Auto-PyTorch
auto-sklearn
Auto-PyTorch | auto-sklearn | |
---|---|---|
4 | 3 | |
2,282 | 7,409 | |
1.0% | 0.4% | |
0.0 | 1.8 | |
25 days ago | 4 months ago | |
Python | Python | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Auto-PyTorch
-
[Project] AMLTK: A framework for building your own AutoML (AutoSklearn authors)
We took some of the lessons learned while building AutoSklearn and AutoPytorch, the good, the bad and the ugly and made a library that to enable the next generation of open-source AutoML tools, to allow them to be research-able but also efficient and scalable. We have some future plans and on-going work with this and we'd like to gather any feedback the community might have!
- What are sota hyperparameter optimization methods?
-
A question for any AI programmers
Well it seems so, yes. Take a look here.
-
What free AutoML library do you recommend?
For more information, you can checkout the github page AutoPytorch. Disclaimer: its under development and there can be potentially many undiscovered bugs which we will be happy to resolve as quick as possible. I recommend using the development branch which is a complete overhaul of the library from scratch.
auto-sklearn
-
Why not AutoML every tabular data?
Efficiency Ignoring the feature engineering aspects aside, a typical data scientist workflow involves trying out the different models. Some of the AutoML modules like H2O AutoML, AutoSklearn does this for you, and allow you to interpret your models. All these save so much time experimenting with the standard models.
- [R] Regularization is all you Need: Simple Neural Nets can Excel on Tabular Data
-
What free AutoML library do you recommend?
If you want a more stable AutoML library, i’ll suggest auto-sklearn which optimises performance of sklearn learning algorithms.
What are some alternatives?
autogluon - AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data [Moved to: https://github.com/autogluon/autogluon]
autogluon - Fast and Accurate ML in 3 Lines of Code
lightning-flash - Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains
tune-sklearn - A drop-in replacement for Scikit-Learn’s GridSearchCV / RandomizedSearchCV -- but with cutting edge hyperparameter tuning techniques.
carefree-learn - Deep Learning ❤️ PyTorch
syne-tune - Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
cleanrl - High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
OCTIS - OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
SMAC3 - SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
pymarl2 - Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)