# CharlesShang/FastMaskRCNN

Mask RCNN in TensorFlow

Repository: https://github.com/CharlesShang/FastMaskRCNN
Canonical: https://ross.abutalabs.com/products/fastmaskrcnn
Language: Python
License: Apache-2.0
License Family: permissive
Topics: maskrcnn, rcnn, fasterrcnn, tensorflow, detection, segmentation, pfn, coco
Last push: 2021-01-05T04:08:12+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": 3448, "days_push": 2066, "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 3082, forks 1081 (observed 2026-08-28T04:07:41.949973+00:00)

## What it is
A TensorFlow implementation of Mask R-CNN for instance segmentation, reproducing the paper by Kaiming He et al. It includes ROIAlign, a COCO data provider, ResNet50 backbone, and a Feature Pyramid Network, with training scripts for COCO.

## Use cases
- train a Mask R-CNN model in TensorFlow
- instance segmentation on the COCO dataset
- reproduce the Mask R-CNN paper results
- object detection with a feature pyramid network
- learn how Mask R-CNN is implemented from scratch
- fine-tune a segmentation model on custom images

## When to choose
- you need a readable TensorFlow 1.x codebase for studying or modifying Mask R-CNN internals
- you want a lightweight standalone implementation rather than a large model zoo
- you are working with the COCO dataset and ResNet50 backbones

## When to avoid
- you need a maintained, production-ready segmentation model - the repo is unfinished and inactive
- you use TensorFlow 2.x or PyTorch - this targets TensorFlow 1.0+
- you need full COCO training/evaluation, which was never completed

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python
- tags: mask-rcnn, instance-segmentation, object-detection, tensorflow, coco-dataset, feature-pyramid-network, roi-align, linux, gpu

## Member repositories
- CharlesShang/FastMaskRCNN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.949973+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 2026-08-30T07:27:42.432206+00:00, confidence not recorded.
  - readme: https://github.com/CharlesShang/FastMaskRCNN (fetched 2026-08-28T04:07:41.949973+00:00, sha 2fe0b1408b2d)
- Data as of 2026-08-30T08:39:29.467469+00:00.