Different result with Tensorflow about pytorch-opcounter HOT 4 OPEN

I found the reason.
In thop, the count_convNd has an error that it estimate MAC ops but not FLOPs for convolution operation.

...
  total_ops = y.nelement() * (m.in_channels // m.groups * kernel_ops + bias_ops)
...

In convolution operation, we cut input data into many slices, multiply kernel coefficient with them, then add them into one. So we can modify the code like this:

...
  total_ops = y.nelement() * (m.in_channels // m.groups * kernel_ops * 2 + bias_ops)
...

Result:

Tensorflow: 38612737
Torch: 38610432.0

from pytorch-opcounter.

You are right. I will soon push a patch to fix it.

from pytorch-opcounter.

Can this be merged?

from pytorch-opcounter.

Is there a mistake here about ConV2D?
bias_ops = 1 if m.bias is not None else 0
I think, bias_ops should be 0 if bias exists, otherwise -1.

from pytorch-opcounter.