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

optimiser state

Browse Source
This commit is contained in:
Mike Innes 2018-03-06 09:41:06 +00:00
parent 7fe8308831
commit eab26be0af
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/src/saving.md
View File

@ -108,3 +108,11 @@ revert to an older copy of the model if it starts to overfit.
```julia ```julia
@save "model-$(now()).bson" model loss = testloss() @save "model-$(now()).bson" model loss = testloss()
``` ```
You can even store optimiser state alongside the model, to resume training
exactly where you left off.
```julia
opt = ADAM(params(model))
@save "model-$(now()).bson" model opt
```