search

JiahuiYu / slimmable_networks

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
Other
914 stars 131 forks source link

model profiling #37

Closed lyn0102 closed 4 years ago

lyn0102 commented 4 years ago

Hello! I compared the results of statistical FLOPs and parameters in your code with the results in the thop tool, and found that there are some differences. I guess the reason is that you did not count the FLOPs and parameters of the bn layer? Looking forward to your answer, thank you!

JiahuiYu commented 4 years ago

I think all papers do not include BN as they can be fused during inference.

lyn0102 commented 4 years ago

Thank you for your reply :D

abhishekaich27 commented 2 years ago

Hi @JiahuiYu, are you calculating MACs or Flops? The code says "n_macs".

Asking to be sure and make necessary changes.