Update.

[dagnn.git] / test-dagnn.lua

diff --git a/test-dagnn.lua b/test-dagnn.lua
index 53302fd..3801956 100755 (executable)
--- a/test-dagnn.lua
+++ b/test-dagnn.lua
@@ -23,9 +23,8 @@ require 'torch'
 require 'nn'
 require 'dagnn'
 
--- torch.setnumthreads(params.nbThreads)
 torch.setdefaulttensortype('torch.DoubleTensor')
-torch.manualSeed(2)
+torch.manualSeed(1)
 
 function checkGrad(model, criterion, input, target)
    local params, gradParams = model:getParameters()
@@ -76,13 +75,13 @@ 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 -->
+--                            \                        /
+--                             \                      /
+--                              +----- Mul(-1) ------+
 
 model = nn.DAG()
 
@@ -92,12 +91,11 @@ 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: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(e)
@@ -109,4 +107,5 @@ output:uniform()
 
 print('Error = ' .. checkGrad(model, nn.MSECriterion(), input, output))
 
-model:dot('/tmp/graph.dot')
+print('Writing /tmp/graph.dot')
+model:saveDot('/tmp/graph.dot')