Open Source Neural Network Libraries

This is YOLO-v3 and v2 for Windows and Linux. YOLO (You only look once) is a state-of-the-art, real-time object detection system of Darknet, an open source neural network framework in C. YOLO is extremely fast and accurate. It uses a single neural network to divide a full image into regions, and then predicts bounding boxes and probabilities for each region. This project is a fork of the original Darknet project.

The Simd Library is a free open source image processing library, designed for C and C++ programmers. It provides many useful high performance algorithms for image processing such as: pixel format conversion, image scaling and filtration, extraction of statistic information from images, motion detection, object detection (HAAR and LBP classifier cascades) and classification, neural network. The algorithms are optimized with using of different SIMD CPU extensions. In particular the library supports following CPU extensions: SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2 and AVX-512 for x86/x64, VMX(Altivec) and VSX(Power7) for PowerPC, NEON for ARM. The Simd Library has C API and also contains useful C++ classes and functions to facilitate access to C API. The library supports dynamic and static linking, 32-bit and 64-bit Windows, Android and Linux, MSVS, G++ and Clang compilers, MSVS project and CMake build systems.

MMDeploy is an open-source deep learning model deployment toolset. It is a part of the OpenMMLab project. Models can be exported and run in several backends, and more will be compatible. All kinds of modules in the SDK can be extended, such as Transform for image processing, Net for Neural Network inference, Module for postprocessing and so on. Install and build your target backend. ONNX Runtime is a cross-platform inference and training accelerator compatible with many popular ML/DNN frameworks. Please read getting_started for the basic usage of MMDeploy.

Neuroph OCR - Handwriting Recognition is developed to recognize hand written letter and characters. It's engine derived's from the Java Neural Network Framework - Neuroph and as such it can be used as a standalone project or a Neuroph plug in.

ANNGD is a artificial neural network gender detection application. The detection is made in real time images captured by webcam by opencv library. The package include applications to image pre-processing and artificial neural network back-propagation training.

Foad is an open source software which receive an EKG Signal from scanner, WFDB database or heart sensors. Finding patient disease started by taking Fourier transform (FFT) from input signal and extract a single cycle. Based on some heuristic algorithm the most important feature like P , Q , R , S , T captured and feed to trained neural network. and so the final decision made by CNN library. As mentioned before this software also capable do some image processing on scanned paper to lower the final costs.

This project uses massively parallel Graphics Processing Units(GPU) for neural network(Backpropagation) purposes.

A library written in C# for encoding and decoding animated Graphics Interchange Format (GIF) images. Based on NGif http://www.codeproject.com/KB/GDI-plus/NGif.aspx. Includes sample apps for encoding and decoding GIF files.

PyTorch-NLP is a library for Natural Language Processing (NLP) in Python. It’s built with the very latest research in mind, and was designed from day one to support rapid prototyping. PyTorch-NLP comes with pre-trained embeddings, samplers, dataset loaders, metrics, neural network modules and text encoders. It’s open-source software, released under the BSD3 license. With your batch in hand, you can use PyTorch to develop and train your model using gradient descent. For example, check out this example code for training on the Stanford Natural Language Inference (SNLI) Corpus. Now you've setup your pipeline, you may want to ensure that some functions run deterministically. Wrap any code that's random, with fork_rng and you'll be good to go. Now that you've computed your vocabulary, you may want to make use of pre-trained word vectors to set your embeddings.

RNNLIB is a recurrent neural network library for sequence learning problems. Applicable to most types of spatiotemporal data, it has proven particularly effective for speech and handwriting recognition. full installation and usage instructions given at http://sourceforge.net/p/rnnl/wiki/Home/

Thank you for your interest in Speedy Composer. Speedy Composer is an automated application for composing melodies for Speedy Net members. We recently made changes to the source code of Speedy Net, and converted it into the Python language and Django framework. Since Speedy Composer was originally written in PHP, it is not adapted to work with Speedy Net in its current form. So unfortunately we were forced to temporarily close the app Speedy Composer. But don't worry, we kept backups of all the tunes composed by Speedy Composer, and when the website is reopened we will upload them to the new site. Speedy Composer and Speedy Net are open source applications, free software. We are currently looking for volunteers to help us convert Speedy Composer to Python. If you are interested in volunteering, please contact me by email. Thank you and good luck, Uri Rodberg Founder and Director of Speedy Net and Speedy Composer, Speedy Paz Technologies Ltd. uri@speedy.net

TensorSpace is a neural network 3D visualization framework built using TensorFlow.js, Three.js and Tween.js. TensorSpace provides Keras-like APIs to build deep learning layers, load pre-trained models, and generate a 3D visualization in the browser. From TensorSpace, it is intuitive to learn what the model structure is, how the model is trained and how the model predicts the results based on the intermediate information. After preprocessing the model, TensorSpace supports the visualization of pre-trained models from TensorFlow, Keras and TensorFlow.js. TensorSpace is a neural network 3D visualization framework designed for not only showing the basic model structure but also presenting the processes of internal feature abstractions, intermediate data manipulations and final inference generations. By applying TensorSpace API, it is more intuitive to visualize and understand any pre-trained models built by TensorFlow, Keras, TensorFlow.js, etc.

video-nonlocal-net implements Non-local Neural Networks for video understanding, adding long-range dependency modeling to 2D/3D ConvNet backbones. Non-local blocks compute attention-like responses across all positions in space-time, allowing a feature at one frame and location to aggregate information from distant frames and regions. This formulation improves action recognition and spatiotemporal reasoning, especially for classes requiring context beyond short temporal windows. The repo provides training recipes and models for standard datasets, as well as ablations that show how many non-local blocks to insert and at which stages. Efficient implementations keep memory and compute manageable so the blocks can be added without rewriting the entire backbone. The result is a practical, drop-in mechanism for upgrading purely local video models into context-aware networks with strong benchmark performance.

openlpr is a open source project to implement license plate recognition in Win32 and Linux platform. It will provide the basic image processing to locate plate and character split and a neural network design to recognize character.