Closed eugenelawrence closed 5 years ago
@eugenelawrence Thanks for your attention. In the paper, we calculate the floating point operations (FLOPs) of the RCCA module rather than the whole network. We follow this paper to calculate FLOPs. The Input size of CCNet is 1x3x769x769, the input feature maps of RCCA has shape 1x512x97x97 (after channel reduction). Three 1x1 convolutions: 2x97x97x(512+1)x64 + 2x97x97x(512+1)x64 + 2x97x97x(512+1)x512 Affinty: 2x97x97x(97+97)x64 Aggregation: 2x97x97x(97+97)x512 Besides, the softmax and add are operations with light weight calculation. Finally, the FLOPs are about 8 x 10^9.
@speedinghzl Hi, thank you for sharing this project. In your paper, you also compare the FLOPs of CCNet with nonlocal, you report the FLOPs of nonlocal is 108G, can you tell me what is the input size of nonlocal in your experiment, do you reduce the number of channels by conv g
,theta
or phi
, or use subsampling tricks?
@zhangpj The input size of nonlocal is also 1x512x97x97. To make a fair comparison, I did reduce the number of channels and did not use a subsampling trick, which shared the same settings with RCCA.
@speedinghzl All right, thank you.
Nice Work! Can you provide the code or details about how to calculate the flops of the CCNet?