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

This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.

The world's cleanest AutoML library ✨ - Do hyperparameter tuning with the right pipeline abstractions to write clean deep learning production pipelines. Let your pipeline steps have hyperparameter spaces. Design steps in your pipeline like components. Compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks and MLOps enviro…

Tuning hyperparams fast with Hyperband

ML hyperparameters tuning and features selection, using evolutionary algorithms.

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

Configure Python functions explicitly and safely

A library for composing end-to-end tunable machine learning pipelines.

Adventures using keras on Google's Cloud ML Engine

An interactive framework to visualize and analyze your AutoML process in real-time.

Deep learning, architecture and hyper parameters search with genetic algorithms

Easily declare large spaces of (keras) neural networks and run (hyperopt) optimization experiments on them.

A Machine Learning Approach to Forecasting Remotely Sensed Vegetation Health in Python

Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent

⚡️ AllenNLP plugin for adding subcommands to use Optuna, making hyperparameter optimization easy

OptKeras: wrapper around Keras and Optuna for hyperparameter optimization

AutoML - Hyper parameters search for scikit-learn pipelines using Microsoft NNI

Meta Transfer Learning for Few Shot Semantic Segmentation using U-Net

How optimizer and learning rate choice affects training performance

🚀 Optuna visualization dashboard that lets you log and monitor hyperparameter sweep live.