projects
/
dagnn.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Added a check that all nodes are connected to the inputs.
[dagnn.git]
/
test-dagnn.lua
diff --git
a/test-dagnn.lua
b/test-dagnn.lua
index
366e98f
..
5d8a309
100755
(executable)
--- a/
test-dagnn.lua
+++ b/
test-dagnn.lua
@@
-23,9
+23,8
@@
require 'torch'
require 'nn'
require 'dagnn'
require 'nn'
require 'dagnn'
--- torch.setnumthreads(params.nbThreads)
torch.setdefaulttensortype('torch.DoubleTensor')
torch.setdefaulttensortype('torch.DoubleTensor')
-torch.manualSeed(
2
)
+torch.manualSeed(
1
)
function checkGrad(model, criterion, input, target)
local params, gradParams = model:getParameters()
function checkGrad(model, criterion, input, target)
local params, gradParams = model:getParameters()
@@
-58,7
+57,7
@@
function checkGrad(model, criterion, input, target)
local num = (loss1 - loss0) / (2 * epsilon)
if num ~= ana then
local num = (loss1 - loss0) / (2 * epsilon)
if num ~= ana then
- err = math.max(err,
torch.abs(num - ana) / torc
h.abs(num))
+ err = math.max(err,
math.abs(num - ana) / mat
h.abs(num))
end
end
end
end
@@
-76,38
+75,49
@@
function printTensorTable(t)
end
end
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()
a = nn.Linear(50, 10)
b = nn.ReLU()
c = nn.Linear(10, 15)
d = nn.CMulTable()
-e = nn.
CAddTable(
)
+e = nn.
Mul(-1
)
-model:connect(a, b)
-model:connect(b, nn.Linear(10, 15), nn.ReLU(), d)
-model:connect(d, e)
-model:connect(b, c)
-model:connect(c, d)
-model:connect(c, nn.Mul(-1), e)
+dag:connect(a, b, c)
+dag:connect(b, nn.Linear(10, 15), nn.ReLU(), d)
+dag:connect(c, d)
+dag:connect(c, e)
-model:setInput(a)
-model:setOutput(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()
local input = torch.Tensor(30, 50):uniform()
local output = model:updateOutput(input):clone()
-
output:uniform()
output:uniform()
-print('Error = ' .. checkGrad(model, nn.MSECriterion(), input, output))
+-- Check that DAG:accGradParameters and friends work okay
+print('Gradient estimate error ' .. checkGrad(model, nn.MSECriterion(), input, output))
-print('Writing /tmp/graph.dot')
-model:dot('/tmp/graph.dot')
+-- 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))