TheanoLM is a recurrent neural network language modeling tool implemented using the Python library Theano. Theano allows the user to customize and extend the neural network very conveniently, still generating highly efficient code that can utilize multiple GPUs or CPUs for parallel computation. TheanoLM allows the user to specify an arbitrary network architecture. New layer types and optimization methods can be easily implemented. Implementations of common layer types, such as long short-term memory and gated recurrent units, and Stochastic Gradient Descent, RMSProp, AdaGrad, ADADELTA, and Adam optimizers are provided.
TheanoLM is open source and licensed under the Apache License, Version 2.0. The source code is available on GitHub. Documentation can be read online on Read the Docs.
http://senarvi.github.io/