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

How to compute the Mult-Adds operations of CSLNL? #25

Open

Vinh-Duong opened this issue Mar 1, 2021 · 0 comments

Vinh-Duong commented Mar 1, 2021

I tried to compute it by using the package from "https://github.com/nmhkahn/torchsummaryX" or "https://github.com/yeluyue/Flops_count_pytorch". But it is not a success. The CSNLN seems to require too much memory overhead.

I guess if only I can using the same 4 GPU V100 GPUs as in the paper I can calculate. But I only have 2 GPU RTX 2080, which makes it impossible.

If it is possible, can you provide the Mult-Adds operations, please?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment