# lukemelas/EfficientNet-PyTorch

A PyTorch implementation of EfficientNet

Repository: https://github.com/lukemelas/EfficientNet-PyTorch
Canonical: https://ross.abutalabs.com/products/efficientnet-pytorch
Language: Python
License: Apache-2.0
License Family: permissive
Topics: efficientnet-pytorch, imagenet, feature-extraction, pretrained-models
Last push: 2022-04-08T12:30:25+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": 2652, "days_push": 1608, "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 8222, forks 1535 (observed 2026-08-28T04:10:19.672875+00:00)

## What it is
A PyTorch implementation of the EfficientNet convolutional neural network family with pretrained ImageNet weights. It provides a simple pip-installable API for loading models for classification and feature extraction.

## Use cases
- load pretrained efficientnet in pytorch
- image classification with efficientnet
- extract features from images with a cnn
- transfer learning backbone for vision models
- run imagenet classification inference

## When to choose
- you need EfficientNet specifically in PyTorch with pretrained weights
- you want a lightweight pip-installable vision backbone for feature extraction or fine-tuning

## When to avoid
- you need newer architectures like EfficientNetV2 or timm's broader model zoo
- you use TensorFlow or another framework
- you need actively maintained code with recent fixes

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

## Member repositories
- lukemelas/EfficientNet-PyTorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:19.672875+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 2026-08-29T17:29:31.659744+00:00, confidence not recorded.
  - readme: https://github.com/lukemelas/EfficientNet-PyTorch (fetched 2026-08-28T04:10:19.672875+00:00, sha 28f6cefccf68)
  - registry_pypi: https://pypi.org/pypi/efficientnet-pytorch/json (fetched 2026-08-29T08:28:09.004411+00:00, sha 00d628ad38bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.