Update GRU.lua

Added oneHot encoding and softmax

model/GRU.lua

@@ -5,8 +5,8 @@ local GRU = {}
 Creates one timestep of one GRU
 Paper reference: http://arxiv.org/pdf/1412.3555v1.pdf
 ]]--
-function GRU.gru(input_size, rnn_size, n)
-
+function GRU.gru(input_size, rnn_size, n, dropout)
+  dropout = dropout or 0 
   -- there are n+1 inputs (hiddens on each layer and x)
   local inputs = {}
   table.insert(inputs, nn.Identity()()) -- x
@@ -25,9 +25,15 @@ function GRU.gru(input_size, rnn_size, n)
   for L = 1,n do
 
     local prev_h = inputs[L+1]
-    if L == 1 then x = inputs[1] else x = outputs[L-1] end
-    if L == 1 then input_size_L = input_size else input_size_L = rnn_size end
-
+    -- the input to this layer
+    if L == 1 then 
+      x = OneHot(input_size)(inputs[1])
+      input_size_L = input_size
+    else 
+      x = outputs[(L-1)] 
+      if dropout > 0 then x = nn.Dropout(dropout)(x) end -- apply dropout, if any
+      input_size_L = rnn_size
+    end
     -- GRU tick
     -- forward the update and reset gates
     local update_gate = nn.Sigmoid()(new_input_sum(input_size_L, x, prev_h))
@@ -44,9 +50,14 @@ function GRU.gru(input_size, rnn_size, n)
 
     table.insert(outputs, next_h)
   end
+-- set up the decoder
+  local top_h = outputs[#outputs]
+  if dropout > 0 then top_h = nn.Dropout(dropout)(top_h) end
+  local proj = nn.Linear(rnn_size, input_size)(top_h)
+  local logsoft = nn.LogSoftMax()(proj)
+  table.insert(outputs, logsoft)
 
   return nn.gModule(inputs, outputs)
 end
 
 return GRU
-