ML Libraries

Top

Web

Other

- βApache MXNet - Deep learning framework designed for both efficiency and flexibility. It allows you to mix symbolic and imperative programming to maximize efficiency and productivity.
- βcuML - Suite of libraries that implement machine learning algorithms and mathematical primitives functions that share compatible APIs with other RAPIDS projects.
- βauto-sklearn - Automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator.
- βlambda-ml - Small machine learning library aimed at providing simple, concise implementations of machine learning techniques and utilities.
- βscikit-learn - Python module for machine learning built on top of SciPy. (Tutorials) (Course) (Web) (HN)
- βMlxtend (machine learning extensions) - Python library of useful tools for the day-to-day data science tasks.
- βDeepLearning.scala - Simple library for creating complex neural networks from object-oriented and functional programming constructs.
- βVowpal Wabbit - Machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning. (Web) (Article)
- βKarate Club - General purpose community detection and network embedding library for research built on NetworkX.
- βFlexFlow - Distributed deep learning framework that supports flexible parallelization strategies.
- βDeepkit - Collaborative and real-time machine learning training suite: Experiment execution, tracking, and debugging.
- βimbalanced-learn - Python package offering a number of re-sampling techniques commonly used in datasets showing strong between-class imbalance.
- βDeepSpeed - Deep learning optimization library that makes distributed training easy, efficient, and effective.
- βAx - Accessible, general-purpose platform for understanding, managing, deploying, and automating adaptive experiments.
- βNNI (Neural Network Intelligence) - Lightweight but powerful toolkit to help users automate Feature Engineering, Neural Architecture Search, Hyperparameter Tuning and Model Compression.
- βLMfit-py - Non-Linear Least Squares Minimization, with flexible Parameter settings, based on scipy.optimize.leastsq, and with many additional classes and methods for curve fitting.
- βXGBoost - Optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework.
- βDMLC-Core - Common bricks library for building scalable and portable distributed machine learning.
- βLinear Models - Add linear models including instrumental variable and panel data models that are missing from statsmodels.
- βpescador - Library for streaming (numerical) data, primarily for use in machine learning applications.
- βTPOT (Tree-based Pipeline Optimization Tool) - Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming. (Docs)
- βGraKeL - Library that provides implementations of several well-established graph kernels. scikit-learn compatible.
- βNNFusion - Flexible and efficient DNN compiler that can generate high-performance executables from a DNN model description.
- βncnn - High-performance neural network inference computing framework optimized for mobile platforms.
- βscikit-rebate - Scikit-learn-compatible Python implementation of ReBATE, a suite of Relief-based feature selection algorithms for Machine Learning.
- βFedlearner - Collaborative machine learning frameowork that enables joint modeling of data distributed between institutions.
- βmodestpy - Facilitates parameter estimation in models compliant with Functional Mock-up Interface.
- βEvalML - AutoML library that builds, optimizes, and evaluates machine learning pipelines using domain-specific objective functions.
- βMindSpore - New open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
- βraster-deep-learning - ArcGIS built-in python raster functions for deep learning to get you started fast.
- βCausal Discovery Toolbox - Algorithms for graph structure recovery (including algorithms from the bnlearn, pcalg packages), mainly based out of observational data.
- βMNN - Blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba.
- βHaste - CUDA implementation of fused RNN layers with built-in DropConnect and Zoneout regularization.
- βcleanlab - Machine learning python package for learning with noisy labels and finding label errors in datasets.
- βdeeptime - Python library for analysis of time series data including dimensionality reduction, clustering, and Markov model estimation.
- βHyperactive - Hyperparameter optimization and meta-learning toolbox for convenient and fast prototyping of machine-learning models.
- βautofeat - Linear Prediction Model with Automated Feature Engineering and Selection Capabilities.
- βDistrax - Lightweight library of probability distributions and bijectors. It acts as a JAX-native reimplementation of a subset of TensorFlow Probability (TFP).
- βBackdoors 101 - PyTorch framework for state-of-the-art backdoor defenses and attacks on deep learning models.
- βMars - Tensor-based unified framework for large-scale data computation which scales Numpy, pandas, Scikit-learn and Python functions.
- βPySR - Simple, fast, and parallelized symbolic regression in Python/Julia via regularized evolution and simulated annealing.
- βSparseML - Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models.
- βOpenAI Python - Provides convenient access to the OpenAI API from applications written in Python.
- βdeepC - Vendor independent deep learning library, compiler and inference framework designed for small form-factor devices.
- βPetastorm - Enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format.
- βTriage - General Purpose Risk Modeling and Prediction Toolkit for Policy and Social Good Problems.
- βTransmogrifAI - End-to-end AutoML library for structured data written in Scala that runs on top of Apache Spark. (Web)
- βchitra - Multi-functional library for full-stack Deep Learning. It simplifies Model Building, API development, and Model Deployment.
- βpyltr - Python learning-to-rank toolkit with ranking models, evaluation metrics, data wrangling helpers, and more.
- βPhiFlow - Open-source simulation toolkit built for optimization and machine learning applications.
- βOpenVINO Toolkit - Deploy pre-trained deep learning models through a high-level C++ Inference Engine API integrated with application logic.
- βWILDS - Machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.
- βDeepSparse - Neural network inference engine that delivers GPU-class performance for sparsified models on CPUs.
- βNVTabular - Engineering and preprocessing library for tabular data that is designed to easily manipulate terabyte scale datasets and train deep learning (DL) based recommender systems.
- βFedJAX - JAX-based open source library for Federated Learning simulations that emphasizes ease-of-use in research.
- βMosaicML Composer - Library of methods, and ways to compose them together for more efficient ML training.
- βFeature Engine - Python library with multiple transformers to engineer and select features for use in machine learning models.
- βTorchArrow - torch.Tensor-like DataFrame library supporting multiple execution runtimes and Arrow as a common memory format.
- βFlexFlow - Distributed deep learning framework that supports flexible parallelization strategies.
- βT5X - Modular, composable, research-friendly framework for high-performance, configurable, self-service training.
- βPrivacy Lint - Library that allows you to perform a privacy analysis (Membership Inference) of your model in PyTorch.
- βNVIDIA Object Detection Toolkit (ODTK) - Fast and accurate single stage object detection with end-to-end GPU optimization.
- βPyPAL - Multiobjective active learning with tunable accuracy/efficiency tradeoff and clear stopping criterion.
- βimodels - Interpretable ML package for concise, transparent, and accurate predictive modeling (sklearn-compatible).
- βFLSim - Flexible, standalone library written in PyTorch that simulates FL settings with a minimal, easy-to-use API.
- βMiniTorch - DIY teaching library for machine learning engineers who wish to learn about the internal concepts underlying deep learning systems.
- βapricot - Implements submodular optimization for the purpose of selecting subsets of massive data sets to train machine learning models quickly.
- βNVIDIA DALI - GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
- βMIPLearn - Framework for solving discrete optimization problems using a combination of Mixed-Integer Linear Programming (MIP) and Machine Learning (ML).
- βExplainX - Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code.
- βkingly - Zero-cost state-machine library for robust, testable and portable user interfaces (most machines compile ~1-2KB).
- βchop - Optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.
- βjaxdf - JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations.

Last modified 10d ago