search

fyangneil / pavement-crack-detection

348 stars 77 forks source link

If I make my own data set with the same format as crack500, what code do I need to modify to work normally? Is there any requirement for the size of the picture? #28

Open a957815154 opened 3 years ago

fyangneil commented 3 years ago

@a957815154 In my understanding, if your dataset is the same format as crack500, you can train and test the model directly. But if you want a good result, some tuning may be needed, which is based on your experience and understanding of your data and the model. There is no specific restriction on image size, it is up to your GPU memory size.

a957815154 commented 3 years ago

Thank you ! Is it necessary to modify the image average?

fyangneil commented 3 years ago

not that much

From: 夜神之死 @.> Sent: Monday, August 30, 2021 12:20 AM To: fyangneil/pavement-crack-detection @.> Cc: Fan Yang @.>; Comment @.> Subject: Re: [fyangneil/pavement-crack-detection] If I make my own data set with the same format as crack500, what code do I need to modify to work normally? Is there any requirement for the size of the picture? (#28)

Thank you ! Is it necessary to modify the image average?

— You are receiving this because you commented. Reply to this email directly, view it on GitHubhttps://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ffyangneil%2Fpavement-crack-detection%2Fissues%2F28%23issuecomment-908005512&data=04%7C01%7Cfyang%40temple.edu%7C3c558bb49edb4cc63df208d96b6d70ef%7C716e81efb52244738e3110bd02ccf6e5%7C0%7C0%7C637658940077246135%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=cWEoOvAQDyYv1Fj8uCCS%2F9V%2BjUjRamUTkyaN3fh7bN8%3D&reserved=0, or unsubscribehttps://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FALAUWTTC4OWKQXSQAYF75EDT7MBHHANCNFSM5C7MZC5A&data=04%7C01%7Cfyang%40temple.edu%7C3c558bb49edb4cc63df208d96b6d70ef%7C716e81efb52244738e3110bd02ccf6e5%7C0%7C0%7C637658940077246135%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=DxcbDuCHvwE1sDr11U%2FxG2OapnVSw2%2BnFpNX7crOOH4%3D&reserved=0. Triage notifications on the go with GitHub Mobile for iOShttps://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fapps.apple.com%2Fapp%2Fapple-store%2Fid1477376905%3Fct%3Dnotification-email%26mt%3D8%26pt%3D524675&data=04%7C01%7Cfyang%40temple.edu%7C3c558bb49edb4cc63df208d96b6d70ef%7C716e81efb52244738e3110bd02ccf6e5%7C0%7C0%7C637658940077256091%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=rFGhoJNhGvw998fVm3iUiJS4anDvsr35KHTNoBnSa74%3D&reserved=0 or Androidhttps://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fplay.google.com%2Fstore%2Fapps%2Fdetails%3Fid%3Dcom.github.android%26referrer%3Dutm_campaign%253Dnotification-email%2526utm_medium%253Demail%2526utm_source%253Dgithub&data=04%7C01%7Cfyang%40temple.edu%7C3c558bb49edb4cc63df208d96b6d70ef%7C716e81efb52244738e3110bd02ccf6e5%7C0%7C0%7C637658940077256091%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=SDNBjGFtClv2LUw3IPC5enbA8VjuRSQZBWH4%2BFvyIwI%3D&reserved=0.