get_num_procs+000030
[ 17] 0x00007f5d4fe3fec4 /opt/intel/mkl/lib/intel64/libmkl_intel_thread.so+01158852
[ 18] 0x00007f5d4fe41239 /opt/intel/mkl/lib/intel64/libmkl_intel_thread.so+01163833 mkl_serv_domain_get_max_threads+000089
[ 19] 0x00007f5d4fe94d90 /opt/intel/mkl/lib/intel64/libmkl_intel_thread.so+01506704
[ 20] 0x00007f5d4fe91597 /opt/intel/mkl/lib/intel64/libmkl_intel_thread.so+01492375 mkl_blas_sgemm+001543
[ 21] 0x00007f5d4f6b983c /opt/intel/mkl/lib/intel64/libmkl_intel_lp64.so+00927804 sgemm+000300
[ 22] 0x00007f5d4f6d28c2 /opt/intel/mkl/lib/intel64/libmkl_intel_lp64.so+01030338 cblas_sgemm+000370
[ 23] 0x00007f5d4308df86 /opt/intel/mkl/lib/intel64/libmkl_rt.so+01015686 cblas_sgemm+000238
[ 24] 0x00007f5d5c96b542 /home/michael/caffe/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00267586
[ 25] 0x00007f5d5ca03cbd /home/michael/caffe/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00892093
[ 26] 0x00007f5d5c94e66c /home/michael/caffe/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00149100
[ 27] 0x00007f5d5c946a76 /home/michael/caffe/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00117366
[ 28] 0x00007f5d5c946024 /home/michael/caffe/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00114724 mexFunction+000225
[ 29] 0x00007f5e0a6ba69a /usr/local/MATLAB/R2012b/bin/glnxa64/libmex.so+00112282 mexRunMexFile+000090
[ 30] 0x00007f5e0a6b64e9 /usr/local/MATLAB/R2012b/bin/glnxa64/libmex.so+00095465
[ 31] 0x00007f5e0a6b733c /usr/local/MATLAB/R2012b/bin/glnxa64/libmex.so+00099132
[ 32] 0x00007f5e13729a4b /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_dispatcher.so+00596555 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+000539
[ 33] 0x00007f5e131aa206 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+04280838
[ 34] 0x00007f5e131aa97a /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+04282746
[ 35] 0x00007f5e131ab4ea /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+04285674
[ 36] 0x00007f5e1300e4cd /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02593997
[ 37] 0x00007f5e13039d22 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02772258
[ 38] 0x00007f5e13039e4f /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02772559
[ 39] 0x00007f5e13156b30 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+03939120
[ 40] 0x00007f5e12f72fec /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01957868
[ 41] 0x00007f5e12f6f0d3 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01941715
[ 42] 0x00007f5e12f6fed7 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01945303
[ 43] 0x00007f5e12fdb760 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02385760
[ 44] 0x00007f5e13729a4b /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_dispatcher.so+00596555 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+000539
[ 45] 0x00007f5e12fbde56 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02264662
[ 46] 0x00007f5e12f6e1c6 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01937862
[ 47] 0x00007f5e12f72ab4 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01956532
[ 48] 0x00007f5e12f6f0d3 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01941715
[ 49] 0x00007f5e12f6fed7 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01945303
[ 50] 0x00007f5e12fdb760 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02385760
[ 51] 0x00007f5e13729a4b /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_dispatcher.so+00596555 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+000539
[ 52] 0x00007f5e12fbde56 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02264662
[ 53] 0x00007f5e12f6e1c6 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01937862
[ 54] 0x00007f5e12f72ab4 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01956532
[ 55] 0x00007f5e12f6f0d3 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01941715
[ 56] 0x00007f5e12f6fed7 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01945303
[ 57] 0x00007f5e12fdb760 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02385760
[ 58] 0x00007f5e13729a4b /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_dispatcher.so+00596555 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+000539
[ 59] 0x00007f5e12fbde56 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02264662
[ 60] 0x00007f5e12f49c1d /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01788957
[ 61] 0x00007f5e12f7224e /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01954382
[ 62] 0x00007f5e12f6f0d3 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01941715
[ 63] 0x00007f5e12f6fed7 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01945303
[ 64] 0x00007f5e12fdb760 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02385760
[ 65] 0x00007f5e13729a4b /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_dispatcher.so+00596555 ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2+000539
[ 66] 0x00007f5e12faa97b /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+02185595
[ 67] 0x00007f5e12f6821c /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01913372
[ 68] 0x00007f5e12f6524d /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01901133
[ 69] 0x00007f5e12f65685 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwm_interpreter.so+01902213
[ 70] 0x00007f5e0a8e522e /usr/local/MATLAB/R2012b/bin/glnxa64/libmwbridge.so+00143918
[ 71] 0x00007f5e0a8e5391 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwbridge.so+00144273
[ 72] 0x00007f5e0a8e5f6d /usr/local/MATLAB/R2012b/bin/glnxa64/libmwbridge.so+00147309 _Z8mnParserv+000733
[ 73] 0x00007f5e139c0472 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00447602 _ZN11mcrInstance30mnParser_on_interpreter_threadEv+000034
[ 74] 0x00007f5e1399eb69 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00310121
[ 75] 0x00007f5e1399ed48 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00310600
[ 76] 0x00007f5e0794cc36 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwuix.so+00474166
[ 77] 0x00007f5e07957cc2 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwuix.so+00519362
[ 78] 0x00007f5e1404ea11 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwservices.so+01628689 ZSt8for_eachIN9__gnu_cxx17__normal_iteratorIPN5boost8weak_ptrIN4sysq10ws_ppeHookEEESt6vectorIS6_SaIS6_EEEENS4_8during_FIS6_NS2_10shared_ptrIS5_EEEEET0_T_SH_SG+000081
[ 79] 0x00007f5e1404faeb /usr/local/MATLAB/R2012b/bin/glnxa64/libmwservices.so+01633003 ZN4sysq12ppe_for_eachINS_8during_FIN5boost8weak_ptrINS_10ws_ppeHookEEENS2_10shared_ptrIS4_EEEEEET_RKS9+000251
[ 80] 0x00007f5e1404d5a2 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwservices.so+01623458 _ZN4sysq19ppePollingDuringFcnEb+000114
[ 81] 0x00007f5e1404d969 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwservices.so+01624425 _ZN4sysq11ppeMainLoopEiib+000121
[ 82] 0x00007f5e1404db08 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwservices.so+01624840 _ZN4sysq11ppeLoopIfOKEiib+000152
[ 83] 0x00007f5e1404dc63 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwservices.so+01625187 _ZN4sysq20processPendingEventsEiib+000147
[ 84] 0x00007f5e1399f664 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00312932
[ 85] 0x00007f5e1399fb3c /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00314172
[ 86] 0x00007f5e13999592 /usr/local/MATLAB/R2012b/bin/glnxa64/libmwmcr.so+00288146
[ 87] 0x00007f5e11ec9e9a /lib/x86_64-linux-gnu/libpthread.so.0+00032410
[ 88] 0x00007f5e11bf63fd /lib/x86_64-linux-gnu/libc.so.6+01000445 clone+000109

This error was detected while a MEX-file was running. If the MEX-file
is not an official MathWorks function, please examine its source code
for errors. Please consult the External Interfaces Guide for information
on debugging MEX-files.

If this problem is reproducible, please submit a Service Request via:
http://www.mathworks.com/support/contact_us/

A technical support engineer might contact you with further information.

Thank you for your help.

Is GeForce GTX 980 enough? or I should buy titan black?
Thanks!

I was trying to run the demo (I am using only CPU mode, on a 4gb RAM 4core i7 along with 80GB swap)

I got the following error in my terminal (http://pastebin.com/6sx8uBXe). Not sure how to fix this. COuld you please help ?

I've been trying to get this implementation online, but am running into a roadblock with the PASCAL 2007 dataset. It appears as though pascallin.ecs.soton.ac.uk is down and unreachable.

Does anybody have a working mirror or willing to host a copy of the data:

• http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
• http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/VOCtest_06-Nov-2007.tar
• http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/VOCdevkit_08-Jun-2007.tar

Edit: If I can get a copy of the data, I will add it to the academictorrents.com tracker so this doesn't happen again.

Edit 2: I'm still trying to track them all down, but I've added some of the missing VOC dataset files to academictorrents.com: http://academictorrents.com/browse.php?search=voc

Hello,

First of all, thank you for providing a well documented tutorial for rcnn.

I followed the tutorial. I got to the point where I executed the command:

key = caffe('get_init_key');

and it returns me -2 as the tutorial says. Everything seemed to be going well until that point. When I tried running `rcnn_demo('ILSVRC13', 0) ; I got this

I traced the execution flow of the program and I found out that it stopped at here:

rcnn_model.cnn.init_key = ...
caffe('init', rcnn_model.cnn.definition_file, rcnn_model.cnn.binary_file);

It already passes 3 arguments to caffe. Why does MATLAB still output the following error message?

Error using caffe
Expected 3 arguments, got 2

And MATLAB also displays a warning:

Warning: Could not find appropriate function on path loading function handle
/home/rbg/working/rcnn-ilsvrc/imdb/imdb_from_ilsvrc13.m>@(i)fullfile(imdb.image_dir,[imdb.image_ids{i},'.',imdb.extension])

In rcnn_load_model at 21
In rcnn_demo at 59

/home/rbg/working/rcnn-ilsvrc/imdb/imdb_from_ilsvrc13.m>@(i)fullfile(imdb.image_dir,[imdb.image_ids{i},'.',imdb.extension]) seems to be a path on Dr. Girshick's(the writer) computer. This is very strange. Does this warning matter?

I use the latest version of Caffe and MATLAB 2014a to run the code.