# megvii-model/ShuffleNet-Series

Repository: https://github.com/megvii-model/ShuffleNet-Series
Canonical: https://ross.abutalabs.com/products/shufflenet-series
Language: Python
License: MIT
License Family: permissive
Last push: 2020-08-27T03:27:25+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": 2582, "days_push": 2197, "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 1513, forks 272 (observed 2026-08-28T04:04:56.309857+00:00)

## What it is
A collection of ShuffleNet-series efficient convolutional neural network models (V1, V2, V2+, Large, ExLarge) plus NAS-derived backbones like OneShot and DetNAS from Megvii Research. It provides PyTorch model definitions and pretrained weights for image classification and detection backbones.

## Use cases
- build an image classifier with a lightweight CNN
- run inference on mobile or edge devices with efficient models
- get pretrained ShuffleNetV2 weights for transfer learning
- compare efficient backbone accuracy against MobileNet
- use a NAS-searched backbone for object detection
- reproduce ShuffleNet paper results

## When to choose
- you need fast, low-FLOPs image classification backbones
- you want pretrained weights for ShuffleNet variants
- you need detection backbones from DetNAS or One-Shot NAS

## When to avoid
- you need transformer-based vision models
- you want actively maintained training pipelines
- you need models beyond classification and detection backbones

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning
- platform: python
- tags: shufflenet, image-classification, model-zoo, neural-architecture-search, pretrained-models, efficient-networks

## Member repositories
- megvii-model/ShuffleNet-Series (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:56.309857+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 2026-08-30T04:32:16.596422+00:00, confidence not recorded.
  - readme: https://github.com/megvii-model/ShuffleNet-Series (fetched 2026-08-28T04:04:56.309857+00:00, sha c978d28f7dde)
- Data as of 2026-08-30T08:39:29.467469+00:00.