Open Source Python Neural Network Libraries
Sort By:
Python Neural Network Libraries
View 49 business solutionsBrowse free open source Python Neural Network Libraries and projects below. Use the toggles on the left to filter open source Python Neural Network Libraries by OS, license, language, programming language, and project status.
-
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
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. -
2
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. -
3
SFD
S³FD: Single Shot Scale-invariant Face Detector, ICCV, 2017
S³FD (Single Shot Scale-invariant Face Detector) is a real-time face detection framework designed to handle faces of various sizes with high accuracy using a single deep neural network. Developed by Shifeng Zhang, S³FD introduces a scale-compensation anchor matching strategy and enhanced detection architecture that makes it especially effective for detecting small faces—a long-standing challenge in face detection research. The project builds upon the SSD framework in Caffe, with modifications tailored for face detection tasks. It includes training scripts, evaluation code, and pre-trained models that achieve strong results on popular benchmarks such as AFW, PASCAL Face, FDDB, and WIDER FACE. The framework is optimized for speed and accuracy, making it suitable for both academic research and practical applications in computer vision. -
4
cnn-for-image-retrieval is a research-oriented project that demonstrates the use of convolutional neural networks (CNNs) for image retrieval tasks. The repository provides implementations of CNN-based methods to extract feature representations from images and use them for similarity-based retrieval. It focuses on applying deep learning techniques to improve upon traditional handcrafted descriptors by learning features directly from data. The code includes training and evaluation scripts that can be adapted for custom datasets, making it useful for experimenting with retrieval systems in computer vision. By leveraging CNN architectures, the project showcases how learned embeddings can capture semantic similarity across varied images. This resource serves as both an educational reference and a foundation for further exploration in image retrieval research.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
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. -
6
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. -
7
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. -
8
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. -
9
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. -
Build Securely on Azure with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
10
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) -
11
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. -
12
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. -
13
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. -
14
SVoice (Speech Voice Separation)
We provide a PyTorch implementation of the paper Voice Separation
SVoice is a PyTorch-based implementation of Facebook Research’s study on speaker voice separation as described in the paper “Voice Separation with an Unknown Number of Multiple Speakers.” This project presents a deep learning framework capable of separating mixed audio sequences where several people speak simultaneously, without prior knowledge of how many speakers are present. The model employs gated neural networks with recurrent processing blocks that disentangle voices over multiple computational steps, while maintaining speaker consistency across output channels. Separate models are trained for different speaker counts, and the largest-capacity model dynamically determines the actual number of speakers in a mixture. The repository includes all necessary scripts for training, dataset preparation, distributed training, evaluation, and audio separation. -
15
Fast Artificial Neural Network Library is a free open source neural network library, which implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution in both fixed and floating point are supported. It includes a framework for easy handling of training data sets. It is easy to use, versatile, well documented, and fast. Bindings to more than 15 programming languages are available. An easy to read introduction article and a reference manual accompanies the library with examples and recommendations on how to use the library. Several graphical user interfaces are also available for the library.
-
16
PrettyTensor
Pretty Tensor: Fluent Networks in TensorFlow
Pretty Tensor is a high-level API built on top of TensorFlow that simplifies the process of creating and managing deep learning models. It wraps TensorFlow tensors in a chainable object syntax, allowing developers to build multi-layer neural networks with concise and readable code. Pretty Tensor preserves full compatibility with TensorFlow’s core functionality while providing syntactic sugar for defining complex architectures such as convolutional and recurrent networks. The library’s design emphasizes flexibility and modularity, supporting advanced features like default scopes, parameter templates, and variable reuse. It also allows easy integration with custom operations and third-party libraries, making it ideal for both research experimentation and production-grade modeling. By combining TensorFlow’s power with an intuitive builder-style API, Pretty Tensor accelerates model development without sacrificing transparency or control. -
17
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). -
18
DeepXDE
A library for scientific machine learning & physics-informed learning
DeepXDE is a library for scientific machine learning and physics-informed learning. DeepXDE includes the following algorithms. Physics-informed neural network (PINN). Solving different problems. Solving forward/inverse ordinary/partial differential equations (ODEs/PDEs) [SIAM Rev.] Solving forward/inverse integro-differential equations (IDEs) [SIAM Rev.] fPINN: solving forward/inverse fractional PDEs (fPDEs) [SIAM J. Sci. Comput.] NN-arbitrary polynomial chaos (NN-aPC): solving forward/inverse stochastic PDEs (sPDEs) [J. Comput. Phys.] PINN with hard constraints (hPINN): solving inverse design/topology optimization [SIAM J. Sci. Comput.] Residual-based adaptive sampling [SIAM Rev., arXiv] Gradient-enhanced PINN (gPINN) [Comput. Methods Appl. Mech. Eng.] PINN with multi-scale Fourier features [Comput. Methods Appl. Mech. Eng.] -
19
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. -
20
Flax
Flax is a neural network library for JAX
Flax is a flexible neural-network library for JAX that embraces functional programming while offering ergonomic module abstractions. Its design separates pure computation from state by threading parameter collections and RNGs explicitly, enabling reproducibility, transformation, and easy experimentation with JAX transforms like jit, pmap, and vmap. Modules define parameterized computations, but initialization and application remain side-effect free, which pairs naturally with JAX’s staging and compilation model. Flax emphasizes composability: optimizers, training loops, and checkpointing are provided as examples or utilities rather than monolithic frameworks, encouraging research-friendly customization. The library is widely used in vision, language, and reinforcement learning, often serving as a thin layer atop NumPy-like JAX primitives. Tutorials and examples show patterns for multi-host training, mixed precision, and advanced input pipelines that scale from laptops to TPUs. -
21
NLP Architect
A model library for exploring state-of-the-art deep learning
NLP Architect is an open-source Python library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing and Natural Language Understanding neural networks. The library includes our past and ongoing NLP research and development efforts as part of Intel AI Lab. NLP Architect is designed to be flexible for adding new models, neural network components, data handling methods, and for easy training and running models. NLP Architect is a model-oriented library designed to showcase novel and different neural network optimizations. The library contains NLP/NLU-related models per task, different neural network topologies (which are used in models), procedures for simplifying workflows in the library, pre-defined data processors and dataset loaders and misc utilities. The library is designed to be a tool for model development: data pre-processing, build model, train, validate, infer, save or load a model. -
22
Nerfies
This is the code for Deformable Neural Radiance Fields
Nerfies demonstrates deformation-aware neural radiance fields that reconstruct and render dynamic, real-world scenes from casual video. Instead of assuming a static world, the method learns a canonical space plus a deformation field that maps changing poses or expressions back to that space during training. This lets the system generate photorealistic novel views of nonrigid subjects—faces, bodies, cloth—while preserving fine detail and consistent lighting. The training pipeline handles imperfect captures by modeling camera poses, exposure variations, and background segmentation, producing stable geometry and appearance. A set of utilities manages dataset preparation, pose estimation, and checkpoints so researchers can reproduce results on their own footage. The work sits at the intersection of graphics and vision, showing how learned volumetric rendering can handle human motion without dense markers or studio rigs. -
23
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. -
24
Opacus
Training PyTorch models with differential privacy
Opacus is a library that enables training PyTorch models with differential privacy. It supports training with minimal code changes required on the client, has little impact on training performance, and allows the client to online track the privacy budget expended at any given moment. Vectorized per-sample gradient computation that is 10x faster than micro batching. Supports most types of PyTorch models and can be used with minimal modification to the original neural network. Open source, modular API for differential privacy research. Everyone is welcome to contribute. ML practitioners will find this to be a gentle introduction to training a model with differential privacy as it requires minimal code changes. Differential Privacy researchers will find this easy to experiment and tinker with, allowing them to focus on what matters. -
25
captcha_break
Identification codes
This project will use Keras to build a deep convolutional neural network to identify the captcha verification code. It is recommended to use a graphics card to run the project. The following visualization codes are jupyter notebookall done in . If you want to write a python script, you can run it normally with a little modification. Of course, you can also remove these visualization codes. captcha is a library written in python to generate verification codes. It supports image verification codes and voice verification codes. We use its function of generating image verification codes. First, we set our verification code format to numbers and capital letters, and generate a string of verification codes. It is well known that tensorflow occupies all video memory by default, which is not conducive to us conducting multiple experiments at the same time, so we can use the following code when tensorflow uses the video memory it needs instead of directly occupying all video memory.
