# forresti/SqueezeNet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

Repository: https://github.com/forresti/SqueezeNet
Canonical: https://ross.abutalabs.com/products/squeezenet
License: BSD-2-Clause
License Family: permissive
Last push: 2018-07-09T21:10:27+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": 3845, "days_push": 2977, "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 2218, forks 717 (observed 2026-08-28T04:06:27.304763+00:00)

## What it is
SqueezeNet is a deep convolutional neural network architecture that achieves AlexNet-level image classification accuracy with 50x fewer parameters and a model under 0.5MB. The repository provides Caffe-compatible model definition files, solver configurations, and pretrained model weights.

## Use cases
- run image classification with a tiny pretrained model
- deploy a CNN on resource-constrained or embedded devices
- study a compact CNN architecture for research
- fine-tune a small pretrained ImageNet model
- reproduce SqueezeNet training results in Caffe

## When to choose
- you need AlexNet-level accuracy with a very small model footprint
- you work in Caffe and want pretrained weights and training configs
- you are researching model compression or efficient architectures

## When to avoid
- you need a modern framework like PyTorch or TensorFlow
- you need state-of-the-art accuracy rather than a small footprint
- you need actively maintained code - this is primarily a model release, not a maintained library

## Facets
- artifact type: dataset
- maturity: maintenance
- function: deep-learning, machine-learning, image-processing
- domain: deep-learning, computer-vision, machine-learning
- platform: cpp, python
- tags: caffe, pretrained-model, model-architecture, image-classification, model-compression, research-paper, gpu

## Member repositories
- forresti/SqueezeNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:27.304763+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 2026-08-30T02:45:54.094613+00:00, confidence not recorded.
  - readme: https://github.com/forresti/SqueezeNet (fetched 2026-08-28T04:06:27.304763+00:00, sha 318e7e98c9ba)
- Data as of 2026-08-30T08:39:29.467469+00:00.