function DAG:__init()
parent.__init(self)
- self.pred = {}
- self.succ = {}
+ -- Nodes are indexed by the module they encompass
+ self.node = { }
end
-function DAG:addEdge(a, b)
- self.sorted = nil
- local pred, succ = self.pred, self.succ
- if not pred[a] and not succ[a] then
- self:add(a)
- end
- if not pred[b] and not succ[b] then
- self:add(b)
+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
- pred[b] = pred[b] or {}
- pred[b][#pred[b] + 1] = a
- succ[a] = succ[a] or {}
- succ[a][#succ[a] + 1] = b
+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 a1 and a2 elements
-- (i.e. same keys) as second and third parameters to f when
-- available; return the results from f, organized in a similarly
-- nested table.
-function DAG:applyOnModules(f, t, a1, a2)
+function DAG:nestApply(f, t, a1, a2)
if torch.type(t) == 'table' then
local result = {}
for k, s in pairs(t) do
- result[k] = self:applyOnModules(f, s, a1 and a1[k], a2 and a2[k])
+ result[k] = self:nestApply(f, s, a1 and a1[k], a2 and a2[k])
end
return result
else
function DAG:setInput(i)
self.sorted = nil
self.inputModules = i
- self:applyOnModules(
- function(m)
- if not self.succ[m] or #self.succ[m] == 0 then
+ self:nestApply(
+ function(nnm)
+ if #self.node[nnm].succ == 0 then
error('Input modules must have outgoing edges.')
end
- if self.pred[m] and #self.pred[m] > 0 then
+ if #self.node[nnm].pred > 0 then
error('Input modules cannog have incoming edges.')
end
end,
function DAG:setOutput(o)
self.sorted = nil
self.outputModules = o
- self:applyOnModules(
- function(m)
- if not self.pred[m] or #self.pred[m] == 0 then
+ self:nestApply(
+ function(nnm)
+ if #self.node[nnm].pred == 0 then
error('Output module must have incoming edges.')
end
- if self.succ[m] and #self.succ[m] > 0 then
+ if #self.node[nnm].succ > 0 then
error('Output module cannot have outgoing edges.')
end
end,
)
end
-function DAG:sort()
+function DAG:putInOrder()
if self.sorted then
return
end
+ -- First, we sort the nodes according to the DAG order
+
local distance = {}
- self:applyOnModules(function(m) distance[m] = 1 end, self.inputModules)
+ self:nestApply(function(m) distance[m] = 1 end, self.inputModules)
local nc
repeat
nc = 0
- for i, isucc in pairs(self.succ) do
- for _, j in pairs(isucc) do
- if distance[i] and (not distance[j] or distance[j] < distance[i] + 1) then
- distance[j] = distance[i] + 1
+ 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
until nc == 0
self.sorted = { }
- for i, d in pairs(distance) do
- table.insert(self.sorted, { d, i })
+ 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[1] < b[1] end)
- for i, a in ipairs(self.sorted) do self.sorted[i] = a[2] 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:print()
- self:sort()
+ self:putInOrder()
for i, d in ipairs(self.sorted) do
print('#' .. i .. ' -> ' .. torch.type(d))
end
function DAG:updateOutput(input)
- self:sort()
-
- self:applyOnModules(function(m, i) m:updateOutput(i) end, self.inputModules, input)
-
- for _, d in ipairs(self.sorted) do
- if self.pred[d] then
- if #self.pred[d] == 1 then
- d:updateOutput(self.pred[d][1].output)
- elseif #self.pred[d] > 1 then
- local c = {}
- for k = 1, #self.pred[d] do
- c[k] = self.pred[d][k].output
+ self:putInOrder()
+
+ self:nestApply(
+ function(nnm, i)
+ self.node[nnm].input = i
+ nnm:updateOutput(i)
+ end,
+ self.inputModules,
+ input
+ )
+
+ for _, nnm in ipairs(self.sorted) do
+ local node = self.node[nnm]
+ if #node.pred > 0 then
+ local i
+ if #node.pred == 1 then
+ i = node.pred[1].output
+ elseif #node.pred > 1 then
+ i = {}
+ for k = 1, #node.pred do
+ i[k] = node.pred[k].output
end
- d:updateOutput(c)
end
+ node.input = i
+ nnm:updateOutput(i)
end
end
- self.output = self:applyOnModules(function(m) return m.output end, self.outputModules)
+ self.output = self:nestApply(function(m) return m.output end, self.outputModules)
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:sort()
-
- self:applyOnModules(function(m, i, go) m:updateGradInput(i, go) end, self.outputModules, input, gradOutput)
-
- for k = self.sorted, 1, -1 do
- local m = sorted[k]
- if self.succ[d] then
- if #self.succ[d] == 1 then
- d:updateGradInput(self.succ[d][1].gradInput)
- elseif #self.succ[d] > 1 then
- local sum
- for k = 1, #self.succ[d] do
- if sum then
- sum:add(self.succ[d][k].gradInput)
- else
- sum = self.succ[d][k].gradInput:clone()
- end
- end
- d:updateGradInput(sum)
+ self:putInOrder()
+
+ self:nestApply(
+ function(nnm, go) nnm:updateGradInput(self.node[nnm].input, go) end,
+ self.outputModules, gradOutput
+ )
+
+ self:nestApply(
+ function(nnm, i) self.node[nnm].input = i end,
+ self.inputModules, input
+ )
+
+ for _, node in pairs(self.node) do
+ node.gradInputSucc = {}
+ end
+
+ for k = #self.sorted, 1, -1 do
+ local nnm = self.sorted[k]
+ local node = self.node[nnm]
+ local pred, gradInputSucc = node.pred, node.gradInputSucc
+
+ if #gradInputSucc > 0 then
+ nnm:updateGradInput(node.input, self:computeGradInput(gradInputSucc))
+ 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
+ for n = 1, #pred do
+ table.insert(self.node[node.pred[n]].gradInputSucc, nnm.gradInput[n])
end
end
end
- self.gradInput = self:applyOnModules(function(m) return m.gradInput end, self.inputModules)
+ self.gradInput = self:nestApply(function(m) return m.gradInput end, self.inputModules)
return self.gradInput
end
projects / dagnn.git / blobdiff