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.

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

Is there a script for calculating FLOPs of MSDNet? #5

Open
jh-jeong opened this issue Feb 6, 2018 · 2 comments
Open

Is there a script for calculating FLOPs of MSDNet? #5

jh-jeong opened this issue Feb 6, 2018 · 2 comments

Comments

@jh-jeong
Copy link

jh-jeong commented Feb 6, 2018

Hi, I wonder if there's any code snippet to calculate FLOPs of each classifier in a given MSDNet.
If so, could you share it please?
Thanks.

@taineleau-zz
Copy link
Collaborator

Hi,
sorry for the late reply. You may use https://github.com/apaszke/torch-opCounter to calculate the FLOPs of any Lua torch network.

@kazulittlefox
Copy link

I have tried to run the snippet above to calculate MSDNet computational cost, but failed
(maybe) because of lack of implementing definition of custom layer or manupilation, like train_joint module .

Anyone else trying running it? And would you like to show how to solve the problem?

Thanks in advance.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants