# TorchEnsemble-Community/Ensemble-Pytorch

A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model.

Repository: https://github.com/TorchEnsemble-Community/Ensemble-Pytorch
Canonical: https://ross.abutalabs.com/products/ensemble-pytorch
Homepage: https://ensemble-pytorch.readthedocs.io
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: pytorch, pytorch-tutorial, ensemble-learning, ensemble, deeplearning, neural-networks, deep-learning, gradient-boosting, voting-classifier, bagging
Last push: 2024-06-16T13:18:31+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2548, "days_push": 808, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1037, forks 95 (observed 2026-08-28T04:03:19.453293+00:00)

## What it is
A unified ensemble learning framework for PyTorch that implements strategies like voting, bagging, and gradient boosting to improve deep learning model performance and robustness. It is part of the official PyTorch ecosystem and provides a scikit-learn-like API for training ensembles of neural networks.

## Use cases
- improve accuracy of a pytorch neural network with ensembling
- train a voting classifier of deep learning models
- apply gradient boosting with neural network base estimators
- run bagging on pytorch models
- reduce variance of a deep learning classifier
- compare ensemble methods on image classification

## When to choose
- you already use PyTorch and want ensemble methods with a familiar fit/predict API
- you need multiple ensemble strategies (voting, bagging, fusion, gradient boosting) in one library
- you want a maintained project from the official PyTorch ecosystem

## When to avoid
- you work outside PyTorch (e.g., TensorFlow or JAX)
- you need ensembles of non-neural models like decision trees - use scikit-learn instead
- you need distributed or highly scaled production ensembling beyond single-machine training

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: ensemble-learning, pytorch, bagging, gradient-boosting, voting-classifier, neural-networks

## Member repositories
- TorchEnsemble-Community/Ensemble-Pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.453293+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:04:21.641212+00:00, confidence not recorded.
  - readme: https://github.com/TorchEnsemble-Community/Ensemble-Pytorch (fetched 2026-08-28T04:03:19.453293+00:00, sha c3291346b251)
- Data as of 2026-08-30T08:39:29.467469+00:00.