# BVLC/caffe

Caffe: a fast open framework for deep learning.

Repository: https://github.com/BVLC/caffe
Canonical: https://ross.abutalabs.com/products/caffe
Homepage: http://caffe.berkeleyvision.org/
Language: C++
License: NOASSERTION
License Family: other
Topics: deep-learning, machine-learning, vision
Last push: 2024-07-31T23:10:28+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4738, "days_push": 763, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 34556, forks 18423 (observed 2026-08-28T04:12:00.634143+00:00)

## What it is
Caffe is a fast, modular deep learning framework developed by Berkeley AI Research, focused on convolutional neural networks for vision, speech, and multimedia. Models are defined via plaintext protobuf configuration, with C++ core and Python/MATLAB/command-line interfaces, and CPU/GPU switching via a single flag.

## Use cases
- train convolutional neural networks for image classification
- deploy fast CNN inference on GPU or CPU
- run pretrained vision models from the model zoo
- train siamese networks with contrastive loss
- process millions of images per day for vision research
- define neural network architectures without writing code

## When to choose
- you need a proven, fast CNN framework for computer vision research or deployment
- you want config-file-defined models with CPU/GPU portability
- you need to reproduce classic vision models like AlexNet or GoogLeNet
- you work in C++ and want an extensible layer system

## When to avoid
- you need modern architectures like transformers or dynamic graphs - use PyTorch or TensorFlow instead
- you need active development and current community support
- you require Python 3-first tooling or modern ecosystem integrations
- you are starting a new deep learning project today

## Facets
- artifact type: framework
- maturity: maintenance
- function: deep-learning, machine-learning, computer-vision, image-processing, gpu-computing
- domain: deep-learning, machine-learning, computer-vision, image-processing
- platform: windows, cpp, python, cross-platform
- tags: convolutional-networks, cuda, cudnn, model-zoo, bsd-license, legacy-framework, linux, macos, docker, gpu

## Member repositories
- BVLC/caffe (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:00.634143+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 2026-08-29T16:27:28.536602+00:00, confidence not recorded.
  - readme: https://github.com/BVLC/caffe (fetched 2026-08-28T04:12:00.634143+00:00, sha d34263891b8b)
  - homepage: http://caffe.berkeleyvision.org/ (fetched 2026-08-29T07:48:14.764504+00:00, sha bf446dd073c6)
  - site_page: http://caffe.berkeleyvision.org/installation.html (fetched 2026-08-29T07:48:14.769337+00:00, sha d49d0db4d345)
  - site_page: http://caffe.berkeleyvision.org/tutorial (fetched 2026-08-29T07:48:14.767364+00:00, sha 20ef490d309a)
  - site_page: http://caffe.berkeleyvision.org/doxygen/annotated.html (fetched 2026-08-29T07:48:14.771322+00:00, sha 182c920ae07e)
- Data as of 2026-08-30T08:39:29.467469+00:00.