hughperkins / clnn

OpenCL backend for Torch nn neural networks library

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Error while running test-mnist2.lua

manjunaths opened this issue · comments

When I try to run the mnist2 test in clnn I get this error.

using luaexe: luajit
model.modules[#model].padding   nil
Using Intel(R) Corporation , OpenCL platform: Intel(R) OpenCL
Using OpenCL device: Intel(R) HD Graphics
# StochasticGradient: training
luajit: ...epLearning/torch/install/share/lua/5.1/nn/Sequential.lua:44: bad argument #1 (field padW does not exist)
stack traceback:
        [C]: in function 'updateOutput'
        ...epLearning/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward'
        ...ng/torch/install/share/lua/5.1/nn/StochasticGradient.lua:35: in function 'train'
        test/test-mnist2.lua:117: in main chunk
        [C]: at 0x004058d0

Do you know what is happening here ?

Hmmm, seems like a discrepancy between two of your instaled libraries. Can you luarocks install all the following please:

  • nn
  • clnn

(and I think your cltorch is already latest version)

I did a luarocks install of the above and tried the test and it failed. I git cloned the above and did a luarocks make rocks/*.spec and they still fail with the same error as above.

My cltorch is also the install of a git cloned version. So all of them are at the latest revision is what I am thinking. Anything else that I can try ?

Can you double-check the tests pass please? ie:

luajit -l nn -e 'nn.test()'
luajit -l clnn -e 'clnn.test()'

Oh... I think this is an old script, and doesnt work. Let me see if I can fix it. Sorry :-P

Repaired it. Sorry about that. If you 'luarocks install clnn', it should work now.