No description, website, or topics provided.
Python
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
README.md Update README.md Mar 11, 2018
cell.py code Oct 15, 2016
iterator.py code Oct 15, 2016
main.py code Oct 15, 2016
model.py change variable name Oct 15, 2016
updater.py code Oct 15, 2016

README.md

seq2seq-chainer

THIS REPO IS NO LONGER MAINTAINED. FOR A MORE STRUCTURED CODEBASE, VISIT simple-nmt, IMPLEMENTED IN PYTORCH, which is very similar to Chainer.

Implementation of recurrent neural network (RNN) and seq2seq models in Chainer. This repo is inspired by Tal Baumel's cnn (now dynet) seq2seq notebook.

The toy task is learning to reverse a string (i.e. given input "abcde", output "edcba"). Implemented models are:

  • Vanilla multi-layer LSTM RNN model.
  • Vanilla encoder-decoder model.
  • Global-attentional encoder-decoder model (Vinyals et al.)

To run the code, please install Chainer and CuDNN first. Then evoke main.py:

$ python main.py

To run with different modes, modify main.py. Some notable variables are:

  • DEVICE: the code is set to run on CPU (DEVICE = -1), set DEVICE = 0 to run on single GPU.
  • LARGE: size of the data set.
  • ATTEND: whether to use attention or not.

If there are any problems, email me at nguyenxuankhanhm@gmail.com