rwightman/gen-efficientnet-pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1577 stars · 215 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch library providing generic implementations and pretrained weights for compute-efficient image classification models such as EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3/V2, MNASNet, FBNet, and Single-Path NAS. It supports ONNX and Caffe2 export and includes string-based architecture definitions for flexible block layouts.

Use cases

• load pretrained efficientnet weights in pytorch
• export mobilenetv3 model to onnx
• image classification with efficientnet-lite
• compare mobile-friendly cnn architectures
• port tensorflow efficientnet weights to pytorch
• run inference with mnasnet or fbnet models

When to choose

• you need pretrained weights for EfficientNet-family or MobileNet-family models in PyTorch
• you want ONNX or Caffe2 export of these architectures
• you are reproducing older research that depends on this repo

When to avoid

• starting a new project - use timm (pytorch-image-models) instead, which supersedes this repo
• you need maintained code or recent PyTorch compatibility guarantees
• you need architectures beyond the MobileNet-block family

Facets

library · maturity abandoned

machine-learning deep-learning image-processing machine-learning computer-vision deep-learning python efficientnet mobilenet pretrained-models pytorch onnx image-classification neural-architecture-search deprecated

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rwightman/gen-efficientnet-pytorch")