require 'torch'
require 'nn'
-
require 'dagnn'
+torch.setdefaulttensortype('torch.DoubleTensor')
+torch.manualSeed(1)
+
function checkGrad(model, criterion, input, target)
local params, gradParams = model:getParameters()
model:backward(input, gradOutput)
local analyticalGradParam = gradParams:clone()
+ local err = 0
+
for i = 1, params:size(1) do
local x = params[i]
local ana = analyticalGradParam[i]
local num = (loss1 - loss0) / (2 * epsilon)
- local err
- if num == ana then
- err = 0
- else
- err = torch.abs(num - ana) / torch.abs(num)
+ if num ~= ana then
+ err = math.max(err, torch.abs(num - ana) / torch.abs(num))
end
-
- print(
- 'CHECK '
- .. err
- .. ' checkGrad ' .. i
- .. ' analytical ' .. ana
- .. ' numerical ' .. num
- )
end
+ return err
end
function printTensorTable(t)
end
end
--- torch.setnumthreads(params.nbThreads)
-torch.setdefaulttensortype('torch.DoubleTensor')
-torch.manualSeed(2)
+-- +-- Linear(10, 10) --> ReLU --> d --+
+-- / / \
+-- / / \
+-- --> a --> b -----------> c --------------+ e -->
+-- \ /
+-- \ /
+-- +----- Mul(-1) ------+
--- +--> c ----> e --+
--- / / \
--- / / \
--- input --> a --> b ---> d ----+ g --> output
--- \ /
--- \ /
--- +--> f ---+
+model = nn.DAG()
-a = nn.Linear(10, 10)
+a = nn.Linear(50, 10)
b = nn.ReLU()
-c = nn.Linear(10, 3)
-d = nn.Linear(10, 3)
-e = nn.CMulTable()
-f = nn.Linear(3, 3)
-g = nn.CAddTable()
-
-model = nn.DAG()
+c = nn.Linear(10, 15)
+d = nn.CMulTable()
+e = nn.CAddTable()
-model:addEdge(a, b)
-model:addEdge(b, c)
-model:addEdge(b, d)
-model:addEdge(c, e)
-model:addEdge(d, e)
-model:addEdge(d, f)
-model:addEdge(e, g)
-model:addEdge(f, g)
+model:connect(a, b, c)
+model:connect(b, nn.Linear(10, 15), nn.ReLU(), d)
+model:connect(d, e)
+model:connect(c, d)
+model:connect(c, nn.Mul(-1), e)
model:setInput(a)
-model:setOutput(g)
+model:setOutput(e)
-input = torch.Tensor(3, 10):uniform()
-
-print('******************************************************************')
-print('** updateOutput **************************************************')
-print('******************************************************************')
-
-output = model:updateOutput(input):clone()
-
-printTensorTable(output)
-
-print('******************************************************************')
-print('** updateGradInput ***********************************************')
-print('******************************************************************')
-
-gradInput = model:updateGradInput(input, output)
-
-printTensorTable(gradInput)
-
-print('******************************************************************')
-print('** checkGrad *****************************************************')
-print('******************************************************************')
+local input = torch.Tensor(30, 50):uniform()
+local output = model:updateOutput(input):clone()
output:uniform()
-checkGrad(model, nn.MSECriterion(), input, output)
+print('Error = ' .. checkGrad(model, nn.MSECriterion(), input, output))
+
+print('Writing /tmp/graph.dot')
+model:saveDot('/tmp/graph.dot')