# ethereon/caffe-tensorflow

Caffe models in TensorFlow

Repository: https://github.com/ethereon/caffe-tensorflow
Canonical: https://ross.abutalabs.com/products/caffe-tensorflow
Language: Python
License: NOASSERTION
License Family: other
Last push: 2019-07-18T13:35:38+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": 3949, "days_push": 2603, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2786, forks 1012 (observed 2026-08-28T04:07:21.933982+00:00)

## What it is
A Python tool that converts Caffe-trained neural network models into TensorFlow format, producing a NumPy parameter file and a Python class that builds the model graph. It includes verified conversion examples for popular ImageNet models like ResNet, VGG, GoogLeNet, and AlexNet.

## Use cases
- convert a caffe model to tensorflow
- port pretrained imagenet weights from caffe to tensorflow
- load caffe .caffemodel parameters in tensorflow
- rebuild a vgg16 or resnet graph in tensorflow
- verify converted model accuracy on ilsvrc2012
- migrate legacy deep learning models between frameworks

## When to choose
- you have pretrained Caffe models (new format) and want to use them in TensorFlow
- you need verified conversions of standard architectures like ResNet or VGG
- you want weights extracted as NumPy data plus a graph-building class

## When to avoid
- your Caffe model uses old format or unsupported layers/padding
- you need a maintained tool - the project has seen little activity since 2019
- you need runtime interop between Caffe and TensorFlow in one process (CUDA conflicts prevent it)

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, parser, serialization
- domain: deep-learning, machine-learning, developer-tools
- platform: python
- tags: caffe, tensorflow, model-conversion, neural-networks, model-porting, gpu

## Member repositories
- ethereon/caffe-tensorflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:21.933982+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 2026-08-30T08:16:01.026624+00:00, confidence not recorded.
  - readme: https://github.com/ethereon/caffe-tensorflow (fetched 2026-08-28T04:07:21.933982+00:00, sha 1bdcf516f1f4)
- Data as of 2026-08-30T08:39:29.467469+00:00.