groundhog | WARNING : Groundhog development

groundhog is a Python library. groundhog has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can download it from GitHub.

WARNING: Groundhog development is over. Please consider using [Blocks] instead. For an example of machine translation using Blocks please see [Blocks-examples] repository. GroundHog is a python framework on top of Theano (that aims to provide a flexible, yet efficient way of implementing complex recurrent neural network models. It supports a variety of recurrent layers, such as DT-RNN, DOT-RNN, RNN with gated hidden units and LSTM. Furthermore, it enables the flexible combination of various layers, for instance, to build a neural translation model. This is a version forked from the original GroundHog (developed by Razvan Pascanu, Caglar Gulcehre and Kyunghyun Cho. This fork will be the version developed and maintained by the members of the LISA Lab at the University of Montreal. The main contributors and maintainers of this fork are currently Dzmitry Bahdanau and Kyunghyun Cho. Most of the library documentation is still work in progress, but check the files containing Tut (in tutorials) for a quick tutorial on how to use the library. The library is under the 3-clause BSD license, so it may be used for commercial purposes.