barrista  a Python interface to Berkeley Caffe.

Berkeley Caffe  a framework for convolutional neural network algorithms

BigDL  Distributed Deep learning Library for Apache Spark

Caffe 2  a Lightweight, Modular, and Scalable Deep Learning Framework

Catalyst  Highlevel utils for PyTorch DL & RL research. It was developed with a focus on reproducibility, fast experimentation and code/ideas reusing.

Chainer  Flexible neural network (NN) framework. See, also the main website.

cudaconvnet  a fast C++/CUDA implementation of convolutional (or more generally, feedforward) neural networks. It can model arbitrary layer connectivity and network depth.

DeepLearn toolbox  Matlab/Octave toolbox for deep learning.

deeplearning4j: Deep learning for Java 
DIGITS: an interactive training system from NVIDIA 
DJL  Amazon's deep Java library

DSSTNE  Amazon DSSTNE (pronounced "Destiny") is an open source software library for training and deploying deep neural networks using GPUs.

DyNET  Dynamic neural network library

Gorgonia  deep learning package for GoLang.

H2O  Open Source Fast Scalable Machine Learning Platform For Smarter Applications: Deep Learning, Gradient Boosting & XGBoost, Random Forest, Generalized Linear Modeling (Logistic Regression, Elastic Net), KMeans, PCA, Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

Keras Theanobased Deep Learning library 
Lasagne a lightweight library to build and train neural networks in Theano. 
Microsoft CNTK  (Computational Network Toolkit by Microsoft Research) a unified deeplearning toolkit that describes neural networks as a series of computational steps via a directed graph. It implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers.

MXNET  Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutationaware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more.

NEON  NErvana's pythON based Deep Learning Framework.

Neural Network Libraries by Sony  Efficient and flexible C++ neural net libraries (dynamic graphs are supported)

NeuralTalk2  contains Python+numpy source code for learning Multimodal Recurrent Neural Networks that describe images with sentences.

NNVM  Open Compiler for AI Frameworks.

OpenSeq2Seq  Toolkit for efficient experimentation with various sequencetosequence models.

probtorch  Probabilistic Torch is library for deep generative models that extends PyTorch.

Pyro  Deep universal probabilistic programming with Python and PyTorch

Pytorch  Tensors and Dynamic neural networks in Python with strong GPU acceleration.

Pytorch Ignite  a highlevel library to help with training neural networks in PyTorch.

tensorflow  Open source software library for numerical computation using data flow graphs.

Veles  Distributed platform for rapid Deep learning application development from Samsung.
