hyperparameter-search

🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.

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

Determined: Deep Learning Training Platform

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

PaddleSlim is an open-source library for deep model compression and architecture search.

Sequential Model-based Algorithm Configuration

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

Hyperparameter optimization that enables researchers to experiment, visualize, and scale quickly.

Library for Semi-Automated Data Science

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

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

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

Black-box optimization library

Distribution transparent Machine Learning experiments on Apache Spark

🔬 Some personal research code on analyzing CNNs. Started with a thorough exploration of Stanford's Tiny-Imagenet-200 dataset.

Hyperparameter search for AllenNLP - powered by Ray TUNE

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

An AutoRecSys library for Surprise. Automate algorithm selection and hyperparameter tuning 🚀

Code examples for https://blog.floydhub.com/guide-to-hyperparameters-search-for-deep-learning-models/

sharpDARTS: Faster and More Accurate Differentiable Architecture Search

Hyperparameters-Optimization

Platform + GUI for hyperparameter optimization of recurrent neural networks (MATLAB).

Sentiment analysis for amazon product reviews using NLTK, Scikit-Learn, and Keras. Using hyperparameter search and LSTM, our best model achieves ~96% accuracy.

sklearn wrapper for Hyperopt

hyperparameter search for machine learning

The objective of the dataset is to diagnostically predict whether or not a patient has diabetes, based on certain diagnostic measurements included in the dataset