# endernewton/tf-faster-rcnn

Tensorflow Faster RCNN for Object Detection

Repository: https://github.com/endernewton/tf-faster-rcnn
Canonical: https://ross.abutalabs.com/products/tf-faster-rcnn
Homepage: https://arxiv.org/pdf/1702.02138.pdf
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, object-detection, faster-rcnn, coco, voc, resnet, mobilenet, tensorboard
Last push: 2021-09-27T10:11:10+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": 3509, "days_push": 1801, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3646, forks 1535 (observed 2026-08-28T04:08:12.932219+00:00)

## What it is
A TensorFlow implementation of the Faster R-CNN object detection framework, supporting VGG16, ResNet, and MobileNet backbones trained and evaluated on PASCAL VOC and COCO datasets. The repository is officially deprecated in favor of more up-to-date multi-GPU implementations.

## Use cases
- train a Faster R-CNN object detector on PASCAL VOC
- evaluate object detection models on COCO minival
- run object detection inference with pretrained VGG16 or ResNet101 models
- reproduce Faster R-CNN baseline results in TensorFlow
- fine-tune an object detection model with MobileNet backbone
- study region proposal network implementations for object detection

## When to choose
- you need a reference TensorFlow implementation of Faster R-CNN for research or study
- you want to reproduce published VOC or COCO detection baselines
- you need pretrained Faster R-CNN models with VGG16, ResNet, or MobileNet backbones

## When to avoid
- you need an actively maintained or multi-GPU production detector - the repo is deprecated
- you want modern architectures like FPN or Mask R-CNN training support
- you are starting a new project and should use up-to-date detection frameworks instead

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: tensorflow, faster-rcnn, object-detection, deprecated, coco, pascal-voc, vgg16, resnet, mobilenet, gpu, linux

## Member repositories
- endernewton/tf-faster-rcnn (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:12.932219+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 2026-08-29T18:31:44.196713+00:00, confidence not recorded.
  - readme: https://github.com/endernewton/tf-faster-rcnn (fetched 2026-08-28T04:08:12.932219+00:00, sha 67a8867a10a6)
- Data as of 2026-08-30T08:39:29.467469+00:00.