How did you get the FLOPs of your models?

XiaLiPKU / EMANet

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

https://xialipku.github.io/publication/expectation-maximization-attention-networks-for-semantic-segmentation/

GNU General Public License v3.0

680 stars 130 forks source link

How did you get the FLOPs of your models? #16

Closed hanhuili closed 4 years ago

hanhuili commented 4 years ago

I have tried tools like thop (https://github.com/Lyken17/pytorch-OpCounter) yet the results are significantly different from yours. So could you please explain how did you calcualte FLOPs in details?

XiaLiPKU commented 4 years ago

I use torchsummary for other parts. And for EMAU, I have to compute by myself.