Open Source Neural Network Libraries
Sort By:
Neural Network Libraries
View 52 business solutionsBrowse free open source Neural Network Libraries and projects below. Use the toggles on the left to filter open source Neural Network Libraries by OS, license, language, programming language, and project status.
-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
1
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. -
2
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. -
3
PlotNeuralNet
Latex code for making neural networks diagrams
Latex code for drawing neural networks for reports and presentations. Have a look into examples to see how they are made. Additionally, let's consolidate any improvements that you make and fix any bugs to help more people with this code. -
4
FairChem
FAIR Chemistry's library of machine learning methods for chemistry
FAIRChem is a unified library for machine learning in chemistry and materials, consolidating data, pretrained models, demos, and application code into a single, versioned toolkit. Version 2 modernizes the stack with a cleaner core package and breaking changes relative to V1, focusing on simpler installs and a stable API surface for production and research. The centerpiece models (e.g., UMA variants) plug directly into the ASE ecosystem via a FAIRChem calculator, so users can run relaxations, molecular dynamics, spin-state energetics, and surface catalysis workflows with the same pretrained network by switching a task flag. Tasks span heterogeneous domains—catalysis (OC20-style), inorganic materials (OMat), molecules (OMol), MOFs (ODAC), and molecular crystals (OMC)—allowing one model family to serve many simulations. The README provides quick paths for pulling models (e.g., via Hugging Face access), then running energy/force predictions on GPU or CPU. -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
5
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. -
6
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. -
7
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. -
8
Minkowski Engine
Auto-diff neural network library for high-dimensional sparse tensors
The Minkowski Engine is an auto-differentiation library for sparse tensors. It supports all standard neural network layers such as convolution, pooling, unspooling, and broadcasting operations for sparse tensors. The Minkowski Engine supports various functions that can be built on a sparse tensor. We list a few popular network architectures and applications here. To run the examples, please install the package and run the command in the package root directory. Compressing a neural network to speed up inference and minimize memory footprint has been studied widely. One of the popular techniques for model compression is pruning the weights in convnets, is also known as sparse convolutional networks. Such parameter-space sparsity used for model compression compresses networks that operate on dense tensors and all intermediate activations of these networks are also dense tensors. -
9
NN-SVG
Publication-ready NN-architecture schematics
Illustrations of Neural Network architectures are often time-consuming to produce, and machine learning researchers all too often find themselves constructing these diagrams from scratch by hand. NN-SVG is a tool for creating Neural Network (NN) architecture drawings parametrically rather than manually. It also provides the ability to export those drawings to Scalable Vector Graphics (SVG) files, suitable for inclusion in academic papers or web pages. The tool provides the ability to generate figures of three kinds: classic Fully-Connected Neural Network (FCNN) figures, Convolutional Neural Network (CNN) figures of the sort introduced in the LeNet paper, and Deep Neural Network figures following the style introduced in the AlexNet paper. The former two are accomplished using the D3 javascript library and the latter with the javascript library Three.js. NN-SVG provides the ability to style the figure to the user's liking via many size, color, and layout parameters. -
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
10
Neural Network Intelligence
AutoML toolkit for automate machine learning lifecycle
Neural Network Intelligence is an open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning. NNI (Neural Network Intelligence) is a lightweight but powerful toolkit to help users automate feature engineering, neural architecture search, hyperparameter tuning and model compression. The tool manages automated machine learning (AutoML) experiments, dispatches and runs experiments' trial jobs generated by tuning algorithms to search the best neural architecture and/or hyper-parameters in different training environments like Local Machine, Remote Servers, OpenPAI, Kubeflow, FrameworkController on K8S (AKS etc.) DLWorkspace (aka. DLTS) AML (Azure Machine Learning) and other cloud options. NNI provides CommandLine Tool as well as an user friendly WebUI to manage training experiements. -
11
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. -
12
CRFasRNN
Semantic image segmentation method described in the ICCV 2015 paper
CRF-RNN is a deep neural architecture that integrates fully connected Conditional Random Fields (CRFs) with Convolutional Neural Networks (CNNs) by reformulating mean-field CRF inference as a Recurrent Neural Network. This fusion enables end-to-end training via backpropagation for semantic image segmentation tasks, eliminating the need for separate, offline post-processing steps. Our work allows computers to recognize objects in images, what is distinctive about our work is that we also recover the 2D outline of objects. Currently we have trained this model to recognize 20 classes. This software allows you to test our algorithm on your own images – have a try and see if you can fool it, if you get some good examples you can send them to us. CRF-RNN has been developed as a custom Caffe layer named MultiStageMeanfieldLayer. Usage of this layer in the model definition prototxt file looks the following. Check the matlab-scripts or the python-scripts folder for more detailed examples. -
13
ConvNetJS
Deep learning in Javascript to train convolutional neural networks
ConvNetJS is a Javascript library for training Deep Learning models (Neural Networks) entirely in your browser. Open a tab and you're training. No software requirements, no compilers, no installations, no GPUs, no sweat. ConvNetJS is an implementation of Neural networks, together with nice browser-based demos. It currently supports common Neural Network modules (fully connected layers, non-linearities), classification (SVM/Softmax) and Regression (L2) cost functions, ability to specify and train Convolutional Networks that process images, and experimental Reinforcement Learning modules, based on Deep Q Learning. The library allows you to formulate and solve Neural Networks in Javascript. If you would like to add features to the library, you will have to change the code in src/ and then compile the library into the build/ directory. The compilation script simply concatenates files in src/ and then minifies the result. -
14
DeepDream
This repository contains IPython Notebook with sample code
DeepDream is a small, educational repository that accompanies Google’s original “Inceptionism” blog post by providing a runnable IPython/Jupyter notebook that demonstrates how to “dream” through a convolutional neural network. The notebook shows how to take a trained vision model and iteratively amplify patterns the network detects, producing the hallmark surreal, hallucinatory visuals. It walks through loading a pretrained network, selecting layers and channels to maximize, computing gradients with respect to the input image, and applying multi-scale “octave” processing to reveal fine and coarse patterns. The code is intentionally compact and exploratory, encouraging users to tweak layers, step sizes, and scales to influence the aesthetic. Although minimal, it illustrates important concepts like feature visualization, activation maximization, and the effect of different receptive fields on the final image. -
15
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. We provide reference implementations of various sequence modeling papers. Recent work by Microsoft and Google has shown that data parallel training can be made significantly more efficient by sharding the model parameters and optimizer state across data parallel workers. These ideas are encapsulated in the new FullyShardedDataParallel (FSDP) wrapper provided by fairscale. Fairseq can be extended through user-supplied plug-ins. Models define the neural network architecture and encapsulate all of the learnable parameters. Criterions compute the loss function given the model outputs and targets. Tasks store dictionaries and provide helpers for loading/iterating over Datasets, initializing the Model/Criterion and calculating the loss. -
16
Forecasting Best Practices
Time Series Forecasting Best Practices & Examples
Time series forecasting is one of the most important topics in data science. Almost every business needs to predict the future in order to make better decisions and allocate resources more effectively. This repository provides examples and best practice guidelines for building forecasting solutions. The goal of this repository is to build a comprehensive set of tools and examples that leverage recent advances in forecasting algorithms to build solutions and operationalize them. Rather than creating implementations from scratch, we draw from existing state-of-the-art libraries and build additional utilities around processing and featuring the data, optimizing and evaluating models, and scaling up to the cloud. The examples and best practices are provided as Python Jupyter notebooks and R markdown files and a library of utility functions. -
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
Lightweight' GAN
Implementation of 'lightweight' GAN, proposed in ICLR 2021
Implementation of 'lightweight' GAN proposed in ICLR 2021, in Pytorch. The main contribution of the paper is a skip-layer excitation in the generator, paired with autoencoding self-supervised learning in the discriminator. Quoting the one-line summary "converge on single gpu with few hours' training, on 1024 resolution sub-hundred images". Augmentation is essential for Lightweight GAN to work effectively in a low data setting. You can test and see how your images will be augmented before they pass into a neural network (if you use augmentation). The general recommendation is to use suitable augs for your data and as many as possible, then after some time of training disable the most destructive (for image) augs. You can turn on automatic mixed precision with one flag --amp. You should expect it to be 33% faster and save up to 40% memory. Aim is an open-source experiment tracker that logs your training runs, and enables a beautiful UI to compare them. -
19
MIVisionX
Set of comprehensive computer vision & machine intelligence libraries
MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX delivers highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions along with Convolution Neural Net Model Compiler & Optimizer supporting ONNX, and Khronos NNEF™ exchange formats. The toolkit allows for rapid prototyping and deployment of optimized computer vision and machine learning inference workloads on a wide range of computer hardware, including small embedded x86 CPUs, APUs, discrete GPUs, and heterogeneous servers. AMD OpenVX is a highly optimized open-source implementation of the Khronos OpenVX™ 1.3 computer vision specification. It allows for rapid prototyping as well as fast execution on a wide range of computer hardware, including small embedded x86 CPUs and large workstation discrete GPUs. -
20
MMdnn
Tools to help users inter-operate among deep learning frameworks
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML. MMdnn is a comprehensive and cross-framework tool to convert, visualize and diagnose deep learning (DL) models. The "MM" stands for model management, and "dnn" is the acronym of deep neural network. We implement a universal converter to convert DL models between frameworks, which means you can train a model with one framework and deploy it with another. During the model conversion, we generate some code snippets to simplify later retraining or inference. We provide a model collection to help you find some popular models. We provide a model visualizer to display the network architecture more intuitively. We provide some guidelines to help you deploy DL models to another hardware platform. -
21
Mixup-CIFAR10
mixup: Beyond Empirical Risk Minimization
mixup-cifar10 is the official PyTorch implementation of “mixup: Beyond Empirical Risk Minimization” (Zhang et al., ICLR 2018), a foundational paper introducing mixup, a simple yet powerful data augmentation technique for training deep neural networks. The core idea of mixup is to generate synthetic training examples by taking convex combinations of pairs of input samples and their labels. By interpolating both data and labels, the model learns smoother decision boundaries and becomes more robust to noise and adversarial examples. This repository implements mixup for the CIFAR-10 dataset, showcasing its effectiveness in improving generalization, stability, and calibration of neural networks. The approach acts as a regularizer, encouraging linear behavior in the feature space between samples, which helps reduce overfitting and enhance performance on unseen data. -
22
NanoNeuron
NanoNeuron is 7 simple JavaScript functions
Nano-Neuron is a didactic project that reduces the idea of a neuron to a handful of tiny JavaScript functions so learners can see “learning” in action without heavy frameworks. It demonstrates how a scalar input can be linearly transformed with a weight and bias, then adjusted via gradient updates to fit a simple mapping such as Celsius-to-Fahrenheit conversion. The code emphasizes readability over performance, inviting you to step through calculations and watch parameters converge. Because every concept is expressed in a few lines, it’s easy to tinker—change learning rates, swap cost functions, or visualize error curves. The repository bridges the gap between formulae and intuition by making each update transparent and observable. It’s ideal for absolute beginners who want to internalize core ideas before moving on to multi-layer networks and libraries. -
23
NeuMan
Neural Human Radiance Field from a Single Video (ECCV 2022)
NeuMan is a reference implementation that reconstructs both an animatable human and its background scene from a single monocular video using neural radiance fields. It supports novel view and novel pose synthesis, enabling compositional results like transferring reconstructed humans into new scenes. The pipeline separates human/body and environment, learning consistent geometry and appearance to support animation. Demos showcase sequences such as dance and handshake, and the code provides guidance for running evaluations and rendering. As a research release, it serves both as a baseline and as a starting point for work on human-centric NeRFs. The emphasis is on practical reconstruction quality from minimal capture setups. Compositional outputs to blend humans and backgrounds. Novel view and novel pose synthesis from learned radiance fields. -
24
Neural Network Visualization
Project for processing neural networks and rendering to gain insights
nn_vis is a minimalist visualization tool for neural networks written in Python using OpenGL and Pygame. It provides an interactive, graphical representation of how data flows through neural network layers, offering a unique educational experience for those new to deep learning or looking to explain it visually. By animating input, weights, activations, and outputs, the tool demystifies neural network operations and helps users intuitively grasp complex concepts. Its lightweight codebase is great for customization and teaching purposes. -
25
PyG
Graph Neural Network Library for PyTorch
PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data. It consists of various methods for deep learning on graphs and other irregular structures, also known as geometric deep learning, from a variety of published papers. In addition, it consists of easy-to-use mini-batch loaders for operating on many small and single giant graphs, multi GPU-support, DataPipe support, distributed graph learning via Quiver, a large number of common benchmark datasets (based on simple interfaces to create your own), the GraphGym experiment manager, and helpful transforms, both for learning on arbitrary graphs as well as on 3D meshes or point clouds. All it takes is 10-20 lines of code to get started with training a GNN model (see the next section for a quick tour).
