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 elements from args
end
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
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.
+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
node.gradOutput = gradInputSucc[1]
elseif #gradInputSucc > 1 then
- if node.gradOutput then
- node.gradOutput:resize(gradInputSucc[1]):copy(gradInputSucc[1])
- else
- node.gradOutput = gradInputSucc[1]:clone()
- end
- for k = 2, #gradInputSucc do
- node.gradOutput:add(gradInputSucc[k])
+ for k = 1, #gradInputSucc do
+ node.gradOutput = self:nestedAccTensor(node.gradOutput, gradInputSucc[k], k == 1)
end
end
end
self:nestedApply(
function(nnm)
if #self.node[nnm].succ == 0 then
- error('Input modules must have outgoing edges.')
+ error('Input modules must have outgoing edges.')
end
if #self.node[nnm].pred > 0 then
- error('Input modules cannog have incoming edges.')
+ error('Input modules cannot have incoming edges.')
end
end,
self.inputModules
self:nestedApply(
function(nnm, i)
- self.node[nnm].input = 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
end
end
node.input = i
- self:rethrowErrors(nnm, self.node[nnm].index, 'updateOutput', i)
+ self:rethrowErrors(nnm, node.index, 'updateOutput', i)
end
end
function(nnm, go)
local node = self.node[nnm]
node.gradOutput = go
- self:rethrowErrors(nnm, node.index, 'updateGradInput', self.node[nnm].input, go)
+ self:rethrowErrors(nnm, node.index, 'updateGradInput', node.input, go)
end,
self.outputModules, gradOutput
)
if #node.gradInputSucc > 0 then
self:updateGradOutput(node)
- self:rethrowErrors(nnm, self.node[nnm].index, 'updateGradInput', node.input, node.gradOutput)
+ self:rethrowErrors(nnm, node.index, 'updateGradInput', node.input, node.gradOutput)
end
-- We fill the gradInputSucc of our predecessors
end
function DAG:accGradParameters(input, gradOutput, scale)
- scale = scale or 1
-
assert(self.sorted, 'There has been a DAG structure change before a DAG:accGradParameters')
self:nestedApply(
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.gradInputSucc = nil
+ node.input = nil
+ node.gradOutput = nil
+ end
+ return parent.clearState(self)
+end