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

gpu memory used by tensorrt #153

Open
andyqian2015 opened this issue Nov 13, 2019 · 5 comments
Open

gpu memory used by tensorrt #153

andyqian2015 opened this issue Nov 13, 2019 · 5 comments

Comments

@andyqian2015
Copy link

when I convert of the example of resnet, I find that the gpu memory used by trt model of fp32 is bigger than the pytorch model, and when I test the fp16 model of trt , the memort is just the same as the fp32 model, which puzzle me.
@andyqian2015
Copy link
Author

wish to get your reply soon

@kawashima1129
Copy link

Did you find the answer to this?

@amirassov
Copy link

@andyqian2015 @kawashima1129 Did you find the answer to this?

@czs1886
Copy link

czs1886 commented Jul 27, 2020 •
edited
Loading

What models are you guys using?

@gioipv
Copy link

gioipv commented Aug 4, 2021 •
edited
Loading

Hello @andyqian2015
I converted mobilenetV3. and I met this issues.
do u find the answer for your question yet ?

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
5 participants
@andyqian2015 @amirassov @kawashima1129 @czs1886 @gioipv