X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=dagnn.lua;h=1f45b2acae3bc546495e2b33bd0666f6f577c54e;hb=f3a748c4119c4f374b30d0010198732bb80b43a6;hp=14cd5821c2064ac74b50dde101449d10d8f2274e;hpb=fe54a7c5c8425ee9783d82e16a42924e23add457;p=dagnn.git

diff --git a/dagnn.lua b/dagnn.lua
index 14cd582..1f45b2a 100755
--- a/dagnn.lua
+++ b/dagnn.lua
@@ -26,10 +26,10 @@ 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 element from args
+-- Apply f on t recursively; use the corresponding elements from args
 -- (i.e. same keys) as second parameter to f when available; return
 -- the results from f, organized in a similarly nested table.
 function DAG:nestedApply(f, t, args)
@@ -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
@@ -74,9 +78,15 @@ function DAG:putInOrder()
             end
          end
       end
+      assert(nl < #self.modules, 'Cycle detected in the graph.')
+      nl = nl + 1
    until nc == 0
 
-   self.sorted = { }
+   for _, nnm in pairs(self.modules) do
+      assert(distance[nnm], 'Some modules are not connected to inputs')
+   end
+
+   self.sorted = {}
    for m, d in pairs(distance) do
       table.insert(self.sorted, { distance = d, nnm = m })
    end
@@ -86,20 +96,40 @@ 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 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 = {}
+      for i in pairs(x) do
+         b[i] = self:nestedAccTensor(a[i], x[i], first)
+      end
+      a = b
+   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
 
 ----------------------------------------------------------------------
@@ -123,12 +153,8 @@ function DAG:setInput(i)
    self.inputModules = i
    self:nestedApply(
       function(nnm)
-         if #self.node[nnm].succ == 0 then
-            error('Input modules must have outgoing  edges.')
-         end
-         if #self.node[nnm].pred > 0 then
-            error('Input modules cannog have incoming edges.')
-         end
+         assert(#self.node[nnm].succ > 0, 'Input modules must have outgoing edges.')
+         assert(#self.node[nnm].pred == 0, 'Input modules cannot have incoming edges.')
       end,
       self.inputModules
    )
@@ -139,12 +165,8 @@ function DAG:setOutput(o)
    self.outputModules = o
    self:nestedApply(
       function(nnm)
-         if #self.node[nnm].pred == 0 then
-            error('Output module must have incoming edges.')
-         end
-         if #self.node[nnm].succ > 0 then
-            error('Output module cannot have outgoing edges.')
-         end
+         assert(#self.node[nnm].pred > 0, 'Output module must have incoming edges.')
+         assert(#self.node[nnm].succ == 0, 'Output module cannot have outgoing edges.')
       end,
       self.outputModules
    )
@@ -167,20 +189,26 @@ function DAG:saveDot(filename)
 
    file:write('\n')
 
-   for nnma, node in pairs(self.node) do
+   for nnmb, node in pairs(self.node) do
       file:write(
          '  '
             .. node.index
-            .. ' [shape=box,label=\"' .. torch.type(nnma) .. '\"]'
+            .. ' [shape=box,label=\"' .. torch.type(nnmb) .. '\"]'
             .. '\n'
       )
 
-      for _, nnmb in pairs(node.succ) do
+      for i, nnma in pairs(node.pred) do
+         local decoration = ''
+         if #node.pred > 1 then
+            -- decoration = ' [headlabel=\"' .. i .. '\"]'
+            decoration = ' [label=\"' .. i .. '\"]'
+         end
          file:write(
             '  '
-               .. node.index
+               .. self.node[nnma].index
                .. ' -> '
                .. self.node[nnmb].index
+               .. decoration
                .. '\n'
          )
       end
@@ -199,9 +227,9 @@ 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)
+         local node = self.node[nnm]
+         node.input = i
+         self:rethrowErrors(nnm, node.index, 'updateOutput', i)
       end,
       self.inputModules,
       input
@@ -209,19 +237,19 @@ 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
-         -- nnm:updateOutput(i)
-         self:rethrowErrors(nnm, self.node[nnm].index, 'updateOutput', i)
+         self:rethrowErrors(nnm, node.index, 'updateOutput', i)
       end
    end
 
@@ -234,12 +262,13 @@ 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)
-         -- nnm:updateGradInput(self.node[nnm].input, go)
-         self:rethrowErrors(nnm, self.node[nnm].index, 'updateGradInput', self.node[nnm].input, go)
+         local node = self.node[nnm]
+         node.gradOutput = go
+         self:rethrowErrors(nnm, node.index, 'updateGradInput', node.input, go)
       end,
       self.outputModules, gradOutput
    )
@@ -256,41 +285,59 @@ 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)
-         self:rethrowErrors(nnm, self.node[nnm].index, 'updateGradInput', node.input, node.gradOutput)
+      if #node.gradInputSucc > 0 then
+         self:updateGradOutput(node)
+         self:rethrowErrors(nnm, node.index, 'updateGradInput', node.input, node.gradOutput)
       end
 
       -- We fill the gradInputSucc of our predecessors
       if #pred == 1 then
          table.insert(self.node[pred[1]].gradInputSucc, nnm.gradInput)
       elseif #pred > 1 then
-         if not torch.type(nnm.gradInput) == 'table' then
-            error('Should have a table gradInput since it has multiple predecessors')
-         end
+         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)
-   scale = scale or 1
+   assert(self.sorted, 'There has been a structure change before a DAG:accGradParameters')
+
+   self:nestedApply(
+      function(nnm, go) self.node[nnm].gradOutput = go end,
+      self.outputModules, gradOutput
+   )
 
-   assert(self.sorted, 'there has been a DAG structure change before a DAG:accGradParameters')
+   self:nestedApply(
+      function(nnm, i) self.node[nnm].input = i end,
+      self.inputModules, input
+   )
 
    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, self:computeGradOutput(node.gradInputSucc), 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.input = nil
+      node.gradInputSucc = nil
+      node.gradOutput = nil
    end
+   return parent.clearState(self)
 end