RETURNN paper.

RETURNN - RWTH extensible training framework for universal recurrent neural networks, is a Theano-based implementation of modern recurrent neural network architectures. It is optimized for fast and reliable training of recurrent neural networks in a multi-GPU environment.

Features include:

• Mini-batch training of feed-forward neural networks
• Sequence-chunking based batch training for recurrent neural networks
• Long short-term memory recurrent neural networks
• Multidimensional LSTM (GPU only, there is no CPU version)
• Memory management for large data sets
• Work distribution across multiple devices

Please read the documentation for more information.

There are some example demos in /demos which work on artifically generated data, i.e. they should work as-is.

There are some real-world examples here.

Some benchmark setups against other frameworks can be found here. The results are in the RETURNN paper.