diff options
author | Nicholas Léonard <nick@nikopia.org> | 2014-07-09 23:50:02 +0400 |
---|---|---|
committer | Nicholas Léonard <nick@nikopia.org> | 2014-07-09 23:50:02 +0400 |
commit | 2186853a8343621a5a7f5bda7d7c76240d1e69aa (patch) | |
tree | f60f258c9e99291d1829ae948fd7d505e68d9a7c | |
parent | eb074947c027e8a11f9a94acb1f4a0c5b0e1330c (diff) |
added Module:training/evaluate to module.md
-rw-r--r-- | doc/module.md | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/doc/module.md b/doc/module.md index c8bf501..273fec2 100644 --- a/doc/module.md +++ b/doc/module.md @@ -274,3 +274,11 @@ Custom modules should not override this function. They should instead override [ This function will go over all the weights and gradWeights and make them view into a single tensor (one for weights and one for gradWeights). Since the storage of every weight and gradWeight is changed, this function should be called only once on a given network. +<a name="nn.Module.training"/> +### training() ### +This sets the mode of the Module (or sub-modules) to `train=true`. This is useful for modules like [Dropout](simple.md#nn.Dropout) that have a different behaviour during training vs evaluation. + +<a name="nn.Module.evaluate"/> +### evaluate() ### +This sets the mode of the Module (or sub-modules) to `train=false`. This is useful for modules like [Dropout](simple.md#nn.Dropout) that have a different behaviour during training vs evaluation. + |