Conv2d/conv3d at only selected pixel locations

Is it possible to perform convolution operation in pytorch at specific locations (list of pixel location probably fed by the user or collected from other algorithm) rather than at locations predetermined by the stride?

I am not sure if it is possible yet. As a naive solution (assuming that computation is not a bottleneck), why can’t you multiply the conv output with a mask that specifies 1 in the locations selected by user or other algorithms?

The main goal is to avoid unnecessary computations, make algorithm memory friendly and speed up the process. Assume you have a bunch of points in 3D space and you want to operate convolution with nxnxn filter at those points but not in grid locations where there are no points.

Thanks for your reply.

I found the solution.