PocketSphinx is a lightweight speech recognition engine, specifically tuned for handheld and mobile devices, though it works equally well on the desktop

Fast, scalable, easy-to-use Python based Deep Learning Framework by Nervana™

A curated list of deep learning resources for computer vision

Keras' fork with several new functionalities. Caffe2Keras converter, multimodal layers, etc.

Caffe: a fast open framework for deep learning.

Torch on steroids

Build and run Docker containers leveraging NVIDIA GPUs

Vehicle Detection by Haar Cascades with OpenCV

Learn how to train your own OpenCV Haar classifier

A minimalistic framework for fast object detection (with a pre-trained face detector)

C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library

Faster R-CNN

Dense image captioning in Torch

A tool for use with clang to analyze #includes in C and C++ source files

Fast R-CNN Torch Implementation

End to end detection in crowded scenes

Computational Network Toolkit (CNTK)

Visualization Toolkit

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

A toolkit for making real world machine learning and data analysis applications in C++

Easy benchmarking of all publicly accessible implementations of convnets

Computation using data flow graphs for scalable machine learning

Example program showing how to train your custom HOG detector using openCV

LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.

🍺 The missing package manager for OS X.

Breeze is a numerical processing library for Scala.