Open Source Linux Neural Network Libraries
Sort By:
Neural Network Libraries for Linux
View 10 business solutionsBrowse free open source Neural Network Libraries and projects for Linux below. Use the toggles on the left to filter open source Neural Network Libraries by OS, license, language, programming language, and project status.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
1
ncnn
High-performance neural network inference framework for mobile
ncnn is a high-performance neural network inference computing framework designed specifically for mobile platforms. It brings artificial intelligence right at your fingertips with no third-party dependencies, and speeds faster than all other known open source frameworks for mobile phone cpu. ncnn allows developers to easily deploy deep learning algorithm models to the mobile platform and create intelligent APPs. It is cross-platform and supports most commonly used CNN networks, including Classical CNN (VGG AlexNet GoogleNet Inception), Face Detection (MTCNN RetinaFace), Segmentation (FCN PSPNet UNet YOLACT), and more. ncnn is currently being used in a number of Tencent applications, namely: QQ, Qzone, WeChat, and Pitu. -
2
spaCy
Industrial-strength Natural Language Processing (NLP)
spaCy is a library built on the very latest research for advanced Natural Language Processing (NLP) in Python and Cython. Since its inception it was designed to be used for real world applications-- for building real products and gathering real insights. It comes with pretrained statistical models and word vectors, convolutional neural network models, easy deep learning integration and so much more. spaCy is the fastest syntactic parser in the world according to independent benchmarks, with an accuracy within 1% of the best available. It's blazing fast, easy to install and comes with a simple and productive API. -
3
Netron
Visualizer for neural network, deep learning, machine learning models
Netron is a viewer for neural network, deep learning and machine learning models. Netron supports ONNX, Keras, TensorFlow Lite, Caffe, Darknet, Core ML, MNN, MXNet, ncnn, PaddlePaddle, Caffe2, Barracuda, Tengine, TNN, RKNN, MindSpore Lite, and UFF. Netron has experimental support for TensorFlow, PyTorch, TorchScript, OpenVINO, Torch, Arm NN, BigDL, Chainer, CNTK, Deeplearning4j, MediaPipe, ML.NET, scikit-learn, TensorFlow.js. There is an extense variety of sample model files to download or open using the browser version. It is supported by macOS, Windows, Linux, Python Server and browser. -
4
AIMET
AIMET is a library that provides advanced quantization and compression
Qualcomm Innovation Center (QuIC) is at the forefront of enabling low-power inference at the edge through its pioneering model-efficiency research. QuIC has a mission to help migrate the ecosystem toward fixed-point inference. With this goal, QuIC presents the AI Model Efficiency Toolkit (AIMET) - a library that provides advanced quantization and compression techniques for trained neural network models. AIMET enables neural networks to run more efficiently on fixed-point AI hardware accelerators. Quantized inference is significantly faster than floating point inference. For example, models that we’ve run on the Qualcomm® Hexagon™ DSP rather than on the Qualcomm® Kryo™ CPU have resulted in a 5x to 15x speedup. Plus, an 8-bit model also has a 4x smaller memory footprint relative to a 32-bit model. However, often when quantizing a machine learning model (e.g., from 32-bit floating point to an 8-bit fixed point value), the model accuracy is sacrificed. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
Darknet YOLO
Real-Time Object Detection for Windows and Linux
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. -
6
AlphaZero.jl
A generic, simple and fast implementation of Deepmind's AlphaZero
Beyond its much publicized success in attaining superhuman level at games such as Chess and Go, DeepMind's AlphaZero algorithm illustrates a more general methodology of combining learning and search to explore large combinatorial spaces effectively. We believe that this methodology can have exciting applications in many different research areas. Because AlphaZero is resource-hungry, successful open-source implementations (such as Leela Zero) are written in low-level languages (such as C++) and optimized for highly distributed computing environments. This makes them hardly accessible for students, researchers and hackers. Many simple Python implementations can be found on Github, but none of them is able to beat a reasonable baseline on games such as Othello or Connect Four. As an illustration, the benchmark in the README of the most popular of them only features a random baseline, along with a greedy baseline that does not appear to be significantly stronger. -
7
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers, embedded, or automotive product platforms. TensorRT is built on CUDA®, NVIDIA’s parallel programming model, and enables you to optimize inference leveraging libraries, development tools, and technologies in CUDA-X™ for artificial intelligence, autonomous machines, high-performance computing, and graphics. With new NVIDIA Ampere Architecture GPUs, TensorRT also leverages sparse tensor cores providing an additional performance boost. -
8
Darknet
Convolutional Neural Networks
Darknet is an open source neural network framework written in C and CUDA, developed by Joseph Redmon. It is best known as the original implementation of the YOLO (You Only Look Once) real-time object detection system. Darknet is lightweight, fast, and easy to compile, making it suitable for research and production use. The repository provides pre-trained models, configuration files, and tools for training custom object detection models. With GPU acceleration via CUDA and OpenCV integration, it achieves high performance in image recognition tasks. Its simplicity, combined with powerful capabilities, has made Darknet one of the most influential projects in the computer vision community. -
9
Alpa
Training and serving large-scale neural networks
Alpa is a system for training and serving large-scale neural networks. Scaling neural networks to hundreds of billions of parameters has enabled dramatic breakthroughs such as GPT-3, but training and serving these large-scale neural networks require complicated distributed system techniques. Alpa aims to automate large-scale distributed training and serving with just a few lines of code. -
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
10
SponsorBlock
Skip YouTube video sponsors (browser extension)
SponsorBlock is an open-source crowdsourced browser extension and open API for skipping sponsor segments in YouTube videos. Users submit when a sponsor happens from the extension, and the extension automatically skips sponsors it knows about using a privacy-preserving query system. It also supports skipping other categories, such as intros, outros, and reminders to subscribe, and skipping to the point with highlights. The extension also features an upvote/downvote system with a weighted random-based distribution algorithm. Once one person submits this information, everyone else with this extension will skip right over the sponsored segment. SponsorBlock is a crowdsourced browser extension that let's anyone submit the start and end time's of sponsored segments of YouTube videos. -
11
Python Outlier Detection
A Python toolbox for scalable outlier detection
PyOD is a comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. This exciting yet challenging field is commonly referred as outlier detection or anomaly detection. PyOD includes more than 30 detection algorithms, from classical LOF (SIGMOD 2000) to the latest COPOD (ICDM 2020) and SUOD (MLSys 2021). Since 2017, PyOD [AZNL19] has been successfully used in numerous academic researches and commercial products [AZHC+21, AZNHL19]. PyOD has multiple neural network-based models, e.g., AutoEncoders, which are implemented in both PyTorch and Tensorflow. PyOD contains multiple models that also exist in scikit-learn. It is possible to train and predict with a large number of detection models in PyOD by leveraging SUOD framework. A benchmark is supplied for select algorithms to provide an overview of the implemented models. In total, 17 benchmark datasets are used for comparison, which can be downloaded at ODDS. -
12
RuVector
Self-Learning, Vector Graph Neural Network, and Database built in Rust
RuVector is part of the broader rUv ecosystem of AI engineering tools and focuses on enabling advanced vector-based processing and intelligent system development within agentic and AI-driven pipelines. The project fits into a larger vision of modular, composable AI infrastructure designed to support autonomous agents, data retrieval, and intelligent automation workflows. It emphasizes extensibility and interoperability with modern AI stacks, allowing developers to integrate vector operations into search, reasoning, or generative systems. The repository reflects a research-forward approach that blends practical utilities with experimental agentic concepts, encouraging exploration of emerging AI design patterns. It is intended for developers building sophisticated AI-powered applications who need flexible vector handling and integration capabilities. -
13
Neural Tangents
Fast and Easy Infinite Neural Networks in Python
Neural Tangents is a high-level neural network API for specifying complex, hierarchical models at both finite and infinite width, built in Python on top of JAX and XLA. It lets researchers define architectures from familiar building blocks—convolutions, pooling, residual connections, and nonlinearities—and obtain not only the finite network but also the corresponding Gaussian Process (GP) kernel of its infinite-width limit. With a single specification, you can compute NNGP and NTK kernels, perform exact GP inference, and study training dynamics analytically for infinitely wide networks. The library closely mirrors JAX’s stax API while extending it to return a kernel_fn alongside init_fn and apply_fn, enabling drop-in workflows for kernel computation. Kernel evaluation is highly optimized for speed and memory, and computations can be automatically distributed across accelerators with near-linear scaling. -
14
Simd
High performance image processing library in C++
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. -
15
Stock prediction deep neural learning
Predicting stock prices using a TensorFlow LSTM
Predicting stock prices can be a challenging task as it often does not follow any specific pattern. However, deep neural learning can be used to identify patterns through machine learning. One of the most effective techniques for series forecasting is using LSTM (long short-term memory) networks, which are a type of recurrent neural network (RNN) capable of remembering information over a long period of time. This makes them extremely useful for predicting stock prices. Predicting stock prices is a complex task, as it is influenced by various factors such as market trends, political events, and economic indicators. The fluctuations in stock prices are driven by the forces of supply and demand, which can be unpredictable at times. To identify patterns and trends in stock prices, deep learning techniques can be used for machine learning. Long short-term memory (LSTM) is a type of recurrent neural network (RNN) that is specifically designed for sequence modeling and prediction. -
16
Axon
Nx-powered Neural Networks
Nx-powered Neural Networks for Elixir. Axon consists of the following components. Functional API – A low-level API of numerical definitions (defn) of which all other APIs build on. Model Creation API – A high-level model creation API which manages model initialization and application. Optimization API – An API for creating and using first-order optimization techniques based on the Optax library. Training API – An API for quickly training models, inspired by PyTorch Ignite. Axon provides abstractions that enable easy integration while maintaining a level of separation between each component. You should be able to use any of the APIs without dependencies on others. By decoupling the APIs, Axon gives you full control over each aspect of creating and training a neural network. At the lowest-level, Axon consists of a number of modules with functional implementations of common methods in deep learning. -
17
Imagen - Pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network
Implementation of Imagen, Google's Text-to-Image Neural Network that beats DALL-E2, in Pytorch. It is the new SOTA for text-to-image synthesis. Architecturally, it is actually much simpler than DALL-E2. It consists of a cascading DDPM conditioned on text embeddings from a large pre-trained T5 model (attention network). It also contains dynamic clipping for improved classifier-free guidance, noise level conditioning, and a memory-efficient unit design. It appears neither CLIP nor prior network is needed after all. And so research continues. For simpler training, you can directly supply text strings instead of precomputing text encodings. (Although for scaling purposes, you will definitely want to precompute the textual embeddings + mask) -
18
Neuroph is lightweight Java Neural Network Framework which can be used to develop common neural network architectures. Small number of basic classes which correspond to basic NN concepts, and GUI editor makes it easy to learn and use.
-
19
Lucid
A collection of infrastructure and tools for research
Lucid is a collection of infrastructure and tools for research in neural network interpretability. Lucid is research code, not production code. We provide no guarantee it will work for your use case. Lucid is maintained by volunteers who are unable to provide significant technical support. Start visualizing neural networks with no setup. The following notebooks run right from your browser, thanks to Collaboratory. It's a Jupyter notebook environment that requires no setup to use and runs entirely in the cloud. You can run the notebooks on your local machine, too. Clone the repository and find them in the notebooks subfolder. You will need to run a local instance of the Jupyter notebook environment to execute them. Feature visualization answers questions about what a network, or parts of a network, are looking for by generating examples. -
20
Bumblebee
Pre-trained Neural Network models in Axon
Bumblebee provides pre-trained Neural Network models on top of Axon. It includes integration with Models, allowing anyone to download and perform Machine Learning tasks with few lines of code. The best way to get started with Bumblebee is with Livebook. Our announcement video shows how to use Livebook's Smart Cells to perform different Neural Network tasks with a few clicks. You can then tweak the code and deploy it. First, add Bumblebee and EXLA as dependencies in your mix.exs. EXLA is an optional dependency but an important one as it allows you to compile models just-in-time and run them on CPU/GPU. -
21
Gen.jl
A general-purpose probabilistic programming system
An open-source stack for generative modeling and probabilistic inference. Gen’s inference library gives users building blocks for writing efficient probabilistic inference algorithms that are tailored to their models, while automating the tricky math and the low-level implementation details. Gen helps users write hybrid algorithms that combine neural networks, variational inference, sequential Monte Carlo samplers, and Markov chain Monte Carlo. Gen features an easy-to-use modeling language for writing down generative models, inference models, variational families, and proposal distributions using ordinary code. But it also lets users migrate parts of their model or inference algorithm to specialized modeling languages for which it can generate especially fast code. Users can also hand-code parts of their models that demand better performance. Neural network inference is fast, but can be inaccurate on out-of-distribution data, and requires expensive training. -
22
Sonnet
TensorFlow-based neural network library
Sonnet is a neural network library built on top of TensorFlow designed to provide simple, composable abstractions for machine learning research. Sonnet can be used to build neural networks for various purposes, including different types of learning. Sonnet’s programming model revolves around a single concept: modules. These modules can hold references to parameters, other modules and methods that apply some function on the user input. There are a number of predefined modules that already ship with Sonnet, making it quite powerful and yet simple at the same time. Users are also encouraged to build their own modules. Sonnet is designed to be extremely unopinionated about your use of modules. It is simple to understand, and offers clear and focused code. -
23
oneDNN
oneAPI Deep Neural Network Library (oneDNN)
This software was previously known as Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN) and Deep Neural Network Library (DNNL). oneAPI Deep Neural Network Library (oneDNN) is an open-source cross-platform performance library of basic building blocks for deep learning applications. oneDNN is part of oneAPI. The library is optimized for Intel(R) Architecture Processors, Intel Processor Graphics and Xe Architecture graphics. oneDNN has experimental support for the following architectures: Arm* 64-bit Architecture (AArch64), NVIDIA* GPU, OpenPOWER* Power ISA (PPC64), IBMz* (s390x), and RISC-V. oneDNN is intended for deep learning applications and framework developers interested in improving application performance on Intel CPUs and GPUs. Deep learning practitioners should use one of the applications enabled with oneDNN. -
24
Stanza
Stanford NLP Python library for many human languages
Stanza is a collection of accurate and efficient tools for the linguistic analysis of many human languages. Starting from raw text to syntactic analysis and entity recognition, Stanza brings state-of-the-art NLP models to languages of your choosing. Stanza is a Python natural language analysis package. It contains tools, which can be used in a pipeline, to convert a string containing human language text into lists of sentences and words, to generate base forms of those words, their parts of speech and morphological features, to give a syntactic structure dependency parse, and to recognize named entities. The toolkit is designed to be parallel among more than 70 languages, using the Universal Dependencies formalism. Stanza is built with highly accurate neural network components that also enable efficient training and evaluation with your own annotated data. -
25
Face Verification Experiment
Original Caffe Version for LightCNN-9. Highly recommend to use PyTorch
face_verification_experiment is a research repository focused on experiments in face verification using deep learning. It provides implementations and scripts for testing different neural network architectures and training strategies on face recognition and verification tasks. The project is designed to help researchers and practitioners evaluate the performance of models on standard datasets and explore techniques for improving accuracy. By offering experimental setups, it enables reproducibility and comparative study of face verification approaches. The repository serves as a resource for understanding the application of convolutional neural networks to identity verification, highlighting both methodology and results. It is primarily intended for academic and research purposes in computer vision and biometrics.
