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

Merge branch 'master' of github.com:MikeInnes/Flux.jl

Browse Source
This commit is contained in:
Mike J Innes 2017-09-27 21:16:23 +01:00
commit 120a6db2bb
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/src/training/training.md
View File

@ -9,7 +9,7 @@ To actually train a model we need three things:
With these we can call `Flux.train!`: With these we can call `Flux.train!`:
```julia ```julia
Flux.train!(model, data, opt) Flux.train!(modelLoss, data, opt)
``` ```
There are plenty of examples in the [model zoo](https://github.com/FluxML/model-zoo). There are plenty of examples in the [model zoo](https://github.com/FluxML/model-zoo).

4
src/optimise/train.jl
View File

@ -8,8 +8,8 @@ function train!(m, data, opt; cb = () -> ())
cb = tocb(cb) cb = tocb(cb)
@progress for x in data @progress for x in data
l = m(x...) l = m(x...)
isinf(l.data[]) && error("Inf") isinf(l.data[]) && error("Loss is Inf")
isnan(l.data[]) && error("NaN") isnan(l.data[]) && error("Loss is NaN")
back!(l) back!(l)
opt() opt()
cb() cb()