skorch-dev/skorch

A scikit-learn compatible neural network library that wraps PyTorch

57
/ 100
Established

This tool helps machine learning engineers build and train neural networks using the familiar scikit-learn interface, even if they're using PyTorch under the hood. It takes your raw data and a defined neural network architecture, and outputs a trained model ready for predictions. The ideal users are data scientists and ML engineers who are comfortable with Python and scikit-learn's conventions but want to leverage PyTorch's flexibility for deep learning.

6,150 stars. Actively maintained with 2 commits in the last 30 days.

Use this if you want to integrate complex PyTorch neural networks into existing scikit-learn pipelines and workflows without rewriting extensive boilerplate code.

Not ideal if you prefer to build and manage your deep learning models purely within the PyTorch ecosystem without any scikit-learn abstraction.

machine-learning-engineering deep-learning model-training data-science predictive-modeling
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

6,150

Forks

405

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Feb 25, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/skorch-dev/skorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.