Awesome
Torch recurrent neural networks
This is a recurrent neural network (RNN) library that extends Torch's nn. You can use it to build RNNs, LSTMs, GRUs, BRNNs, BLSTMs, and so forth and so on.
This library includes documentation for the following objects :
-
Recurrent modules consider successive calls to
forward
as different time-steps in a sequence. -
Sequencer modules
forward
entire sequences through a decoratedAbstractRecurrent
instance. -
Sequencer criterion handle
input
andtarget
sequences. -
Miscellaneous modules and criterions for things like noise contrastive estimation (NCE) and zero-masking.
-
Reinforce modules and criterions implement the REINFORCE learning rule.
<a name='rnn.examples'></a>
Examples
A complete list of examples is available in the examples directory
Citation
If you use rnn in your work, we'd really appreciate it if you could cite the following paper:
Léonard, Nicholas, Sagar Waghmare, Yang Wang, and Jin-Hwa Kim. rnn: Recurrent Library for Torch. arXiv preprint arXiv:1511.07889 (2015).
Any significant contributor to the library will also get added as an author to the paper. A significant contributor is anyone who added at least 300 lines of code to the library.
Troubleshooting
Most issues can be resolved by updating the various dependencies:
luarocks install torch
luarocks install nn
luarocks install torchx
luarocks install dataload
If you are using CUDA :
luarocks install cutorch
luarocks install cunn
And don't forget to update this package :
luarocks install rnn
If that doesn't fix it, open an issue on github.