Let's say i want to perform a non-learnable nearest neighbor downsampling on the input tensor.
nnDownSample2D(factor, inputLayer)
Specifically, I only want to keep the topleft corner
1 0 .. 0 0 0 .. 0 ... 0 0 .. 0
how do i achieve this in keras?
2.1m questions
2.1m answers
60 comments
57.0k users