Closed peterzpy closed 3 years ago
It is because the involution kernels are shared across channels and generated by 1x1 convolution (or say linear transformation). Anyway, you could practically calculate the FLOPs of our provided network architecture.
This is an interesting work, but I wonder why the FLOPs of RedNet are less than the ResNet when using the same number of layers. It seems that comparing with ResNet, RedNet will additionally generate the involution weights, then slide through the feature map just like convolution operation.