automl/Auto-PyTorch
Automatic architecture search and hyperparameter optimization for PyTorch
This helps data professionals automatically build high-performing deep learning models for classification, regression, and time series forecasting. You provide your tabular or time series data, and it outputs a optimized model ensemble that accurately predicts outcomes or forecasts future values. It's designed for data scientists and analysts who need to quickly deploy robust deep learning solutions without extensive manual tuning.
2,534 stars. No commits in the last 6 months.
Use this if you need to build accurate deep learning models for tabular or time series data but want to automate the complex process of selecting architectures and fine-tuning hyperparameters.
Not ideal if your primary need is for deep learning models on unstructured data types like images, video, or raw text, as it's currently focused on tabular and time series datasets.
Stars
2,534
Forks
304
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/automl/Auto-PyTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
optuna/optuna
A hyperparameter optimization framework
keras-team/keras-tuner
A Hyperparameter Tuning Library for Keras
KernelTuner/kernel_tuner
Kernel Tuner
syne-tune/syne-tune
Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
deephyper/deephyper
DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning