X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=dagnn.lua;h=ca51841f8442417d10097e6a6939fd86f3bceda2;hb=d8fd868f94ce0b66cd2cc1a4615df10a88b5d5ec;hp=158ef785d446fb22f6226248c6a07c83cf47b6c3;hpb=e6516772e13dd5424f0a1b7e2063a7417614844c;p=dagnn.git

diff --git a/dagnn.lua b/dagnn.lua
index 158ef78..ca51841 100755
--- a/dagnn.lua
+++ b/dagnn.lua
@@ -29,24 +29,7 @@ function DAG:__init()
    self.node = { }
 end
 
-function DAG:createNode(nnm)
-   if not self.node[nnm] then
-      self:add(nnm) -- Add it to the object as a Container
-      self.node[nnm] = {}
-      self.node[nnm].succ = {}
-      self.node[nnm].pred = {}
-   end
-end
-
-function DAG:addEdge(nnma, nnmb)
-   self.sorted = nil
-   self:createNode(nnma)
-   self:createNode(nnmb)
-   table.insert(self.node[nnmb].pred, nnma)
-   table.insert(self.node[nnma].succ, nnmb)
-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)
@@ -61,6 +44,80 @@ function DAG:nestedApply(f, t, args)
    end
 end
 
+function DAG:createNode(nnm)
+   if not self.node[nnm] then
+      self:add(nnm) -- Add it to the object as a Container
+      local node = {}
+      node.succ = {}
+      node.pred = {}
+      node.index = #self.modules
+      self.node[nnm] = node
+   end
+end
+
+function DAG:putInOrder()
+   if self.sorted then
+      return
+   end
+
+   local distance = {}
+   self:nestedApply(function(m) distance[m] = 1 end, self.inputModules)
+
+   local nc
+   repeat
+      nc = 0
+      for nnma, node in pairs(self.node) do
+         for _, nnmb in pairs(node.succ) do
+            if distance[nnma] and (not distance[nnmb] or distance[nnmb] < distance[nnma] + 1) then
+               distance[nnmb] = distance[nnma] + 1
+               nc = nc + 1
+            end
+         end
+      end
+   until nc == 0
+
+   self.sorted = { }
+   for m, d in pairs(distance) do
+      table.insert(self.sorted, { distance = d, nnm = m })
+   end
+
+   table.sort(self.sorted, function(a, b) return a.distance < b.distance end)
+
+   for i, a in ipairs(self.sorted) do self.sorted[i] = a.nnm end
+end
+
+function DAG:computeGradOutput(gradInputSucc)
+   local gi
+   if #gradInputSucc == 1 then
+      gi = gradInputSucc[1] -- we avoid a clone()
+   elseif #gradInputSucc > 1 then
+      for k = 1, #gradInputSucc do
+         if gi then
+            gi:add(gradInputSucc[k])
+         else
+            gi = gradInputSucc[k]:clone()
+         end
+      end
+   end
+   return gi
+end
+
+----------------------------------------------------------------------
+
+-- Connect a sequence of modules
+function DAG:connect(...)
+   self.sorted = nil
+   local prev
+   for _, nnm in pairs({...}) do
+      self:createNode(nnm)
+      if prev then
+         table.insert(self.node[nnm].pred, prev)
+         table.insert(self.node[prev].succ, nnm)
+      end
+      prev = nnm
+   end
+end
+
 function DAG:setInput(i)
    self.sorted = nil
    self.inputModules = i
@@ -93,48 +150,49 @@ function DAG:setOutput(o)
    )
 end
 
-function DAG:putInOrder()
-   if self.sorted then
-      return
+function DAG:print()
+   self:putInOrder()
+
+   for i, d in ipairs(self.sorted) do
+      print('#' .. i .. ' -> ' .. torch.type(d))
    end
+end
 
-   -- First, we sort the nodes according to the DAG order
+----------------------------------------------------------------------
 
-   local distance = {}
+function DAG:saveDot(filename)
+   local file = (filename and io.open(filename, 'w')) or io.stdout
 
-   self:nestedApply(function(m) distance[m] = 1 end, self.inputModules)
+   file:write('digraph {\n')
 
-   local nc
+   file:write('\n')
 
-   repeat
-      nc = 0
-      for nnma, node in pairs(self.node) do
-         for _, nnmb in pairs(node.succ) do
-            if distance[nnma] and (not distance[nnmb] or distance[nnmb] < distance[nnma] + 1) then
-               distance[nnmb] = distance[nnma] + 1
-               nc = nc + 1
-            end
-         end
+   for nnma, node in pairs(self.node) do
+      file:write(
+         '  '
+            .. node.index
+            .. ' [shape=box,label=\"' .. torch.type(nnma) .. '\"]'
+            .. '\n'
+      )
+
+      for _, nnmb in pairs(node.succ) do
+         file:write(
+            '  '
+               .. node.index
+               .. ' -> '
+               .. self.node[nnmb].index
+               .. '\n'
+         )
       end
-   until nc == 0
 
-   self.sorted = { }
-   for m, d in pairs(distance) do
-      table.insert(self.sorted, { distance = d, nnm = m })
+      file:write('\n')
    end
 
-   table.sort(self.sorted, function(a, b) return a.distance < b.distance end)
+   file:write('}\n')
 
-   for i, a in ipairs(self.sorted) do self.sorted[i] = a.nnm end
 end
 
-function DAG:print()
-   self:putInOrder()
-
-   for i, d in ipairs(self.sorted) do
-      print('#' .. i .. ' -> ' .. torch.type(d))
-   end
-end
+----------------------------------------------------------------------
 
 function DAG:updateOutput(input)
    self:putInOrder()
@@ -142,7 +200,8 @@ function DAG:updateOutput(input)
    self:nestedApply(
       function(nnm, i)
          self.node[nnm].input = i
-         nnm:updateOutput(i)
+         -- nnm:updateOutput(i)
+         self:rethrowErrors(nnm, self.node[nnm].index, 'updateOutput', i)
       end,
       self.inputModules,
       input
@@ -161,7 +220,8 @@ function DAG:updateOutput(input)
             end
          end
          node.input = i
-         nnm:updateOutput(i)
+         -- nnm:updateOutput(i)
+         self:rethrowErrors(nnm, self.node[nnm].index, 'updateOutput', i)
       end
    end
 
@@ -173,27 +233,14 @@ function DAG:updateOutput(input)
    return self.output
 end
 
-function DAG:computeGradInput(gradInputSucc)
-   local gi
-   if #gradInputSucc == 1 then
-      gi = gradInputSucc[1] -- we avoid a clone()
-   elseif #gradInputSucc > 1 then
-      for k = 1, #gradInputSucc do
-         if gi then
-            gi:add(gradInputSucc[k])
-         else
-            gi = gradInputSucc[k]:clone()
-         end
-      end
-   end
-   return gi
-end
-
 function DAG:updateGradInput(input, gradOutput)
-   self:putInOrder()
+   assert(self.sorted, 'there has been a DAG structure change before a DAG:updateGradInput')
 
    self:nestedApply(
-      function(nnm, go) nnm:updateGradInput(self.node[nnm].input, go) end,
+      function(nnm, go)
+         -- nnm:updateGradInput(self.node[nnm].input, go)
+         self:rethrowErrors(nnm, self.node[nnm].index, 'updateGradInput', self.node[nnm].input, go)
+      end,
       self.outputModules, gradOutput
    )
 
@@ -212,7 +259,9 @@ function DAG:updateGradInput(input, gradOutput)
       local pred, gradInputSucc = node.pred, node.gradInputSucc
 
       if #gradInputSucc > 0 then
-         nnm:updateGradInput(node.input, self:computeGradInput(gradInputSucc))
+         node.gradOutput = self:computeGradOutput(gradInputSucc)
+         -- nnm:updateGradInput(node.input, node.gradOutput)
+         self:rethrowErrors(nnm, self.node[nnm].index, 'updateGradInput', node.input, node.gradOutput)
       end
 
       -- We fill the gradInputSucc of our predecessors
@@ -236,21 +285,12 @@ end
 function DAG:accGradParameters(input, gradOutput, scale)
    scale = scale or 1
 
-   self:putInOrder()
-
-   self:nestedApply(
-      function(nnm, go) nnm:updateGradInput(self.node[nnm].input, go) end,
-      self.outputModules, gradOutput
-   )
-
-   self:nestedApply(
-      function(nnm, i) self.node[nnm].input = i end,
-      self.inputModules, input
-   )
+   assert(self.sorted, 'there has been a DAG structure change before a DAG:accGradParameters')
 
-   for k = #self.sorted, 1, -1 do
-      local nnm = self.sorted[k]
+   for k = 1, #self.modules do
+      local nnm = self.modules[k]
       local node = self.node[nnm]
-      nnm:accGradParameters(node.input, self:computeGradInput(node.gradInputSucc), scale)
+      -- nnm:accGradParameters(node.input, node.gradOutput, scale)
+      self:rethrowErrors(nnm, k, 'accGradParameters', node.input, self:computeGradOutput(node.gradInputSucc), scale)
    end
 end