Now deals when a module whose input is a table has multiple successors.

diff --git a/dagnn.lua b/dagnn.lua
index de9d29b..0e7e8b0 100755 (executable)
--- a/dagnn.lua
+++ b/dagnn.lua
@@ -26,7 +26,7 @@ local DAG, parent = torch.class('nn.DAG', 'nn.Container')
 function DAG:__init()
    parent.__init(self)
    -- Nodes are indexed by the module they contain
-   self.node = { }
+   self.node = {}
 end
 
 -- Apply f on t recursively; use the corresponding elements from args
@@ -76,7 +76,7 @@ function DAG:putInOrder()
       end
    until nc == 0
 
-   self.sorted = { }
+   self.sorted = {}
    for m, d in pairs(distance) do
       table.insert(self.sorted, { distance = d, nnm = m })
    end
@@ -86,18 +86,35 @@ function DAG:putInOrder()
    for i, a in ipairs(self.sorted) do self.sorted[i] = a.nnm end
 end
 
+-- This accumulate x in a where they are both nested tables of
+-- tensors. If first is true, set a = x.
+function DAG:nestedAccTensor(a, x, first)
+   if torch.type(x) == 'table' then
+      a = a or {}
+      for i in pairs(x) do
+         a[i] = self:nestedAccTensor(a[i], x[i], first)
+      end
+   else
+      if first then
+         if a then
+            a:resizeAs(x):copy(x)
+         else
+            a = x:clone()
+         end
+      else
+         a:add(x)
+      end
+   end
+   return a
+end
+
 function DAG:updateGradOutput(node)
    local gradInputSucc = node.gradInputSucc
    if #gradInputSucc == 1 then
       node.gradOutput = gradInputSucc[1]
    elseif #gradInputSucc > 1 then
-      if node.gradOutput then
-         node.gradOutput:resize(gradInputSucc[1]):copy(gradInputSucc[1])
-      else
-         node.gradOutput = gradInputSucc[1]:clone()
-      end
-      for k = 2, #gradInputSucc do
-         node.gradOutput:add(gradInputSucc[k])
+      for k = 1, #gradInputSucc do
+         node.gradOutput = self:nestedAccTensor(node.gradOutput, gradInputSucc[k], k == 1)
       end
    end
 end
@@ -307,3 +324,13 @@ function DAG:accGradParameters(input, gradOutput, scale)
       self:rethrowErrors(nnm, k, 'accGradParameters', node.input, node.gradOutput, scale)
    end
 end
+
+function DAG:clearState()
+   self.sorted = nil
+   for _, node in pairs(self.node) do
+      node.gradInputSucc = nil
+      node.input = nil
+      node.gradOutput = nil
+   end
+   return parent.clearState(self)
+end