songliVT
commented
2 years ago I suspect that the model file is too large to fit into your GPU memory.
Song
On Mon, Dec 20, 2021 at 10:26 AM oliveirads-bioinfo < @.***> wrote:
I'm really interested in use DeepTE to classify 26 TE libraries, but I'm really naive with ML algorithms and I don't know how to solve the problem with tensorflow. I've installed DeepTE from conda repository and it seems everything is good. The problem is shown below:
[image: deepte-1] https://user-images.githubusercontent.com/15055555/146790488-abe9d383-9bd1-4ba4-9e15-d58d64f4ec86.png
I think the problem happens due to "Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR". Is it happening because I'm out of memory?
I tried to monitor the GPU memory usage and I think it's a memory problem:
[image: deepe-2] https://user-images.githubusercontent.com/15055555/146790908-79a036fb-bcdf-47be-bc39-c1325fc8c4c5.png
The usage drops to zero exactly when DeepTE process is killed.
I have 32 cores and 158Gb RAM, but only 4GB Gb GPU. How can I solve this issue? I did a downsampling and then run DeepTE with only one TE sequence, but it still doesn't work.
— Reply to this email directly, view it on GitHub https://github.com/LiLabAtVT/DeepTE/issues/14, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACEEENQEHMW4ULJKLRCDQODUR5DKNANCNFSM5KN67V3Q . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you are subscribed to this thread.Message ID: @.***>
-- Associate Professor in Plant Genomics and Bioinformatics School of Plant and Environmental Sciences Virginia Polytechnic Institute and State University
I'm really interested in use DeepTE to classify 26 TE libraries, but I'm really naive with ML algorithms and I don't know how to solve the problem with tensorflow. I've installed DeepTE from conda repository and it seems everything is good. The problem is shown below:
I think the problem happens due to "Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR". Is it happening because I'm out of memory?
I tried to monitor the GPU memory usage and I think it's a memory problem:
The usage drops to zero exactly when DeepTE process is killed.
I have 32 cores and 158Gb RAM, but only 4GB Gb GPU. How can I solve this issue? I did a downsampling and then run DeepTE with only one TE sequence, but it still doesn't work.