Liyuan Liu

@brandondube thanks for providing the example. I believe this is a known issue and can be fixed by setting `degenerated_to_sgd=False` (in your case, you can simply delete the `else: self.x...

It seems that the error occurs when the program trying to loading the file. However, I'm not sure about the exact reason.

Maybe you can try packages like `ipdb` or `pdb` (especially the `set_trace` method). They are very helpful in debugging programs.

I think the default setting should be using cuda, is that right? Personally I prefer 'store_true'. And in the pull request, I also modified two parts..

Hi, I'm a rookie on torch too. However, I tried to write a sample function for this model myself (unfortunately it's super slow), and you can find it on https://github.com/LiyuanLucasLiu/lstm-char-cnn

Hi, I'm not sure what caused this error (as a rookie...), but it seems that you ignored several necessary options while running sample.lua (the default value might not fit your...

Hi, I spent some time to train a new model and try sample.lua, I find that: ``` $ th main.lua -savefile char-large -EOS '+' $ th sample.lua -model cv/lm_char-large_epoch25.00_81.97.t7 -gpuid...