You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Apr 9, 2023. It is now read-only.
I tried to find a way to use the GPU without modifying the code and since I notice that you have utilized the tensorflow 1.* version for TFDeepSurv. I have done the following:
install the TensorFlow 1.15-GPU version using pip3 install tensorflow-gpu==1.15
run the TFDeepSurv code under TensorFlow 1.15-GPU using my GPU[0]
I notice that the percentage of GPU utilization is in the range of 0%~3%
[0] TITAN RTX | 60'C,3 % | 23216 / 24217 MB |
I am not sure if this actually uses the GPU or not. I think it uses since I can see the temperature of GPU raise and the percentage is not always 0%. But on the other hand, I am not sure why the GPU utilization is low.
Could you please advise if I did the right thing? Thank you!
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
@liupei101 Thank you so much for the package.
Could you please advise is it possible to use GPU support for this TFDeepSurv package?
Thank you!
The text was updated successfully, but these errors were encountered: