-
Notifications
You must be signed in to change notification settings - Fork 232
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
update torch problem occured #16
Comments
Did you update CUDNN to 5.1 also? You can try disabling the cudnn optimization. Change the flag cudnn.benchmark=True in main.lua to False and see if that fixes the problem. cudnn.benchmark true is why FindConvolutionForwardAlgorithm is being called. I had similar problem and I think it is a memory issue. |
Thank you for your reply! Finally I found this problem occurs because someone upgrade the cudnn to 5.0 on server. I fixed this problem by add dependencies in my home directory |
@zhFuECL Hi, I am also working on this code for image dense matching. Can we talk about it a little bit? Here is my QQ: 1376519063 |
After update my torch use ./update.sh, I run the command below, and got the following error:
th ./main.lua mb slow -a predict -net_fname net/net_mb_slow_-a_train_all.t7 -left ../data/md/2005_2006/Wood2/view1.png -right ../data/md/2005_2006/Wood2/view5.png -disp_max 70
The text was updated successfully, but these errors were encountered: