# matterport/Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Repository: https://github.com/matterport/Mask_RCNN
Canonical: https://ross.abutalabs.com/products/mask_rcnn
Language: Python
License: NOASSERTION
License Family: other
Topics: mask-rcnn, tensorflow, object-detection, instance-segmentation, keras
Last push: 2024-06-07T02:36:21+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3240, "days_push": 818, "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 25567, forks 11610 (observed 2026-08-28T04:11:38.281947+00:00)

## What it is
A Python implementation of the Mask R-CNN model for object detection and instance segmentation, built on Keras and TensorFlow with a ResNet101 backbone and Feature Pyramid Network. It includes COCO pre-trained weights, training code, multi-GPU support, and Jupyter notebooks for visualization and custom dataset training.

## Use cases
- segment objects in images with instance masks
- train a custom object detection model on my own dataset
- run pre-trained Mask R-CNN on COCO images
- detect and segment multiple object instances in a photo
- visualize the detection pipeline step by step
- fine-tune Mask R-CNN for my research project

## When to choose
- you need instance segmentation (masks per object), not just bounding boxes
- you want readable, well-documented research code that is easy to extend
- you want pre-trained COCO weights and notebooks to inspect the model internals
- you are working with TensorFlow 1.x/Keras and multi-GPU training

## When to avoid
- you need the latest architectures like YOLO, Detectron2, or transformer-based detectors
- you need TensorFlow 2.x or PyTorch support
- you need production-grade performance or active maintenance
- you only need simple object detection without segmentation masks

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing, deep-learning
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: python, cross-platform
- tags: mask-rcnn, object-detection, instance-segmentation, keras, tensorflow, coco, resnet, feature-pyramid-network, gpu

## Member repositories
- matterport/Mask_RCNN (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.281947+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 2026-08-29T16:56:01.867033+00:00, confidence not recorded.
  - readme: https://github.com/matterport/Mask_RCNN (fetched 2026-08-28T04:11:38.281947+00:00, sha 8af9dd2b1223)
- Data as of 2026-08-30T08:39:29.467469+00:00.