aimerykong / Recurrent-Scene-Parsing-with-Perspective-Understanding-in-the-loop

CVPR2018 - scene parsing network regulated by geometric prior
https://www.cs.cmu.edu/~shuk/recurrentDepthSeg.html
37 stars 7 forks source link

run train_Cityscapes.m error,help,thanks #6

Closed xjlnuc closed 7 years ago

xjlnuc commented 7 years ago

Hi Shu Kong: 1.when I run the demo_cityscapes、train_Cityscapes.m、demo_NYUv2.m and train_NYUv2.m,thers is the same error, I have compile the gpu version of matconvnet.so I don't know what happend, help me, thanks. error is: 错误使用 gpuDevice (line 26) Invalid CUDA device id: 2(or 3). Select a device id from the range 1:1. 出错 train_Cityscapes (line 25) gpuDevice(gpuId); 2.I have another questions,if i must donwload [google drive] and where should i download the NYUv2 dataset、Cityscapes dataset? That’s all,thank you!

aimerykong commented 7 years ago

Hi, it seems that you use the wrong GPU? Try gpuDevice(1) if you only have one gpu?

For datasets, you can search NYUv2 and cityscapes and go to their website to download. Each dataset has its own instruction, so it's better for you to go through them.

Hope this helps!

On Fri, Aug 18, 2017 at 7:19 PM, xjlnuc notifications@github.com wrote:

Hi Shu Kong: 1.when I run the demo_cityscapes、train_Cityscapes.m、demo_NYUv2.m and train_NYUv2.m,thers is the same error, I have compile the gpu version of matconvnet.so I don't know what happend, help me, thanks. error is: 错误使用 gpuDevice (line 26) Invalid CUDA device id: 2(or 3). Select a device id from the range 1:1. 出错 train_Cityscapes (line 25) gpuDevice(gpuId); 2.I have another questions,if i must donwload [google drive] and where should i download the NYUv2 dataset、Cityscapes dataset? That’s all,thank you!

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/aimerykong/Recurrent-Scene-Parsing-with-Perspective-Understanding-in-the-loop/issues/6, or mute the thread https://github.com/notifications/unsubscribe-auth/AGKZJBuQjtDO8xd6V9jOEgDdkYboLKY-ks5sZkYhgaJpZM4O8Mgc .