Two questions on Flux

Specific Domains Machine Learning
21

8 Likes
22

For those still interested in using BFGS (or L-BFGS) to train flux models, I made a small utility package to facilitate this

5 Likes
23

That’s really cool. I’ll try that out later today. :blush:

24

You could define

randomize!(_) = nothing

function randomize!(d::Dense)
    d.W .= randn(Float32, size(d.W))
    d.b .= randn(Float32, size(d.b))
end

function randomize!(c::Chain)
    for l in c.layers
        randomize!(l)
    end
end

and now you can easily reset all your dense layers and chains to random normal distributed parameters, even of nested models like

Chain(x -> [x], Dense(1,2,σ),
    Chain(Dense(2,7,σ), Dense(7,4,σ)),
    Dense(4,1,σ), first)
2 Likes