require 'torch'
require 'nn'
+
+-- require 'cunn'
+
require 'dagnn'
torch.setdefaulttensortype('torch.DoubleTensor')
torch.manualSeed(1)
-function checkGrad(model, criterion, input, target)
+function checkGrad(model, criterion, input, target, epsilon)
local params, gradParams = model:getParameters()
- local epsilon = 1e-5
+ local epsilon = epsilon or 1e-5
local output = model:forward(input)
local loss = criterion:forward(output, target)
local num = (loss1 - loss0) / (2 * epsilon)
if num ~= ana then
- err = math.max(err, math.abs(num - ana) / math.abs(num))
+ err = math.max(err, math.abs(num - ana) / math.max(epsilon, math.abs(num)))
end
end
dag:connect(c, d)
dag:connect(c, e)
+dag:setLabel(a, 'first module')
+
dag:setInput(a)
dag:setOutput({ d, e })
:add(dag)
:add(nn.CAddTable())
+criterion = nn.MSECriterion()
+
+if cunn then
+ print("Using CUDA")
+ model:cuda()
+ criterion:cuda()
+ torch.setdefaulttensortype('torch.CudaTensor')
+ epsilon = 1e-3
+end
+
local input = torch.Tensor(30, 50):uniform()
local output = model:updateOutput(input):clone()
output:uniform()
-- Check that DAG:accGradParameters and friends work okay
-print('Gradient estimate error ' .. checkGrad(model, nn.MSECriterion(), input, output))
+print('Gradient estimate error ' .. checkGrad(model, criterion, input, output, epsilon))
-- Check that we can save and reload the model
model:clearState()
torch.save('/tmp/test.t7', model)
local otherModel = torch.load('/tmp/test.t7')
-print('Gradient estimate error ' .. checkGrad(otherModel, nn.MSECriterion(), input, output))
+print('Gradient estimate error ' .. checkGrad(otherModel, criterion, input, output, epsilon))
+
+dag:print()