X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=test-dagnn.lua;h=cec37d246451b3eb7f639edbf946e22716d6d979;hb=501034fda227664ac04ab5dd2d912f768bcd70e4;hp=5d8a309ce9769b547de0fa104b4b5f0b99157fe1;hpb=59490d9da93f28283c79d44a5e7c791cbd623b24;p=dagnn.git

diff --git a/test-dagnn.lua b/test-dagnn.lua
index 5d8a309..cec37d2 100755
--- a/test-dagnn.lua
+++ b/test-dagnn.lua
@@ -21,15 +21,18 @@
 
 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)
@@ -57,7 +60,7 @@ function checkGrad(model, criterion, input, 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
 
@@ -109,15 +112,25 @@ model = nn.Sequential()
    :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))