How to modify a Conv2d to Depthwise Separable Convolution?

6

I believe this answer is a more complete reply to your question.

If groups = nInputPlane, then it is Depthwise. If groups = nInputPlane, kernel=(K, 1), (and before is a Conv2d layer with groups=1 and kernel=(1, K)), then it is separable.

In short, you can achieve it using Conv2d, by setting the groups parameters of your convolutional layers. Hope it helps.

3 Likes