Closed VGANGV closed 12 months ago
Hi, thanks for your interest! I believe this problem comes from the environment but not the data loading part (the message: Loaded data of size: (81, 106, 76, 160) indicates you have loaded the data correctly). Although we may share the same environment config file, there are still some disparities between CUDA versions and sometimes even the hardware arch. The problem simply means the installed PyTorch package has difficulties running the network, so this is probably a problem related to pytorch-CUDA version. Please see this thread of discussions for examples: https://stackoverflow.com/questions/66588715/runtimeerror-cudnn-error-cudnn-status-not-initialized-using-pytorch You may resolve this by installing an appropriate PyTorch package (not the one we specified in the config) wrt your own CUDA version.
Thank you for your reply, Tiange!
Following your advice, I have reinstalled the latest version of pytorch, and successfully completed all three stages.
Thanks again for your patient reply :). I will close this issue.
Hi, thank you for your research. I am very interested in your research, but got the following Error when I tried to train (Stage I).
I created env on a 2080Ti using the .yml file provided in the repo, so the experimental setup is the same as yours. So I suspect something is wrong with my data processing or config file.
I have used the following code to save the Hardi150 data:
and correspondingly updated
dataroot
in lines 17 and 30 inconfig/hardi_150.json
, and keep everything else as it is.Is the way of saving the data and using the config file correct?
I'm a rookie so probably my questions are very foolish.
I would greatly appreciate it if you could respond me.