binary_focal_loss(ŷ, y; agg=mean, γ=2, ϵ=eps(ŷ))

Return the binary_focal_loss The input, 'ŷ', is expected to be normalized (i.e. [softmax]( Softmax) output).

For γ == 0, the loss is mathematically equivalent to Losses.binarycrossentropy.

See also: Losses.focal_loss for multi-class setting

Example

			julia> y = [0  1  0
            1  0  1]
2×3 Matrix{Int64}:
 0  1  0
 1  0  1

julia> ŷ = [0.268941  0.5  0.268941
            0.731059  0.5  0.731059]
2×3 Matrix{Float64}:
 0.268941  0.5  0.268941
 0.731059  0.5  0.731059

julia> Flux.binary_focal_loss(ŷ, y) ≈ 0.0728675615927385
true