projects
/
dagnn.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Update to make test with cuda simpler.
[dagnn.git]
/
test-dagnn.lua
diff --git
a/test-dagnn.lua
b/test-dagnn.lua
index
f7de819
..
e34ee02
100755
(executable)
--- a/
test-dagnn.lua
+++ b/
test-dagnn.lua
@@
-26,10
+26,10
@@
require 'dagnn'
torch.setdefaulttensortype('torch.DoubleTensor')
torch.manualSeed(1)
torch.setdefaulttensortype('torch.DoubleTensor')
torch.manualSeed(1)
-function checkGrad(model, criterion, input, target)
+function checkGrad(model, criterion, input, target
, epsilon
)
local params, gradParams = model:getParameters()
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)
local output = model:forward(input)
local loss = criterion:forward(output, target)
@@
-57,7
+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
@@
-99,17
+99,32
@@
dag:connect(c, e)
dag:setInput(a)
dag:setOutput({ d, e })
dag:setInput(a)
dag:setOutput({ d, e })
--- We check it works when we put it into a nn.Sequential
+-- 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())
model = nn.Sequential()
:add(nn.Linear(50, 50))
:add(dag)
:add(nn.CAddTable())
+criterion = nn.MSECriterion()
+
+-- model:cuda()
+-- criterion:cuda()
+-- torch.setdefaulttensortype('torch.CudaTensor')
+-- epsilon = 1e-4
+
local input = torch.Tensor(30, 50):uniform()
local output = model:updateOutput(input):clone()
output:uniform()
local input = torch.Tensor(30, 50):uniform()
local output = model:updateOutput(input):clone()
output:uniform()
-print('Gradient estimate 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))
-print('Writing /tmp/graph.dot')
-dag:saveDot('/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, criterion, input, output, epsilon))