# Zehaos/MobileNet

MobileNet build with Tensorflow

Repository: https://github.com/Zehaos/MobileNet
Canonical: https://ross.abutalabs.com/products/mobilenet
Language: Python
License: Apache-2.0
License Family: permissive
Topics: tensorflow, mobilenets, multigpu, slim, detection
Last push: 2017-11-06T01:23:28+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3423, "days_push": 3223, "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 1659, forks 468 (observed 2026-08-28T04:05:18.301753+00:00)

## What it is
A TensorFlow implementation of Google's MobileNets, efficient convolutional neural networks for mobile vision applications, including ImageNet training scripts, pretrained weights, and speed benchmarks. It also includes experimental object detection training on the KITTI dataset.

## Use cases
- train mobilenet on imagenet with tensorflow
- get pretrained mobilenet weights for image classification
- benchmark mobilenet inference speed on cpu and gpu
- implement efficient cnns for mobile vision applications
- train an object detection model on kitti
- experiment with quantized and fused batch norm inference

## When to choose
- you need a standalone TensorFlow 1.x MobileNet implementation with pretrained ImageNet weights
- you want to reproduce or study the MobileNet paper with training and benchmark scripts
- you need a starting point for MobileNet-based detection on KITTI

## When to avoid
- you need the official, maintained MobileNet implementation - use tensorflow/models slim instead
- you work with TensorFlow 2.x or Keras applications
- you need actively maintained code or recent GPU support

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: machine-learning, computer-vision, image-processing
- platform: python
- tags: tensorflow, mobilenet, convolutional-neural-networks, imagenet, object-detection, slim, multigpu, pretrained-models, linux, gpu

## Member repositories
- Zehaos/MobileNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:18.301753+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 2026-08-30T03:44:41.566554+00:00, confidence not recorded.
  - readme: https://github.com/Zehaos/MobileNet (fetched 2026-08-28T04:05:18.301753+00:00, sha db32b00ac51a)
- Data as of 2026-08-30T08:39:29.467469+00:00.