X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=dagnn.lua;h=0e7e8b0364ffb2b13a6319c9d3ee13c519892b17;hb=79f9b2fc425c35c82e07db9cb762c2b04a992bdb;hp=0c1d15303f42ce6e8ad439b787bffe29664511c3;hpb=e50d9b4373f39161df34afb1033c89910963fa47;p=dagnn.git

diff --git a/dagnn.lua b/dagnn.lua
index 0c1d153..0e7e8b0 100755
--- 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
@@ -86,20 +86,37 @@ function DAG:putInOrder()
    for i, a in ipairs(self.sorted) do self.sorted[i] = a.nnm end
 end
 
-function DAG:computeGradOutput(gradInputSucc)
-   local gi
+-- 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
-      gi = gradInputSucc[1] -- we avoid a clone()
+      node.gradOutput = gradInputSucc[1]
    elseif #gradInputSucc > 1 then
       for k = 1, #gradInputSucc do
-         if gi then
-            gi:add(gradInputSucc[k])
-         else
-            gi = gradInputSucc[k]:clone()
-         end
+         node.gradOutput = self:nestedAccTensor(node.gradOutput, gradInputSucc[k], k == 1)
       end
    end
-   return gi
 end
 
 ----------------------------------------------------------------------
@@ -206,7 +223,6 @@ function DAG:updateOutput(input)
    self:nestedApply(
       function(nnm, i)
          self.node[nnm].input = i
-         -- nnm:updateOutput(i)
          self:rethrowErrors(nnm, self.node[nnm].index, 'updateOutput', i)
       end,
       self.inputModules,
@@ -226,7 +242,6 @@ function DAG:updateOutput(input)
             end
          end
          node.input = i
-         -- nnm:updateOutput(i)
          self:rethrowErrors(nnm, self.node[nnm].index, 'updateOutput', i)
       end
    end
@@ -246,7 +261,6 @@ function DAG:updateGradInput(input, gradOutput)
       function(nnm, go)
          local node = self.node[nnm]
          node.gradOutput = go
-         -- nnm:updateGradInput(self.node[nnm].input, go)
          self:rethrowErrors(nnm, node.index, 'updateGradInput', self.node[nnm].input, go)
       end,
       self.outputModules, gradOutput
@@ -264,11 +278,10 @@ function DAG:updateGradInput(input, gradOutput)
    for k = #self.sorted, 1, -1 do
       local nnm = self.sorted[k]
       local node = self.node[nnm]
-      local pred, gradInputSucc = node.pred, node.gradInputSucc
+      local pred = node.pred
 
-      if #gradInputSucc > 0 then
-         node.gradOutput = self:computeGradOutput(gradInputSucc)
-         -- nnm:updateGradInput(node.input, node.gradOutput)
+      if #node.gradInputSucc > 0 then
+         self:updateGradOutput(node)
          self:rethrowErrors(nnm, self.node[nnm].index, 'updateGradInput', node.input, node.gradOutput)
       end
 
@@ -308,7 +321,16 @@ function DAG:accGradParameters(input, gradOutput, scale)
    for k = 1, #self.modules do
       local nnm = self.modules[k]
       local node = self.node[nnm]
-      -- nnm:accGradParameters(node.input, node.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