Closed lzrvch closed 3 years ago
Seems like you add bias addition ops to the total FLOPs count for convolutional and RNN modules, but it looks like it is not the case for linear layers. Is that something to be addressed?
Hi! That's a bug indeed. Thanks for catching it.
Seems like you add bias addition ops to the total FLOPs count for convolutional and RNN modules, but it looks like it is not the case for linear layers. Is that something to be addressed?