Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Native Softmax #175

Closed
MikeInnes opened this issue Jan 10, 2018 · 2 comments
Closed

Native Softmax #175

MikeInnes opened this issue Jan 10, 2018 · 2 comments
Labels
cuda array Stuff about CuArray. enhancement New feature or request

Comments

@MikeInnes
Copy link
Contributor

Can be based on PyTorch's.

The API should be equivalent to:

function softmax(x::AbstractArray, axis=1)
    out = exp.(x .- maximum(x, axis))
    out ./= sum(out, axis)
    return out
end
@maleadt
Copy link
Member

maleadt commented Feb 12, 2019

https://gist.github.com/jekbradbury/becd9fff1c469dc73cb57f73d1f2a439

@maleadt maleadt transferred this issue from JuliaGPU/CuArrays.jl May 27, 2020
@maleadt maleadt added cuda array Stuff about CuArray. enhancement New feature or request labels May 27, 2020
@CarloLucibello CarloLucibello mentioned this issue Jun 17, 2020
Closed
@maleadt
Copy link
Member

maleadt commented Apr 27, 2024

This is something for NNlib.jl.

@maleadt maleadt closed this as not planned Won't fix, can't repro, duplicate, stale Apr 27, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
cuda array Stuff about CuArray. enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@maleadt @MikeInnes