search

zhangliliang / RPN_BF

RPN+BF
Other
203 stars 75 forks source link

error when running scipts_rpn_bf_pedestrian_VGG16_caltech_demo #37

Open liangzimei opened 7 years ago

liangzimei commented 7 years ago

when i run this demo, there is a error Check failed: error == cudaSuccess (2 vs. 0) out of memory. my gpu is k80, i think the memory is enough to run this demo ,do you know why ?

rocksat commented 7 years ago

I have the same problem, my GPU is gtx 1080, which has 8GB memory, why it is still out of memory?

zchrissirhcz commented 7 years ago

@rocksat Is there cudnn installed on your machine? It saves video memory.

rocksat commented 7 years ago

@zchrissirhcz I figured out, install cudnn can solve the memory issue, at lease it works on GTX 1080. I tried to compile with cudnn v5, v4 and v3, only v3 works. Any idea to make it compatible with cudnn v5?

zchrissirhcz commented 7 years ago

See this reference : https://github.com/zhangliliang/RPN_BF/issues/11

The author gives 3 suggestions:

a. Modify the Makefile.config to disable the cudnn before compling this repo.
b. Use older cudnn version like v4 or v3.
c. Merge this repo into current caffe version, which support cudnn v5.

I figure this problem in another way. I installed Caffe from BVLC official site, and change RPN-BF repo prototxt, i.e. use dilation keyword for hole algorithm support.

ChongYunPeng commented 7 years ago

@zchrissirhcz I am quite new to caffe. Could you explain how you got the demo to work using your method? I tried (c) managed successfully run mmake matcaffe but when I run make mattest, I get the error: *** Error in '/usr/local/MATLAB/R2017a/bin/glnxa64/MATLAB': corrupted size vs. prev_size: 0x00007f69fb57d650 ***

My GPU is gtx 1080 and I am using cuda 8.0.