TensorFlowtensorflow/tensorflow
Open source software library for numerical computation using data flow graphs.
251 libraries, 105 updated this year
Libraries for building and training neural networks. The center of gravity is PyTorch, TensorFlow and JAX, with Keras as a high-level layer that now runs on all three. Around them sit model libraries such as Hugging Face Transformers for language and timm for images, and training helpers like PyTorch Lightning and fastai that remove boilerplate from the training loop.
251 libraries
Open source software library for numerical computation using data flow graphs.
A deep learning library containing thousands of pre-trained models on different tasks. The goto place for anything related to Large Language Models.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
OpenCV has C++, C, Python, Java and MATLAB interfaces and supports Windows, Linux, Android and Mac OS.
High-level neural networks frontend for TensorFlow, CNTK and Theano.
Ultralytics' YOLOv8 implementation with C++ support for real-time object detection and tracking, optimized for edge devices.
Streamlit is an framework to create beautiful data apps in hours, not weeks.
RLlib is an industry level, highly scalable RL library for tf and torch, based on Ray. It's used by companies like Amazon and Microsoft to solve real-world decision making problems at scale.
An open-source deep learning system for large-scale model training and inference with high efficiency and low cost.
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more.
JAX is Autograd and XLA, brought together for high-performance machine learning research.
Qdrant is open source vector similarity search engine with extended filtering support, written in Rust.
FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework.
A deep learning framework developed with cleanliness, readability, and speed in mind.
Implementations of Machine Learning models from scratch in Python with a focus on transparency. Aims to showcase the nuts and bolts of ML in an accessible way.
The lightweight PyTorch wrapper for high-performance AI research.
High-level wrapper built on the top of Pytorch which supports vision, text, tabular data and collaborative filtering.
Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.
FAIR's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework.
Examples and best practices for building recommendation systems, provided as Jupyter notebooks. The repo contains some of the latest state of the art algorithms from Microsoft Research as well as from other companies and institutions.
An easier way to build neural search in the cloud. Compatible with Jupyter Notebooks.
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.
A WebGL accelerated, browser based JavaScript library for training and deploying ML models.
Code samples for my book "Neural Networks and Deep Learning".
The Computational Network Toolkit (CNTK) by Microsoft Research, is a unified deep-learning toolkit that describes neural networks as a series of computational steps via a directed graph.
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals
Free and open source face recognition with deep neural networks.
А fast and framework agnostic image augmentation library that implements a diverse set of augmentation techniques. Supports classification, segmentation, detection out of the box. Was used to win a number of Deep Learning competitions at Kaggle, Topcoder and those that were a part of the CVPR workshops.
An offline speech recognition toolkit with C++ support, designed for low-resource devices and multiple languages.
Neural networks in JavaScript - continued community fork of Brain.
DLib has C++ and Python interfaces for face detection and training general object detectors.
Scalable deep learning for industry with parallel GPUs.
A C++ library for unsupervised text tokenization and detokenization, widely used in modern NLP models.
A PyTorch-based toolkit that offers pre-trained segmentation models for computer vision tasks. It simplifies the development of image segmentation applications by providing a collection of popular architecture implementations, such as UNet and PSPNet, along with pre-trained weights, making it easier for researchers and developers to achieve high-quality pixel-level object segmentation in images.
Machine learning experiment tracking, dataset versioning, hyperparameter search, visualization, and collaboration
ConvNetJS is a JavaScript library for training Deep Learning models
Fast State-of-the-Art Tokenizers optimized for Research and Production
Machine learning from Apple. Turi Create simplifies the development of custom machine learning models. You don't have to be a machine learning expert to add recommendations, object detection, image classification, image similarity or activity classification to your app.
AutoML for Image, Text, Tabular, Time-Series, and MultiModal Data.
> Python Outlier Detection, comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. Featured for Advanced models, including Neural Networks/Deep Learning and Outlier Ensembles.
A Python library for secure and private Deep Learning built on PyTorch and TensorFlow.
ESPnet is an end-to-end speech processing toolkit for tasks like speech recognition, translation, and enhancement, using PyTorch and Kaldi-style data processing.
Deep learning operations reinvented (for pytorch, tensorflow, jax and others).
Deep learning library featuring a higher-level API for TensorFlow.
Fastest unstructured dataset management for TensorFlow/PyTorch. Stream & version-control data. Store even petabyte-scale data in a single numpy-like array on the cloud accessible on any machine. Visit activeloop.ai for more info.
Toolkit for package and deploy machine learning models for serving in production