Skorch
A scikit-learn compatible neural network library that wraps pytorch
pytorch skorch scikit-learn code library

The goal of skorch is to make it possible to use PyTorch with sklearn. This is achieved by providing a wrapper around PyTorch that has an sklearn interface. In that sense, skorch is the spiritual successor to nolearn, but instead of using Lasagne and Theano, it uses PyTorch.

skorch also provides many convenient features, among others: • Learning rate schedulers (Warm restarts, cyclic LR and many more) • Scoring using sklearn (and custom) scoring functions • Early stopping • Checkpointing • Parameter freezing/unfreezing • Progress bar (for CLI as well as jupyter) • Automatic inference of CLI parameters

Don't forget to tag @skorch-dev in your comment, otherwise they may not be notified.

Authors
Organization for maintaining skorch, a sklearn wrapper for PyTorch
Share this project
Similar projects
PyTorch Tutorial for Deep Learning Researchers
This repository provides tutorial code for deep learning researchers to learn PyTorch.
Generate Boolean (Yes/No) Questions From Any Content
Question generation algorithm trained on the BoolQ dataset using T5 text-to-text transformer model.
VirTex: Learning Visual Representations from Textual Annotations
We train CNN+Transformer from scratch from COCO, transfer the CNN to 6 downstream vision tasks, and exceed ImageNet features despite using 10x fewer ...
Machine Learning Basics
A practical set of notebooks on machine learning basics, implemented in both TF2.0 + Keras and PyTorch.