Hi, I wonder if I can implement a convolution layer that uses different parameterization for each location. It might be called a locally connected layer instead of a fully connected one.
Is there any way to implement it?
Thanks,
Paul
Hi, I wonder if I can implement a convolution layer that uses different parameterization for each location. It might be called a locally connected layer instead of a fully connected one.
Is there any way to implement it?
Thanks,
Paul
It’s dearly missed, but can be hacked together… I’m not sure on the most efficient way though, I’ve seen several “solutions” to this.
For example, I use this method straight from the backend:
arguments: input, weight, bias, kH, kW, strideH, strideW, padH, padW, inH, inW, outH, outW
conv2Dlocal = torch.nn.backends.thnn.backend.SpatialConvolutionLocal.apply
I find it strange there is still no supported solution for this (should easily be in the functional sub-lib at least).