Tutorial fails on the GPU part with 'cunn' - training with SGD

[salman1993]

Hey, I was just trying the tutorial and the last part doesn't seem to work. Here is the error I got. Can someone help me?

I already tried reinstalling 'nn' and 'cunn' and also reinstall Torch altogether! Btw, can someone also tell me why we do that?

Channel 1, Mean: 125.83175029297
Channel 1, Standard Deviation: 63.143400842609
Channel 2, Mean: 123.26066621094
Channel 2, Standard Deviation: 62.369209019002
Channel 3, Mean: 114.03068681641
Channel 3, Standard Deviation: 66.965808411114
# StochasticGradient: training
# current error = 2.2234263599277
# current error = 1.88329374547
# current error = 1.6842083223224
# current error = 1.5661180615187
# current error = 1.4682321660876
# StochasticGradient: you have reached the maximum number of iterations
# training error = 1.4682321660876
/home/s43moham/torch/install/bin/luajit: /home/s43moham/torch/install/share/lua/5.1/nn/Container.lua:67:
In 1 module of nn.Sequential:
/home/s43moham/torch/install/share/lua/5.1/nn/THNN.lua:110: bad argument #3 to 'v' (cannot convert 'struct THCudaTensor *' to 'struct THDoubleTensor *')
stack traceback:
    [C]: in function 'v'
    /home/s43moham/torch/install/share/lua/5.1/nn/THNN.lua:110: in function 'SpatialConvolutionMM_updateOutput'
    ...am/torch/install/share/lua/5.1/nn/SpatialConvolution.lua:96: in function <...am/torch/install/share/lua/5.1/nn/SpatialConvolution.lua:92>
    [C]: in function 'xpcall'
    /home/s43moham/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors'
    ...e/s43moham/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
    torchCudaTutorial.lua:82: in main chunk
    [C]: in function 'dofile'
    ...oham/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
    [C]: at 0x00406670

WARNING: If you see a stack trace below, it doesn't point to the place where this error occurred. Please use only the one above.
stack traceback:
    [C]: in function 'error'
    /home/s43moham/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors'
    ...e/s43moham/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
    torchCudaTutorial.lua:82: in main chunk
    [C]: in function 'dofile'
    ...oham/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
    [C]: at 0x00406670

[mhmtsarigul]

You are trying a process with non-cuda tensor. Convert it to cuda.

[BenMacKenzie]

i think the tutorial neglects to convert testset.data to a Cuda Tensor:

testset.data = testset.data:cuda()

[davidstutz]

Although it's a bit late, I got this kind of errors when not converting the criterion to CUDA:

criterion = criterion:cuda()

Afterwards, amking sure that in- and outputs are CUDA tensors, everything worked fine. Thought I'd share as the issue is still open!

[minkymorgan]

@davidstutz - thank you! That was exactly what I needed. In my case:
'nn.SequencerCriterion(nn.ClassNLLCriterion()):cuda()'

[ssdutHB]

From my perspective, the issue is caused by the position of :cuda() operation. The :double operation in tutorial converts the tensor not only to double but also to CPU. So the :cuda() operation for training and testing dataset must be placed after the :double operation.