denistome / deepped Goto Github PK
View Code? Open in Web Editor NEWConvolutional Neural Networks for Pedestrian Detection
Convolutional Neural Networks for Pedestrian Detection
Is that like R-CNN?
I work fine with rcnn_demo
but after I download all the codes and data from yours, running deepPed_demo
makes matlab crushed saying "Matlab has encountered an internal problem and needs to close". My platform is Ubuntu 15.04 & Caffe v0.999 & Matlab2015b.
The errors are shown as follows:
[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 7:7: Message type "caffe.NetParameter" has no field named "layer".
F0518 12:21:06.165700 6911 upgrade_proto.cpp:571] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: model-defs/alexnet_deploy_fc7_CAFFE.prototxt
*** Check failure stack trace: ***
I'm running MATLAB R2014a on Ubuntu 14.04 LTS.
I followed your instructions and tried to run your code.
I test rcnn code, i.e. run rcnn_demo, and everything works fine.
I also download your model and place in the right directory.
So when MATLAB trying to load model using following sentence:
rcnn_model = rcnn_load_model(rcnn_model_file, use_gpu);
MATLAB crashed.
------------------------------------------------------------------------
abort() detected at Tue Oct 27 14:17:24 2015
------------------------------------------------------------------------
Configuration:
Crash Decoding : Disabled
Current Visual : 0x5e (class 4, depth 24)
Default Encoding : UTF-8
GNU C Library : 2.19 stable
MATLAB Architecture: glnxa64
MATLAB Root : /usr/local/MATLAB/R2014A
MATLAB Version : 8.3.0.532 (R2014a)
Operating System : Linux 3.13.0-32-generic #57-Ubuntu SMP Tue Jul 15 03:51:08 UTC 2014 x86_64
Processor ID : x86 Family 6 Model 58 Stepping 9, 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 :0.0
Fault Count: 1
Abnormal termination:
abort()
Register State (from fault):
RAX = 0000000000000000 RBX = 00007f16c1eb5620
RCX = ffffffffffffffff RDX = 0000000000000006
RSP = 00007f177f336458 RBP = 00007f177f336590
RSI = 0000000000000c73 RDI = 0000000000000c42
R8 = 000000000000ff08 R9 = ffffffffffff1150
R10 = 0000000000000008 R11 = 0000000000000206
R12 = 00007f177f336830 R13 = 00007f16d44f75e0
R14 = 0000000000000001 R15 = 00007f177f3370b0
RIP = 00007f17916c8cc9 EFL = 0000000000000206
CS = 0033 FS = 0000 GS = 0000
Stack Trace (from fault):
[ 0] 0x00007f17916c8cc9 /lib/x86_64-linux-gnu/libc.so.6+00224457 gsignal+00000057
[ 1] 0x00007f17916cc0d8 /lib/x86_64-linux-gnu/libc.so.6+00237784 abort+00000328
[ 2] 0x00007f16c1c8fd81 /usr/lib/x86_64-linux-gnu/libglog.so.0+00068993 _ZN6google22InstallFailureFunctionEPFvvE+00000000
[ 3] 0x00007f16c1c8fdaa /usr/lib/x86_64-linux-gnu/libglog.so.0+00069034 _ZN6google10LogMessage10SendToSinkEv+00000000
[ 4] 0x00007f16c1c8fce4 /usr/lib/x86_64-linux-gnu/libglog.so.0+00068836 _ZN6google10LogMessage9SendToLogEv+00001224
[ 5] 0x00007f16c1c8f6e6 /usr/lib/x86_64-linux-gnu/libglog.so.0+00067302 _ZN6google10LogMessage5FlushEv+00000414
[ 6] 0x00007f16c1c92687 /usr/lib/x86_64-linux-gnu/libglog.so.0+00079495 _ZN6google15LogMessageFatalD1Ev+00000025
[ 7] 0x00007f16d82f03bb /home/dst/Github/DeepPed_New/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00394171
[ 8] 0x00007f16d82b8b7a /home/dst/Github/DeepPed_New/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00166778
[ 9] 0x00007f16d82a6d9a /home/dst/Github/DeepPed_New/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00093594
[ 10] 0x00007f16d82a7043 /home/dst/Github/DeepPed_New/rcnn/external/caffe/matlab/caffe/caffe.mexa64+00094275 mexFunction+00000203
[ 11] 0x00007f17895f372a /usr/local/MATLAB/R2014A/bin/glnxa64/libmex.so+00120618 mexRunMexFile+00000090
[ 12] 0x00007f17895efa94 /usr/local/MATLAB/R2014A/bin/glnxa64/libmex.so+00105108
[ 13] 0x00007f17895f0fb4 /usr/local/MATLAB/R2014A/bin/glnxa64/libmex.so+00110516
[ 14] 0x00007f17889eaad9 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_dispatcher.so+00670425 _ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2_+00000697
[ 15] 0x00007f1787c872b4 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+04461236
[ 16] 0x00007f1787c88bc9 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+04467657
[ 17] 0x00007f1787c893fc /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+04469756
[ 18] 0x00007f1787b036e3 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02873059
[ 19] 0x00007f1787b1309e /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02936990
[ 20] 0x00007f1787b13183 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02937219
[ 21] 0x00007f1787c49172 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+04206962
[ 22] 0x00007f1787a7e589 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02327945
[ 23] 0x00007f1787a81167 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02339175
[ 24] 0x00007f1787a7f26f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02331247
[ 25] 0x00007f1787a7fec4 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02334404
[ 26] 0x00007f1787add30b /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02716427
[ 27] 0x00007f17889eaad9 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_dispatcher.so+00670425 _ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2_+00000697
[ 28] 0x00007f1787ac120e /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02601486
[ 29] 0x00007f1787a7c1d0 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02318800
[ 30] 0x00007f1787a7e1ea /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02327018
[ 31] 0x00007f1787a81167 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02339175
[ 32] 0x00007f1787a7f26f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02331247
[ 33] 0x00007f1787a7fec4 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02334404
[ 34] 0x00007f1787add30b /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02716427
[ 35] 0x00007f17889eaad9 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_dispatcher.so+00670425 _ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2_+00000697
[ 36] 0x00007f1787ac120e /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02601486
[ 37] 0x00007f1787a621b0 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02212272
[ 38] 0x00007f1787a7d25f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02323039
[ 39] 0x00007f1787a81167 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02339175
[ 40] 0x00007f1787a7f26f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02331247
[ 41] 0x00007f1787a7fec4 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02334404
[ 42] 0x00007f1787add30b /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02716427
[ 43] 0x00007f17889eac5f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_dispatcher.so+00670815 _ZN8Mfh_file11dispatch_fhEiPP11mxArray_tagiS2_+00001087
[ 44] 0x00007f1787ab0135 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02531637
[ 45] 0x00007f1787a770d9 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02298073
[ 46] 0x00007f1787a73dc7 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02284999
[ 47] 0x00007f1787a74193 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwm_interpreter.so+02285971
[ 48] 0x00007f178981dafc /usr/local/MATLAB/R2014A/bin/glnxa64/libmwbridge.so+00142076
[ 49] 0x00007f178981e791 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwbridge.so+00145297 _Z8mnParserv+00000721
[ 50] 0x00007f1792ad492f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwmcr.so+00489775 _ZN11mcrInstance30mnParser_on_interpreter_threadEv+00000031
[ 51] 0x00007f1792ab5b6d /usr/local/MATLAB/R2014A/bin/glnxa64/libmwmcr.so+00363373
[ 52] 0x00007f1792ab5be9 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwmcr.so+00363497
[ 53] 0x00007f17871a9d46 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwuix.so+00343366
[ 54] 0x00007f178718c382 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwuix.so+00222082
[ 55] 0x00007f179322a50f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwservices.so+02323727
[ 56] 0x00007f179322a67c /usr/local/MATLAB/R2014A/bin/glnxa64/libmwservices.so+02324092
[ 57] 0x00007f179322657f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwservices.so+02307455
[ 58] 0x00007f179322b9b5 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwservices.so+02329013
[ 59] 0x00007f179322bde7 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwservices.so+02330087
[ 60] 0x00007f179322c4c0 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwservices.so+02331840 _Z25svWS_ProcessPendingEventsiib+00000080
[ 61] 0x00007f1792ab6098 /usr/local/MATLAB/R2014A/bin/glnxa64/libmwmcr.so+00364696
[ 62] 0x00007f1792ab63bf /usr/local/MATLAB/R2014A/bin/glnxa64/libmwmcr.so+00365503
[ 63] 0x00007f1792ab128f /usr/local/MATLAB/R2014A/bin/glnxa64/libmwmcr.so+00344719
[ 64] 0x00007f1791a5f182 /lib/x86_64-linux-gnu/libpthread.so.0+00033154
[ 65] 0x00007f179178c47d /lib/x86_64-linux-gnu/libc.so.6+01025149 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've been trying to run this but I ran out of GPU memory. Therefore I reduced the batch size and it works fine (i.e no cuda crash) however now I'm facing the problem that your SVM does not take batch reduction into account. Is there any workaround to this (or would you be so kind as to train the SVM again just with less features, I would be eternally grateful) or my only chance is really to get a better GPU?
EDIT: as a botched solution I just did:
% load the trained SVM
SVM = load('data/rcnn_models/DeepPed/SVM_finetuned_alexnet.mat');
%PersonW = SVM.W; %Feature weights for scoring
PersonW = SVM.W(1:end/2);
PersonB = SVM.b; %Constant scoring factor
But I'm pretty sure this will be incorrect.
Thank you
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.