Replies: 1 comment
-
I chekced vram usage via task manager and the usage is not increase once load the model. Is that right? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I'm thinking of the service has sevral yolo models and user can switch between them.
So, I searched the way to achieve that.
Some of people suggested me to have just sevral models in runtime.
But, here's the catch.
Once you load the model, it takes place in your memory.
If you load certain amount of these, program raises cuda out of memeory expection.
So, is there any way to unload the model from the memeory in runtime?
Beta Was this translation helpful? Give feedback.
All reactions