A container for applying a single module to all table elements

This module can be useful when dealing with multi-dimensional mini-batches, for
example when training recurrent neural networks (time X batch_size X elements).
It simply clones the contained module as necessary and applies each clone to the
respective input element.

1 files changed, 1 insertions, 0 deletions

diff --git a/init.lua b/init.lua
index a9c68da..e5bafac 100644
--- a/init.lua
+++ b/init.lua
@@ -142,6 +142,7 @@ require('nn.MixtureTable')
 require('nn.CriterionTable')
 require('nn.FlattenTable')
 require('nn.NarrowTable')
+require('nn.MapTable')
 
 require('nn.Criterion')
 require('nn.MSECriterion')