Skip to content
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.

Sign up for GitHub

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

Jump to bottom

CPU usage when train #31

Open
laisimiao opened this issue Apr 20, 2020 · 2 comments
Open

CPU usage when train #31

laisimiao opened this issue Apr 20, 2020 · 2 comments

Comments

@laisimiao
Copy link

hello, thanks your clean code.
But i found a strange phenomenon that is my cpu usage is very high(almost 100% usage per kernel spied by linux system monitor) so that it run smoothly and stop for a while and continue run...
Have you also experienced this phenomenon when training?What may cause this phenomenon in code?
@laisimiao
Copy link
Author

BTW, its GPU usage is not so tight as cpu usage

@conquerhuang
Copy link

Different from other implementation on Siamese trackers. This demo directly crop trian image in original GOT10K dataset rather than crop the whole dataset before train. So during the train process, there will be a big burden on CPU. I have tried this demo on I7 9700k CPU RTX2080Ti GPU, it will taken 100% usage of CPU while token no more than 5% usage of GPU. If you don't have a powerful CPU and large RAM, I strongly recommend you to crop the training datasets for the first time.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@laisimiao @conquerhuang