search

macournoyer / neuralconvo

Neural conversational model in Torch
776 stars 347 forks source link

"Wrong size for view" error while evalution #83

Closed ghost closed 6 years ago

ghost commented 6 years ago

I got following error and couldn't get reply from a trained model.

$ th eval.lua Loading vocabulary from data/vocab.t7 ... -- Loading model

Type a sentence and hit enter to submit. CTRL+C then enter to quit.

you> hello /home/ubuntu/src/torch/install/bin/luajit: .../ubuntu/src/torch/install/share/lua/5.1/nn/Container.lua:67: In 3 module of nn.Sequential: .../ubuntu/src/torch/install/share/lua/5.1/torch/Tensor.lua:466: Wrong size for view. Input size: 1000. Output size: 25931 stack traceback: [C]: in function 'error' .../ubuntu/src/torch/install/share/lua/5.1/torch/Tensor.lua:466: in function 'view' /home/ubuntu/src/torch/install/share/lua/5.1/rnn/utils.lua:191: in function 'recursiveZeroMask' .../ubuntu/src/torch/install/share/lua/5.1/rnn/MaskZero.lua:37: in function 'updateOutput' .../ubuntu/src/torch/install/share/lua/5.1/rnn/Recursor.lua:13: in function '_updateOutput' ...rc/torch/install/share/lua/5.1/rnn/AbstractRecurrent.lua:50: in function 'updateOutput' ...ubuntu/src/torch/install/share/lua/5.1/rnn/Sequencer.lua:53: in function <...ubuntu/src/torch/install/share/lua/5.1/rnn/Sequencer.lua:34> [C]: in function 'xpcall' .../ubuntu/src/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors' ...ubuntu/src/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward' ./seq2seq.lua:87: in function 'eval' eval.lua:55: in function 'say' eval.lua:69: in main chunk [C]: in function 'dofile' .../src/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: at 0x00405d50

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' .../ubuntu/src/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors' ...ubuntu/src/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function 'forward' ./seq2seq.lua:87: in function 'eval' eval.lua:55: in function 'say' eval.lua:69: in main chunk [C]: in function 'dofile' .../src/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: at 0x00405d50

ghost commented 6 years ago

I found this solve the problem above.

In the file seq2seq.lua line 87, change local prediction = self.decoder:forward(torch.Tensor(output))[#output] to local prediction = self.decoder:forward(torch.Tensor({output}):t())[#output][1]