Added the detection of cycles + cosmetics.

diff --git a/dagnn.lua b/dagnn.lua
index cf45233..1f45b2a 100755 (executable)
--- a/dagnn.lua
+++ b/dagnn.lua
@@ -61,9 +61,13 @@ function DAG:putInOrder()
    end
 
    local distance = {}
-   self:nestedApply(function(m) distance[m] = 1 end, self.inputModules)
+   self:nestedApply(
+      function(m) distance[m] = 1 end,
+      self.inputModules
+   )
 
    local nc
+   local nl = 0
    repeat
       nc = 0
       for nnma, node in pairs(self.node) do
@@ -74,6 +78,8 @@ function DAG:putInOrder()
             end
          end
       end
+      assert(nl < #self.modules, 'Cycle detected in the graph.')
+      nl = nl + 1
    until nc == 0
 
    for _, nnm in pairs(self.modules) do
@@ -90,9 +96,10 @@ function DAG:putInOrder()
    for i, a in ipairs(self.sorted) do self.sorted[i] = a.nnm end
 end
 
--- This accumulates x in a where they are both nested tables of
--- tensors. If first is true, set a = x. Behavior is undefined if a
--- and x do not have the exact same structure.
+-- This accumulates x in a, where they are both nested tables of
+-- tensors with same structures / keys. If first is true, set a = x
+-- (in which case a can be nil) otherwise a = a + x. The behavior is
+-- undefined if a and x do not have the exact same structure.
 function DAG:nestedAccTensor(a, x, first)
    if torch.type(x) == 'table' then
       local b = {}
@@ -230,14 +237,15 @@ function DAG:updateOutput(input)
 
    for _, nnm in ipairs(self.sorted) do
       local node = self.node[nnm]
-      if #node.pred > 0 then
+      local pred = node.pred
+      if #pred > 0 then
          local i
-         if #node.pred == 1 then
-            i = node.pred[1].output
-         elseif #node.pred > 1 then
+         if #pred == 1 then
+            i = pred[1].output
+         elseif #pred > 1 then
             i = {}
-            for k = 1, #node.pred do
-               i[k] = node.pred[k].output
+            for k = 1, #pred do
+               i[k] = pred[k].output
             end
          end
          node.input = i
@@ -254,7 +262,7 @@ function DAG:updateOutput(input)
 end
 
 function DAG:updateGradInput(input, gradOutput)
-   assert(self.sorted, 'There has been a DAG structure change before a DAG:updateGradInput')
+   assert(self.sorted, 'There has been a structure change before a DAG:updateGradInput')
 
    self:nestedApply(
       function(nnm, go)
@@ -291,18 +299,21 @@ function DAG:updateGradInput(input, gradOutput)
          assert(torch.type(nnm.gradInput) == 'table',
                 'Should have a table gradInput since it has multiple predecessors')
          for n = 1, #pred do
-            table.insert(self.node[node.pred[n]].gradInputSucc, nnm.gradInput[n])
+            table.insert(self.node[pred[n]].gradInputSucc, nnm.gradInput[n])
          end
       end
    end
 
-   self.gradInput = self:nestedApply(function(m) return m.gradInput end, self.inputModules)
+   self.gradInput = self:nestedApply(
+      function(m) return m.gradInput end,
+      self.inputModules
+   )
 
    return self.gradInput
 end
 
 function DAG:accGradParameters(input, gradOutput, scale)
-   assert(self.sorted, 'There has been a DAG structure change before a DAG:accGradParameters')
+   assert(self.sorted, 'There has been a structure change before a DAG:accGradParameters')
 
    self:nestedApply(
       function(nnm, go) self.node[nnm].gradOutput = go end,
@@ -324,8 +335,8 @@ end
 function DAG:clearState()
    self.sorted = nil
    for _, node in pairs(self.node) do
-      node.gradInputSucc = nil
       node.input = nil
+      node.gradInputSucc = nil
       node.gradOutput = nil
    end
    return parent.clearState(self)