succ[a][#succ[a] + 1] = b
end
-function DAG:applyOnModules(f, t1, t2)
- if torch.type(t1) == 'table' then
+-- 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)
+ if torch.type(t) == 'table' then
local result = {}
- for k, s in pairs(t1) do
- result[k] = self:applyOnModules(f, s, t2 and t2[k])
+ for k, s in pairs(t) do
+ result[k] = self:applyOnModules(f, s, a1 and a1[k], a2 and a2[k])
end
return result
else
- return f(t1, t2)
+ return f(t, a1, a2)
end
end
function DAG:setInput(i)
self.sorted = nil
self.inputModules = i
+ self:applyOnModules(
+ function(m)
+ if (not self.succ[m] or #self.succ[m] == 0) or (self.pred[m] and #self.pred[m] > 0) then
+ error('Invalid input edges.')
+ end
+ end,
+ self.inputModules
+ )
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) or (self.succ[m] and #self.succ[m] > 0) then
+ error('Invalid output edges.')
+ end
+ end,
+ self.outputModules
+ )
end
function DAG:sort()
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)
+ end
+ end
+ end
+
+ self.gradInput = self:applyOnModules(function(m) return m.gradInput end, self.inputModules)
+
+ return self.gradInput
end
return DAG