# Cadene/pretrained-models.pytorch

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Repository: https://github.com/Cadene/pretrained-models.pytorch
Canonical: https://ross.abutalabs.com/products/pretrained-modelspytorch
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: imagenet, resnet, resnext, pretrained, pytorch, inception
Last push: 2022-04-22T09:08:45+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3433, "days_push": 1594, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9099, forks 1806 (observed 2026-08-28T04:10:28.370147+00:00)

## What it is
A Python library providing pretrained ConvNet models (ResNet, ResNeXt, InceptionV4, Xception, NASNet, SENet, DPN, etc.) for PyTorch behind a unified API inspired by torchvision. It is mainly aimed at reproducing research results and transfer learning setups with ImageNet weights.

## Use cases
- load pretrained imagenet models in pytorch
- transfer learning with pretrained convnets
- reproduce research paper results on imagenet
- compute imagenet validation accuracy for pretrained models
- extract features from pretrained cnn backbones
- compare different cnn architectures with one api

## When to choose
- you need a wide variety of pretrained CNN architectures in PyTorch with a single consistent API
- you want to reproduce published ImageNet results or use classic backbones for transfer learning

## When to avoid
- you need modern architectures or the latest weights — use timm or torchvision instead
- the project has seen little activity since 2018 and its last release was 2022, so it may lag newer PyTorch versions

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, computer-vision, image-processing
- platform: python
- tags: pytorch, pretrained-models, convnets, imagenet, transfer-learning, computer-vision

## Member repositories
- Cadene/pretrained-models.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.370147+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 2026-08-29T17:23:59.099593+00:00, confidence not recorded.
  - readme: https://github.com/Cadene/pretrained-models.pytorch (fetched 2026-08-28T04:10:28.370147+00:00, sha 452363effa22)
- Data as of 2026-08-30T08:39:29.467469+00:00.