Relax! Flux is the ML library that doesn't make you tensor
Go to file
Fredrik Bagge Carlson 8991ce028c
Fix bug in rmsprop and adadelta
`@. p.Δ = η * p.Δ / √acc` parses correctly while `@. p.Δ /= √acc*η` seems to parse like `@. p.Δ /= (√acc*η)`, hence the step size was de facto interpreted as `1/η`
2017-11-14 17:32:16 +01:00
docs Merge pull request #92 from CarloLucibello/drop 2017-10-26 12:07:28 +01:00
src Fix bug in rmsprop and adadelta 2017-11-14 17:32:16 +01:00
test test tweaks 2017-11-08 22:18:45 +00:00
.gitignore add cmudict dataset 2017-11-01 16:01:55 +00:00
.travis.yml don't need this 2017-10-18 10:22:35 +01:00
LICENSE.md Flux.jl generated files. 2016-03-22 19:58:58 +00:00
README.md move 2017-09-11 14:56:35 +01:00
REQUIRE update dataflow bounds 2017-09-07 01:21:41 -04:00

Флукс

Build Status Join the chat at https://gitter.im/FluxML Slack

Flux is a refreshing approach to machine learning. It provides lightweight abstractions on top of Julia's native GPU and AD support, while remaining fully hackable (right down to the GPU kernels).

julia> Pkg.add("Flux")

See the documentation or the model zoo for examples.