Open torfjelde opened 4 years ago
But the problem is ReverseDiff uses similar
to allocate for the gradient wrt to the input and similar(sprand(10, 10, 1.0)')
gives an empty sparse array. This is probably a bug in SparseArrays.jl.
similar(sprand(10, 10, 1.0))
gives the expected output.
Ran into the following issue:
Ran into similar issues with Tracker.jl a good while back and this PR fixed those issues: https://github.com/FluxML/Tracker.jl/pull/37. Related?