102 Open source projects that are alternatives of or similar to Hypersearch

Gradient based hyperparameter optimization & meta-learning package for TensorFlow

A simple, extensible library for developing AutoML systems

Time Series Cross-Validation -- an extension for scikit-learn

mlmodels : Machine Learning and Deep Learning Model ZOO for Pytorch, Tensorflow, Keras, Gluon models...

DeepArchitect: Automatically Designing and Training Deep Architectures

Milano is a tool for automating hyper-parameters search for your models on a backend of your choice.

Population Based Training (in PyTorch with sqlite3). Status: Unsupported

State-of-the art Automated Machine Learning python library for Tabular Data

Notes for Deep Learning Specialization Courses led by Andrew Ng.

[UNMAINTAINED] Automated machine learning for analytics & production

Bilevel Optimization Library in Python for Multi-Task and Meta Learning

A toolset for black-box hyperparameter optimisation.

DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks

A fully decentralized hyperparameter optimization framework

A general, modular, and programmable architecture search framework

Hyperparameter Optimization for TensorFlow, Keras and PyTorch

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Efficient Hyperparameter Optimization of Deep Learning Algorithms Using Deterministic RBF Surrogates

Auto-optimizing a neural net (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.

Python library for CMA Evolution Strategy.

A web-based application for quick, scalable, and automated hyperparameter tuning and stacked ensembling in Python.

Determined: Deep Learning Training Platform

Purely functional genetic algorithms for multi-objective optimisation

Simple, but essential Bayesian optimization package

A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

MIT DeepTraffic top 2% solution (75.01 mph) 🚗.

Automated Machine Learning Pipeline with Feature Engineering and Hyper-Parameters Tuning 🚀

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

Simple and reliable optimization with local, global, population-based and sequential techniques in numerical discrete search spaces.

A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.

Python library to easily log experiments and parallelize hyperparameter search for neural networks

Easy hyperparameter optimization and automatic result saving across machine learning algorithms and libraries

Automated Machine Learning with scikit-learn

Sequential Model-based Algorithm Configuration

Tuning hyperparams fast with Hyperband

Implementation of hyperparameter optimization/tuning methods for machine learning & deep learning models (easy&clear)

Auto Tune Models - A multi-tenant, multi-data system for automated machine learning (model selection and tuning).

A hyperparameter optimization framework

a distributed Hyperband implementation on Steroids

Experimental Global Optimization Algorithm

A Sklearn-like Framework for Hyperparameter Tuning and AutoML in Deep Learning projects. Finally have the right abstractions and design patterns to properly do AutoML. Let your pipeline steps have hyperparameter spaces. Enable checkpoints to cut duplicate calculations. Go from research to production environment easily.

Sequential model-based optimization with a `scipy.optimize` interface