Skorch is an open-source Python library that provides a scikit-learn compatible interface for training neural networks using PyTorch. It simplifies deep learning workflows by combining PyTorch's flexibility with the familiar scikit-learn API.

Features of Skorch:

• Provides scikit-learn-style interface (fit, predict, score) for PyTorch models.
• Supports integration with scikit-learn tools like GridSearchCV, Pipeline, and cross-validation.
• Allows use of custom PyTorch nn.Module models with minimal boilerplate.
• Includes callbacks, metrics, learning rate schedulers, and checkpointing for easy training control.
• Facilitates rapid prototyping and experimentation with deep learning models.
• Open-source and actively maintained, widely used for research and machine learning projects.

To check the installed version of Skorch on Ubuntu 24.04, run these commands in your environment:

$ sudo su
$ sudo apt update
$ source /opt/skorch_venv/bin/activate
$ pip show skorch"

Disclaimer: Skorch is released under the BSD 3-Clause License and maintained by the Skorch and PyTorch communities. Users are responsible for correct usage in their specific applications. Always refer to the official Skorch documentation for the most accurate and up-to-date information.