How does Flux.Conv work?

New to Julia
,
7

@ToucheSir thanks for the reply. I actually attempted porting convolution weights from Flux to PyTorch, using PyCall. PyReverseDims function converts the column major Julia array to a PyTorch-compatible row major array and reverses the ordering of dims. Keeping that in mind, this operation passed all my tests for porting the Conv.weight attribute:

l = Conv((1, 5), 1 => 1, Flux.sigmoid)
w_julia = l.weight
w_torch = PyReverseDims(permutedims(reverse(w_julia, dims=(1,2)), (2, 1, 3, 4)))

and for the bias:

b_julia = l.bias
b_torch = PyReverseDims(b_julia)
1 Like