Skip to content

Commit

Permalink
add a sentence comparing to freeze/thaw
Browse files Browse the repository at this point in the history
  • Loading branch information
mcabbott committed Mar 6, 2024
1 parent 37798ca commit feaa5ff
Showing 1 changed file with 3 additions and 0 deletions.
3 changes: 3 additions & 0 deletions docs/src/training/training.md
Original file line number Diff line number Diff line change
Expand Up @@ -384,6 +384,9 @@ Flux.thaw!(opt_state)
The earlier "implicit" equivalent was to pass to `gradient` an object referencing only
part of the model, such as `Flux.params(bimodel.layers.enc)`.

While `adjust!` and `freeze!`/`thaw!` make temporary modifications to the optimiser state,
permanently removing some fields of a new layer type from training is usually done
when defining the layer, by calling for example [`@layer`](@ref Flux.@layer)` NewLayer trainable=(weight,)`.

## Implicit or Explicit?

Expand Down

0 comments on commit feaa5ff

Please sign in to comment.