# tonylins/pytorch-mobilenet-v2

A PyTorch implementation of MobileNet V2 architecture and pretrained model.

Repository: https://github.com/tonylins/pytorch-mobilenet-v2
Canonical: https://ross.abutalabs.com/products/pytorch-mobilenet-v2
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2019-10-20T05:27:50+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": 3146, "days_push": 2509, "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 1406, forks 330 (observed 2026-08-28T04:04:38.327373+00:00)

## What it is
A PyTorch implementation of the MobileNetV2 architecture with automatic download of ImageNet pretrained weights. It reproduces the official TensorFlow accuracy (~71.8% top-1) and includes a training recipe for ImageNet classification.

## Use cases
- use mobilenet v2 pretrained weights in pytorch
- implement mobilenetv2 architecture for image classification
- train mobilenet v2 on imagenet
- use a lightweight backbone for object detection or segmentation
- compare model flops and parameters against tensorflow implementation

## When to choose
- you need a lightweight, mobile-friendly image classification model in PyTorch
- you want pretrained MobileNetV2 weights with automatic download
- you need a backbone for detection or segmentation tasks

## When to avoid
- you need the latest MobileNetV3 or EfficientNet architectures
- you want an actively maintained project with recent updates
- you need TensorFlow or other framework support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, computer-vision, image-processing
- platform: python
- tags: mobilenet-v2, pytorch, pretrained-model, image-classification, neural-network

## Member repositories
- tonylins/pytorch-mobilenet-v2 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:38.327373+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 2026-08-30T04:38:44.637212+00:00, confidence not recorded.
  - readme: https://github.com/tonylins/pytorch-mobilenet-v2 (fetched 2026-08-28T04:04:38.327373+00:00, sha c46700faae18)
- Data as of 2026-08-30T08:39:29.467469+00:00.