ShaoqingRen / SPP_net

SPP_net : Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
364 stars 237 forks source link

crash problem #20

Closed jackiechensuper closed 9 years ago

jackiechensuper commented 9 years ago

Hi Shaoqing, when I run the SPP_net / experiments / Script_spp_voc.m, it can extract features from images. However, it crashed when it ran for a number of images. This happened occasionally. Have you met this problem before ? Following is the error information, but I found it with little help. Regards

Jackie

          abort() detected at Sat Nov 29 16:18:49 2014

Configuration: Crash Decoding : Disabled Current Visual : 0x24 (class 4, depth 24) Default Encoding : UTF-8 GNU C Library : 2.15 stable MATLAB Architecture: glnxa64 MATLAB Root : /usr/local/MATLAB/R2013b MATLAB Version : 8.2.0.701 (R2013b) Operating System : Linux 3.8.0-38-generic #56~precise1-Ubuntu SMP Thu Mar 13 16:22:48 UTC 2014 x86_64 Processor ID : x86 Family 6 Model 45 Stepping 7, GenuineIntel Virtual Machine : Java 1.7.0_11-b21 with Oracle Corporation Java HotSpot(TM) 64-Bit Server VM mixed mode Window System : The XFree86 Project, Inc (40300000), display :12.0

Fault Count: 1

Abnormal termination: abort()

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.

ShaoqingRen commented 9 years ago

Hi Jackie,

I think the most likely reason is gpu out of memory. You can check the usage of gpu memory using gpu-z,etc. And maybe changing Line 55 in spp_features_convX.m for max memory usage.

Shaoqing

jackiechensuper commented 9 years ago

hi Shaoqing, Thanks for your answer. Actually I am using K40c(12G ), and I have checked it just used around 2G gpu memory. Do you think it might be the difference of Matlab version. I am using the 2013b.

Thanks Jackie

ShaoqingRen commented 9 years ago

Hi Jackie,

I havn't met this problem in feature extraction and I think this is not caused by matlab version. I think a good solution is to check which function crashed, if it's the matcaffe, you can bulid a log in matcaffe's “init" function to see what happened.

Best, Shaoqing