TastyPancakes
/
Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

improve docstring

This commit is contained in:
CarloLucibello 2020-02-27 20:49:55 +01:00
parent 487002878e
commit 97141e8c98
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/optimise/train.jl
View File

@ -61,7 +61,7 @@ end
For each datapoint `d` in `data` computes the gradient of `loss(d...)` through For each datapoint `d` in `data` computes the gradient of `loss(d...)` through
backpropagation and calls the optimizer `opt`. backpropagation and calls the optimizer `opt`.
In case datapoints `d` are of array type, assumes no splatting is needed In case datapoints `d` are of numeric array type, assumes no splatting is needed
and computes the gradient of `loss(d)`. and computes the gradient of `loss(d)`.
Takes a callback as keyword argument `cb`. For example, this will print "training" Takes a callback as keyword argument `cb`. For example, this will print "training"