DNNGraph

DNNGraph is a deep neural network model generation DSL in Haskell. It is a DSL for specifying the model. This uses the lens library for elegant, composable constructions, and the fgl graph library for specifying the network layout. A set of optimization passes that run over the graph representation to improve the performance of the model.

For example, users can take advantage of the fact that several layers types (ReLU, Dropout) can operate in-place. DNNGraph also offers a set of backends to generate code for the platform. Currently, DNNGraph generate Caffe (by generating model prototxt files) and Torch (by generating Lua scripts).

It also has a set of useful CLI tools for exporting, visualizing and understanding a model (visualization of network structure, parameter density). Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by the Berkeley Vision and Learning Center (BVLC) and by community contributors. Google’s DeepDream is based on Caffe Framework.

This framework is a BSD-licensed C++ library with Python Interface. On the other hand, Torch is a scientific computing framework with wide support for machine learning algorithms. It is easy to use and efficient, fast scripting language, LuaJIT, and an underlying C/CUDA implementation. Torch is based on Lua programming language.