# soeaver/caffe-model

Caffe models (including classification, detection and segmentation) and deploy files for famouse networks

Repository: https://github.com/soeaver/caffe-model
Canonical: https://ross.abutalabs.com/products/caffe-model
Language: Python
License: MIT
License Family: permissive
Topics: inception-resnet, caffe, caffemodel, resnext, imagenet, resnet, inception, dpn, faster-rcnn, classification, detection, segmentation
Last push: 2018-03-22T12:52:11+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": 3840, "days_push": 3086, "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 1276, forks 608 (observed 2026-08-28T04:04:13.021623+00:00)

## What it is
A model zoo of pre-trained Caffe models (caffemodel files) and deploy prototxt files for popular architectures such as ResNet, ResNeXt, Inception, Xception, DenseNet, Wide ResNet, SENet, and DPN. It covers ImageNet classification, PASCAL VOC object detection (e.g., Faster R-CNN), and segmentation, with most weights converted from other frameworks like MXNet, TensorFlow, and Keras.

## Use cases
- download pretrained caffe models for imagenet classification
- find caffemodel weights for resnet inception resnext densenet
- get deploy prototxt files for famous cnn architectures
- pretrained faster rcnn detection models on pascal voc
- semantic segmentation pretrained models in caffe
- compare imagenet top-1 top-5 accuracy across caffe backbones
- bootstrap caffe experiments without training from scratch

## When to choose
- You use the Caffe framework and need ready-made pretrained weights instead of training from scratch
- You need deploy-ready prototxt definitions for classic CNN backbones
- You want ImageNet classification, PASCAL VOC detection, or segmentation baselines in Caffe format
- You are reproducing 2017-2018 era computer vision results with py-RFCN-priv or similar Caffe pipelines

## When to avoid
- You work natively in PyTorch, TensorFlow, or MXNet, since weights here target Caffe
- You need modern architectures or ongoing maintenance - the repository has not been updated since 2018
- You need training code rather than converted inference models
- You need models for domains beyond image classification, detection, and segmentation

## Facets
- artifact type: dataset
- maturity: abandoned
- function: deep-learning, machine-learning, computer-vision
- domain: deep-learning, machine-learning, computer-vision, image-processing
- platform: python, cpp
- tags: caffe, model-zoo, pretrained-models, caffemodel, deploy-prototxt, imagenet, resnet, resnext, inception, densenet, dpn, image-classification, object-detection, semantic-segmentation, faster-rcnn, linux, gpu

## Member repositories
- soeaver/caffe-model (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.021623+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 2026-08-30T05:02:58.791924+00:00, confidence not recorded.
  - readme: https://github.com/soeaver/caffe-model (fetched 2026-08-28T04:04:13.021623+00:00, sha 94084bf89bd3)
- Data as of 2026-08-30T08:39:29.467469+00:00.