In this article, we have compiled a list of some of the lesser-known Deep Learning libraries.
This is an open source framework for distributed deep learning on big-data clusters.
This is a library for TensorFlow that allows users to define preprocessing pipelines and run these using large scale data processing frameworks, while also exporting the pipeline in a way that can be run as part of a TensorFlow graph.
A library for probabilistic modeling, inference, and criticism with Deep generative models, variational inference. It runs on TensorFlow.
The downhill package provides algorithms for minimizing scalar loss functions that are defined using Theano.
Knet is the Koç University deep learning framework that supports GPU operation and automatic differentiation using dynamic computational graphs for models defined in plain Julia.
RecNet is a easy to use framework for recurrent neural networks. It implements a deep uni/bidirectional Conventional/LSTM/GRU architecture in Python with the use of the Theano library.
This is a Pythonic Deep Learning Framework Inspired by Torch’s Neural Network package.
Autograd can automatically differentiate native Python and Numpy code. It can handle a large subset of Python’s features.
nmtpy is a suite of Python tools, primarily based on the starter code provided in dl4mt-tutorial for training neural machine translation networks using Theano.
This repository aims at providing a high performing and flexible deep learning platform, by prototyping a pure NumPy interface above MXNet backend.
This is a Python library that benchmarks Machine Learning systems’ vulnerability to adversarial examples.
OpenNMT is an industrial-strength, open-source (MIT) neural machine translation system utilizing the Torch/PyTorch mathematical toolkit.
PaddlePaddle (PArallel Distributed Deep LEarning) is an easy-to-use, efficient, flexible and scalable deep learning platform.
Nematus is an attention-based encoder-decoder model for neural machine translation.
A general-purpose encoder-decoder framework for Tensorflow that can be used for Machine Translation, Text Summarization, Conversational Modeling, Image Captioning, and more.
rllab is a framework for developing and evaluating reinforcement learning algorithms. It includes a wide range of continuous control tasks.
keras-rl implements state-of-the art deep reinforcement learning algorithms in Python and seamlessly integrates with the deep learning library Keras.
Fuel provides your machine learning models with the data they need to learn.
Blocks is a framework that helps you build neural network models on top of Theano.
Chi provides high-level operations for writing and visualizing experiments, defining models and running TensorFlow graphs.
These were some of the Deep Learning Libraries lying low that you should explore. In the next article, we will put together some lesser-known Machine Learning Libraries. Comment below and share your own list of Deep Learning libraries that you think should get surfaced.