matterport/mask_rcnn

Analysis updated 2026-06-21

★ 25,555PythonAudience · researcherComplexity · 4/5Setup · hard

Mindmap

mindmap
  root((mask-rcnn))
    What it does
      Object detection
      Pixel segmentation masks
      Instance segmentation
      Bounding boxes
    Tech stack
      Python
      Keras
      TensorFlow
      ResNet101 backbone
    Use cases
      Medical imaging
      Robotics vision
      Industrial inspection
      Autonomous vehicles
    Included tools
      Pre-trained COCO weights
      Jupyter notebooks
      Custom dataset training
    Audience
      Researchers
      CV engineers

mindmap root((mask-rcnn)) What it does Object detection Pixel segmentation masks Instance segmentation Bounding boxes Tech stack Python Keras TensorFlow ResNet101 backbone Use cases Medical imaging Robotics vision Industrial inspection Autonomous vehicles Included tools Pre-trained COCO weights Jupyter notebooks Custom dataset training Audience Researchers CV engineers

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Detect and outline objects in medical images to identify and segment anatomical regions or anomalies.

USE CASE 2

Train a custom instance segmentation model on your own labeled image dataset for industrial inspection or robotics.

USE CASE 3

Use pre-trained MS COCO weights to segment everyday objects in photos without training from scratch.

USE CASE 4

Build a computer vision pipeline for autonomous vehicles that needs pixel-level object outlines, not just bounding boxes.

What is it built with?

PythonKerasTensorFlow

How does it compare?

	matterport/mask_rcnn	black-forest-labs/flux	subframe7536/maple-font
Stars	25,555	25,496	25,644
Language	Python	Python	Python
Setup difficulty	hard	hard	easy
Complexity	4/5	4/5	1/5
Audience	researcher	researcher	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Requires Python 3, Keras, and TensorFlow, a GPU is strongly recommended for training.

In plain English

Mask R-CNN is a Python implementation of a computer vision technique that can look at a photo and identify every distinct object in it, draw a box around each one, and paint a precise pixel-level outline (called a segmentation mask) around its exact shape. For example, given a street scene it can simultaneously find the cars, people, and traffic lights, label each one separately, and trace their exact outlines rather than just boxing them. This is called instance segmentation, meaning each individual object gets its own mask even if two objects of the same type overlap. The model is built on Keras and TensorFlow, two popular Python frameworks for building and training AI models. It uses a neural network architecture called Feature Pyramid Network combined with a ResNet101 backbone, these are layered mathematical structures that scan an image at multiple scales to catch both large and small objects. The repository includes pre-trained weights from the MS COCO dataset (a large collection of labeled everyday photos), Jupyter notebooks for visualization, and tools to train the model on your own custom dataset. Researchers and developers would use this when they need to detect and precisely outline objects in images or video, such as in medical imaging, robotics, autonomous vehicles, or industrial inspection. It requires Python 3, Keras, and TensorFlow.

Copy-paste prompts

Prompt 1

I want to run Mask R-CNN on my own photos using the pre-trained COCO weights. Show me the Python code to load the model and run inference on a single image.

Prompt 2

How do I train the Mask R-CNN model on a custom dataset? What annotation format does it expect and how do I prepare the data?

Prompt 3

I want to visualize the segmentation masks output by Mask R-CNN on a test image. How do I use the included Jupyter notebooks to display results?

Prompt 4

What GPU and RAM requirements does training Mask R-CNN on a custom dataset need, and roughly how long does a training run take?

Frequently asked questions

What is mask_rcnn?

A Python implementation of Mask R-CNN that detects every object in a photo, draws a bounding box, and paints a precise pixel-level outline around each individual object using Keras and TensorFlow.

What language is mask_rcnn written in?

Mainly Python. The stack also includes Python, Keras, TensorFlow.

How hard is mask_rcnn to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is mask_rcnn for?

Mainly researcher.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub matterport on gitmyhub

Verify against the repo before relying on details.