search

DrSleep / light-weight-refinenet

Light-Weight RefineNet for Real-Time Semantic Segmentation
Other
734 stars 163 forks source link

How to calculate the 'FLOPS' of the given model? #7

Closed wangq95 closed 5 years ago

wangq95 commented 5 years ago

Hi, in this paper, you compare the 'FLOPs' of different models, but I am confused about that how to get the value of one models' FLOPs', is to use some scripts or what? Thank you very much.

DrSleep commented 5 years ago

Hi, for other models, I am using the numbers reported by their papers. For our models, I have adapted this code: https://github.com/ShichenLiu/CondenseNet/blob/master/utils.py

On Thu, 18 Oct 2018 at 20:04, Guqiansheng notifications@github.com wrote:

Hi, in this paper, you compare the 'FLOPs' of different models, but I am confused about that how to get the value of one models' FLOPs', is to use some scripts or what? Thank you very much.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/DrSleep/light-weight-refinenet/issues/7, or mute the thread https://github.com/notifications/unsubscribe-auth/AHemmBE9hp7dIUq6lAY0emqBxFRUCvj5ks5umEs1gaJpZM4XtClh .