Cadene/pretrained-models.pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

9099 stars · 1806 forks observed · 2026-08-28

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

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

library · maturity maintenance

machine-learning deep-learning machine-learning computer-vision image-processing python pytorch pretrained-models convnets imagenet transfer-learning computer-vision

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Cadene/pretrained-models.pytorch")