# shicai/MobileNet-Caffe

Caffe Implementation of Google's MobileNets (v1 and v2)

Repository: https://github.com/shicai/MobileNet-Caffe
Canonical: https://ross.abutalabs.com/products/mobilenet-caffe
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: mobilenet, caffe, imagenet, mobilenetv2, mobilnet-v2
Last push: 2021-06-08T06:28:43+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": 3415, "days_push": 1912, "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 1274, forks 689 (observed 2026-08-28T04:04:12.793372+00:00)

## What it is
A Caffe implementation of Google's MobileNet v1 and v2 architectures with pretrained ImageNet model weights. It includes evaluation scripts for single-image classification and instructions for finetuning on custom datasets.

## Use cases
- run mobilenet image classification with caffe
- download pretrained mobilenet v1 v2 weights for imagenet
- finetune mobilenet on my own image dataset
- evaluate a caffe image classification model on a single image
- use lightweight cnn for mobile vision applications

## When to choose
- you need pretrained MobileNet weights in Caffe format
- you are deploying efficient image classification on mobile or embedded devices with Caffe
- you want a starting point to finetune MobileNet on custom data

## When to avoid
- you work in PyTorch, TensorFlow, or ONNX rather than Caffe
- you need state-of-the-art accuracy rather than a lightweight model
- you need actively maintained code - the project is in maintenance mode

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: deep-learning, computer-vision, image-processing
- platform: python, cpp, cross-platform
- tags: mobilenet, caffe, pretrained-models, imagenet, model-weights, image-classification, mobile-vision

## Member repositories
- shicai/MobileNet-Caffe (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:12.793372+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 2026-08-30T05:03:09.126625+00:00, confidence not recorded.
  - readme: https://github.com/shicai/MobileNet-Caffe (fetched 2026-08-28T04:04:12.793372+00:00, sha c6d968bf2266)
- Data as of 2026-08-30T08:39:29.467469+00:00.