calculation of AvgPooling about pytorch-opcounter HOT 5 CLOSED

I think you suggestion is correct. In total there are H_out * W_out * out_channels pixels and each pixel takes ** in_channels * (kernel_size * kernel_size - 1) ** operations.

For MACs and FLOPs, it is not simple 2 times calculation. In short, it depends how you count the multiplication for floating numbers. I will refactor the codebase to fix the issue.

from pytorch-opcounter.

Thank you! Will you please let me know as soon as you fixed the code, so that I can update the python package?

from pytorch-opcounter.

After talking to an expert in hardware, I made a clarification of MACs and FLOPs. For AVGPooling, the updated MAC should be H_out * W_out * out_channels. If you agree with it, I will update the corresponding code recently.

from pytorch-opcounter.

@fortunex3000 any comments?

from pytorch-opcounter.

After talking to an expert in hardware, I made a clarification of MACs and FLOPs. For AVGPooling, the updated MAC should be H_out * W_out * out_channels. If you agree with it, I will update the corresponding code recently.

But if you do this, it is different from the statistical method of TensorFlow and the user’s conventional perception

from pytorch-opcounter.