LIN YI
LIN YI
> I have same problem, cuda version 10.1 torch version 1.7.1 hardware amd R7-5800h RTX 3060 i tried to run CLIPasso at my computer with ubuntu 22.04 sorry about the...
> I am also running the CLIPasso project on Ubuntu 18.04 with cuda version 11.3 and torch version 1.11 Just solved this problem using the solution from @yuchen-xiyue. Thanks a...
I think caching the data returned from prepare_data() to disk refer to saving these huge extracted pixel representations to files in some specified format (e.g. .npy file) on your disk....
> in CIFAR10 @dongzhuoyao Hi, I encountered the same issue with ImageNet (input size 224*224). Have you found an appropriate #GS value to reduce the noise in CIFAR10?
> You can try to i) reduce the number of training images ii) reduce feature dimensionality iii) store features on the disk and preprocess them by batches. Hi, thanks for...
Hi, I met the same problem, have you solved it yet? Thanks!!
> In my case, there were some issues with cmake. I got some warnings, and I focused on solving them first. Once I fixed all warnings, the library got installed...
> If you are getting the same exact error, then their might be a warning just above the Trace Stack. On time it was regarding nvidia cuda toolkit incompatibility, so...