skorch-dev/skorch

Health v2 · maintenance only

Adoption not part of the score

6173 stars · 417 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

skorch is a Python library that wraps PyTorch neural networks in a scikit-learn compatible API, providing estimators like NeuralNetClassifier and NeuralNetRegressor. It lets you use sklearn pipelines, grid search, and cross-validation directly with PyTorch models.

Use cases

• train pytorch models with scikit-learn api
• use pytorch neural network in sklearn pipeline
• grid search hyperparameters of a pytorch model
• cross-validate a neural network with sklearn
• wrap huggingface transformer in sklearn estimator
• replace keras-style fit loop with sklearn-compatible classifier

When to choose

• you already use scikit-learn and want PyTorch models to fit into pipelines and grid search
• you want a simple fit/predict training loop without writing boilerplate PyTorch training code
• you need sklearn-compatible estimators for neural networks, including Hugging Face models

When to avoid

• you need fine-grained control over every step of the PyTorch training loop
• you are building large-scale or highly customized deep learning training pipelines
• you do not use scikit-learn conventions and prefer raw PyTorch

Facets

library · maturity active

machine-learning deep-learning machine-learning deep-learning data-science python scikit-learn pytorch neural-networks huggingface grid-search

Member repositories

For agents

markdown · JSON · MCP: product_card(name="skorch-dev/skorch")