recurrent-visual-attention.lua issue

[northeastsquare]

Hello, thank you for great project!
After I trained a model using recurrent-visual-attention.lua ,

1. How do I use the model to get a picture's visual attention?
2. When I ran:
   th recurrent-visual-attention.lua --cuda --xpPath /home/silva/save/silva-XPS-8300:1441270258:1.dat
   I got the following error:
   /home/silva/torch/install/bin/luajit: /home/silva/torch/install/share/lua/5.1/torch/File.lua:262: unknown Torch class <optim.ConfusionMatrix>
   stack traceback:
   [C]: in function 'error'
   /home/silva/torch/install/bin/luajit: /home/silva/torch/install/share/lua/5.1/torch/File.lua:262: unknown Torch class <optim.ConfusionMatrix>

[northeastsquare]

This is caused by: torch.load(xpfile)
How to solve?

[nicholas-leonard]

This should be fixed in latest rnn version (re-install it). However, you won't be able to retrain existing saved models using xpPath. For loading the model, you can still use the logic used by xpPath (it was just missing a require 'optim')

[northeastsquare]

Thank you, require 'optim' fix it. But how can I use the trained module to get a picture's visual attention?