What is, and where to get, dispnorm_occ for Kitti 2015?

Question

What is, and where to get, dispnorm_occ for Kitti 2015?

andrewlstewart opened this issue 3 years ago · comments

I downloaded the stereo 2015/flow 2015/scene flow 2015 data set (2 GB) but I don't see any subfolder with the name 'dispnorm_occ'. Without it, I can't call disparity.KITTIloader2015.dataloader to actually train the StereoNet model. Can you help me find it or explain how to generate it?

Thanks!

Yaoxingtian · Answer 1 · Wed Nov 24 2021 17:50:34 GMT+0800 (China Standard Time)

I downloaded the stereo 2015/flow 2015/scene flow 2015 data set (2 GB) but I don't see any subfolder with the name 'dispnorm_occ'. Without it, I can't call disparity.KITTIloader2015.dataloader to actually train the StereoNet model. Can you help me find it or explain how to generate it?

Thanks!

Hi , do you solve this problem ? I meet this problem to .
Could you kindly share info if you know how to do ? thanks much !

Andrew Stewart · Answer 2 · Wed Nov 24 2021 23:43:19 GMT+0800 (China Standard Time)

@Yaoxingtian I found this to be a somewhat broken repo. I wasn't able to find the dispnorm_occ files. I originally came here looking for a StereoNet implementation but couldn't get their implementation working. I implemented the StereoNet framework here: github.com/andrewlstewart/StereoNet_PyTorch

Hope that helps

Yaoxingtian · Answer 3 · Sat Nov 27 2021 16:29:22 GMT+0800 (China Standard Time)

yes, I thinks so , this is a half-done work. they didnot open all source code . 发送自 Outlook<http://aka.ms/weboutlook>

…

________________________________ 发件人: Andrew Stewart ***@***.***> 发送时间: 2021年11月24日 15:43 收件人: meteorshowers/X-StereoLab ***@***.***> 抄送: Yaoxingtian ***@***.***>; Mention ***@***.***> 主题: Re: [meteorshowers/X-StereoLab] What is, and where to get, dispnorm_occ for Kitti 2015? (#36) @Yaoxingtian<https://github.com/Yaoxingtian> I found this to be a somewhat broken repo. I wasn't able to find the dispnorm_occ files. I originally came here looking for a StereoNet implementation but couldn't get their implementation working. I implemented the StereoNet framework here: github.com/andrewlstewart/StereoNet_PyTorch Hope that helps ― You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<#36 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AFCSU4U5FPLVWTOENCYSE6DUNUB2DANCNFSM5ABXJWZQ>.