Closed radenmuaz closed 5 years ago
https://arxiv.org/pdf/1708.06519.pdf How do you calculate table 1 FLOPs?
I use https://github.com/Lyken17/pytorch-OpCounter to calculate baseline vggnet (vgg-19) flops, I got 399718400.0
However Network Slimming paper says 7.97×10e8 -- almost double the flops
If I apply this flops counter to vgg-16, I got matching result with layerwise flops from L1 Pruning ConvNet paper https://arxiv.org/abs/1608.08710
I found the solution, the function multiply_adds is set to True, so flops is doubled.
https://arxiv.org/pdf/1708.06519.pdf How do you calculate table 1 FLOPs?
I use https://github.com/Lyken17/pytorch-OpCounter to calculate baseline vggnet (vgg-19) flops, I got 399718400.0
However Network Slimming paper says 7.97×10e8 -- almost double the flops
If I apply this flops counter to vgg-16, I got matching result with layerwise flops from L1 Pruning ConvNet paper https://arxiv.org/abs/1608.08710