I did not successfully compile your code

[1yaya]

I am using Ubuntu16.04+cuda8.0, make all -j8 and make pycaffe have no problem, but when I ran solve_fphb_crack.py, I encountered an error, "Check failed: error == cudaSuccess (10 vs 0) invalid device ordinal", so please tell me the environment information you used at that time and some details of the compilation. Thank you very much for your help.

[fyangneil]

@1yaya maybe this link can help you BVLC/caffe#1596

[zhoujh2020]

Thank you very much for your help. I have a new problem and I still need to trouble you. I have carried out 12,000 iterations and evaluated, and the results are very close to those given in your paper. But my average test time for a picture is much longer than yours. May I ask if this is just my hardware problem or some parameter setting problem, I look forward to your answer

[zhoujh2020]

If I multiply the time of each picture I get by 0.6, I will get the data in your paper. Do you know what's going on, thank you again

[zhoujh2020]

@fyangneil

[fyangneil]

I am not sure, it may have business with your hardware Get Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ From: zhoujh2020 <notifications@github.com> Sent: Wednesday, October 7, 2020 5:15:22 AM To: fyangneil/pavement-crack-detection <pavement-crack-detection@noreply.github.com> Cc: Fan Yang <fyang@temple.edu>; Mention <mention@noreply.github.com> Subject: [External] Re: [fyangneil/pavement-crack-detection] I did not successfully compile your code (#17) @fyangneil<https://github.com/fyangneil> — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<#17 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ALAUWTVCWJRXBL4TCGEEIU3SJQWSVANCNFSM4R33L5LQ>.

[fyangneil]

@zhoujh2020 it may have business with your harfware

[fightingchun]

I'd like to ask you the difference between traincrop and traindata in the Crack500,thanks!

[fyangneil]

@fightingchun the traincrop is the cropped image patch, traindata is the raw image