X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=dagnn.git;a=blobdiff_plain;f=test-dagnn.lua;h=b390a29a5b7b412c6ff019e44f51ef5ef5e2a6de;hp=e34ee0211336aae7f7f5c033f8d4ed9379289bd4;hb=HEAD;hpb=d77b7e4eedd6fefefaefe0b2656247d563287817

diff --git a/test-dagnn.lua b/test-dagnn.lua
index e34ee02..b390a29 100755
--- a/test-dagnn.lua
+++ b/test-dagnn.lua
@@ -21,6 +21,9 @@
 
 require 'torch'
 require 'nn'
+
+-- require 'cunn'
+
 require 'dagnn'
 
 torch.setdefaulttensortype('torch.DoubleTensor')
@@ -57,7 +60,7 @@ function checkGrad(model, criterion, input, target, epsilon)
       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
 
@@ -96,12 +99,17 @@ dag:connect(b, nn.Linear(10, 15), nn.ReLU(), d)
 dag:connect(c, d)
 dag:connect(c, e)
 
+dag:setLabel(a, 'first module')
+
 dag:setInput(a)
 dag:setOutput({ d, e })
 
--- Check the output of the dot file
-print('Writing /tmp/graph.dot')
-dag:saveDot('/tmp/graph.dot')
+-- Check the output of the dot file. Generate a pdf with:
+--
+-- dot ./graph.dot -Lg -T pdf -o ./graph.pdf
+--
+print('Writing ./graph.dot')
+dag:saveDot('./graph.dot')
 
 -- Let's make a model where the dag is inside another nn.Container.
 model = nn.Sequential()
@@ -111,10 +119,13 @@ model = nn.Sequential()
 
 criterion = nn.MSECriterion()
 
--- model:cuda()
--- criterion:cuda()
--- torch.setdefaulttensortype('torch.CudaTensor')
--- epsilon = 1e-4
+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()
@@ -125,6 +136,8 @@ print('Gradient estimate error ' .. checkGrad(model, criterion, input, output, e
 
 -- Check that we can save and reload the model
 model:clearState()
-torch.save('/tmp/test.t7', model)
-local otherModel = torch.load('/tmp/test.t7')
+torch.save('./test.t7', model)
+local otherModel = torch.load('./test.t7')
 print('Gradient estimate error ' .. checkGrad(otherModel, criterion, input, output, epsilon))
+
+dag:print()