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=53302fd810b1dcad950a74400ab2f678c04745e1;hb=HEAD;hpb=0a630b54355382dfa68c0f3d51729bad0b4c58e6

diff --git a/test-dagnn.lua b/test-dagnn.lua
index 53302fd..b390a29 100755
--- a/test-dagnn.lua
+++ b/test-dagnn.lua
@@ -21,16 +21,18 @@
 
 require 'torch'
 require 'nn'
+
+-- require 'cunn'
+
 require 'dagnn'
 
--- torch.setnumthreads(params.nbThreads)
 torch.setdefaulttensortype('torch.DoubleTensor')
-torch.manualSeed(2)
+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)
@@ -58,7 +60,7 @@ function checkGrad(model, criterion, input, target)
       local num = (loss1 - loss0) / (2 * epsilon)
 
       if num ~= ana then
-         err = math.max(err, torch.abs(num - ana) / torch.abs(num))
+         err = math.max(err, math.abs(num - ana) / math.max(epsilon, math.abs(num)))
       end
    end
 
@@ -76,37 +78,66 @@ function printTensorTable(t)
    end
 end
 
---               +- Linear(10, 10) -> ReLU ---> d --+
---              /                              /     \
---             /                              /       \
---  --> a --> b -----------> c --------------+         e -->
---                            \                       /
---                             \                     /
---                              +-- Mul(-1) --------+
+--               +-- Linear(10, 10) --> ReLU --> d -->
+--              /                               /
+--             /                               /
+--  --> a --> b -----------> c ---------------+
+--                            \
+--                             \
+--                              +--------------- e -->
 
-model = nn.DAG()
+dag = nn.DAG()
 
 a = nn.Linear(50, 10)
 b = nn.ReLU()
 c = nn.Linear(10, 15)
 d = nn.CMulTable()
-e = nn.CAddTable()
-
-model:addEdge(a, b)
-model:addEdge(b, nn.Linear(10, 15), nn.ReLU(), d)
-model:addEdge(d, e)
-model:addEdge(b, c)
-model:addEdge(c, d)
-model:addEdge(c, nn.Mul(-1), e)
-
-model:setInput(a)
-model:setOutput(e)
+e = nn.Mul(-1)
+
+dag:connect(a, b, c)
+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. 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()
+   :add(nn.Linear(50, 50))
+   :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()
 
-print('Error = ' .. checkGrad(model, nn.MSECriterion(), input, output))
+-- Check that DAG:accGradParameters and friends work okay
+print('Gradient estimate error ' .. checkGrad(model, criterion, input, output, epsilon))
+
+-- Check that we can save and reload the model
+model:clearState()
+torch.save('./test.t7', model)
+local otherModel = torch.load('./test.t7')
+print('Gradient estimate error ' .. checkGrad(otherModel, criterion, input, output, epsilon))
 
-model:dot('/tmp/graph.dot')
+dag:print()