X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=dagnn.git;a=blobdiff_plain;f=test-dagnn.lua;h=5d8a309ce9769b547de0fa104b4b5f0b99157fe1;hp=cac5a944a365a8e9b189c71d53b9e08179058798;hb=59490d9da93f28283c79d44a5e7c791cbd623b24;hpb=d0743d66135ed7cedcb3777cfa5dda883cbeadb3

diff --git a/test-dagnn.lua b/test-dagnn.lua
index cac5a94..5d8a309 100755
--- a/test-dagnn.lua
+++ b/test-dagnn.lua
@@ -1,10 +1,31 @@
 #!/usr/bin/env luajit
 
+--[[
+
+   Copyright (c) 2016 Idiap Research Institute, http://www.idiap.ch/
+   Written by Francois Fleuret <francois.fleuret@idiap.ch>
+
+   This file is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 3 as
+   published by the Free Software Foundation.
+
+   It is distributed in the hope that it will be useful, but WITHOUT
+   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+   or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public
+   License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this file.  If not, see <http://www.gnu.org/licenses/>.
+
+]]--
+
 require 'torch'
 require 'nn'
-
 require 'dagnn'
 
+torch.setdefaulttensortype('torch.DoubleTensor')
+torch.manualSeed(1)
+
 function checkGrad(model, criterion, input, target)
    local params, gradParams = model:getParameters()
 
@@ -17,6 +38,8 @@ function checkGrad(model, criterion, input, target)
    model:backward(input, gradOutput)
    local analyticalGradParam = gradParams:clone()
 
+   local err = 0
+
    for i = 1, params:size(1) do
       local x = params[i]
 
@@ -32,15 +55,13 @@ function checkGrad(model, criterion, input, target)
 
       local ana = analyticalGradParam[i]
       local num = (loss1 - loss0) / (2 * epsilon)
-      local err = torch.abs(num - ana) / torch.abs(num)
 
-      print(
-         err .. ' checkGrad ' .. i
-            .. ' analytical ' .. ana
-            .. ' numerical ' .. num
-      )
+      if num ~= ana then
+         err = math.max(err, math.abs(num - ana) / math.abs(num))
+      end
    end
 
+   return err
 end
 
 function printTensorTable(t)
@@ -54,64 +75,49 @@ function printTensorTable(t)
    end
 end
 
--- torch.setnumthreads(params.nbThreads)
-torch.setdefaulttensortype('torch.DoubleTensor')
-torch.manualSeed(2)
+--               +-- Linear(10, 10) --> ReLU --> d -->
+--              /                               /
+--             /                               /
+--  --> a --> b -----------> c ---------------+
+--                            \
+--                             \
+--                              +--------------- e -->
 
---                     +--> c ----> e --+
---                    /            /     \
---                   /            /       \
---  input --> a --> b ---> d ----+         g --> output
---                          \             /
---                           \           /
---                            +--> f ---+
+dag = nn.DAG()
 
-a = nn.Linear(10, 10)
+a = nn.Linear(50, 10)
 b = nn.ReLU()
-c = nn.Linear(10, 3)
-d = nn.Linear(10, 3)
-e = nn.CMulTable()
-f = nn.Linear(3, 3)
-g = nn.CAddTable()
-
-----------------------------------------------------------------------
-
-model = nn.DAG()
-
-model:addEdge(a, b)
-model:addEdge(b, c)
-model:addEdge(b, d)
-model:addEdge(c, e)
-model:addEdge(d, e)
-model:addEdge(d, f)
-model:addEdge(e, g)
-model:addEdge(f, g)
-
-model:setInput(a)
-model:setOutput(g)
-
-input = torch.Tensor(3, 10):uniform()
-
-print('******************************************************************')
-print('** updateOutput **************************************************')
-print('******************************************************************')
-
-output = model:updateOutput(input):clone()
-
-printTensorTable(output)
-
-print('******************************************************************')
-print('** updateGradInput ***********************************************')
-print('******************************************************************')
-
-gradInput = model:updateGradInput(input, output)
-
-printTensorTable(gradInput)
-
-print('******************************************************************')
-print('** checkGrad *****************************************************')
-print('******************************************************************')
-
+c = nn.Linear(10, 15)
+d = nn.CMulTable()
+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:setInput(a)
+dag:setOutput({ d, e })
+
+-- Check the output of the dot file
+print('Writing /tmp/graph.dot')
+dag:saveDot('/tmp/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())
+
+local input = torch.Tensor(30, 50):uniform()
+local output = model:updateOutput(input):clone()
 output:uniform()
 
-checkGrad(model, nn.MSECriterion(), input, output)
+-- Check that DAG:accGradParameters and friends work okay
+print('Gradient estimate error ' .. checkGrad(model, nn.MSECriterion(), input, output))
+
+-- 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))