Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Unable to convert argument 3 from cdata #60

Open
tebdrepo opened this issue Oct 10, 2016 · 0 comments
Open

Unable to convert argument 3 from cdata #60

tebdrepo opened this issue Oct 10, 2016 · 0 comments

Comments

@tebdrepo
Copy link

tebdrepo commented Oct 10, 2016

Im using Lua 5.1 and torch7. While trying to execute

th train.lua --cuda --dataset 50000 --hiddenSize 1000

I'm getting the below error:

Dataset stats:
  Vocabulary size: 25931
         Examples: 83632

-- Epoch 1 / 50

/home/siva/torch/install/bin/lua: unable to convert argument 3 from cdata<struct THCudaTensor*> to cdata<struct THCudaLongTensor*>
stack traceback:
        [C]: in function 'v'
        /home/siva/torch/install/share/lua/5.1/nn/THNN.lua:110: in function 'ClassNLLCriterion_updateOutput'
        ...torch/install/share/lua/5.1/nn/ClassNLLCriterion.lua:41: in function <...torch/install/share/lua/5.1/nn/ClassNLLCriterion.lua:29>
        (tail call): ?
        ...rch/install/share/lua/5.1/rnn/SequencerCriterion.lua:55: in function <...rch/install/share/lua/5.1/rnn/SequencerCriterion.lua:39>
        (tail call): ?
        ./seq2seq.lua:74: in function 'train'
        train.lua:85: in main chunk
        [C]: in function 'dofile'
        .../torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
        [C]: ?


Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant