Mask-RCNN

show more

Implementations

Detectron

Detectron is Facebook AI Research's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework.

using the following backbone network architectures:

Models: https://github.com/facebookresearch/Detectron/tree/master/detectron/modeling

Github: https://github.com/facebookresearch/Detectron

MX Mask R-CNN

An MXNet implementation of Mask R-CNN.

This repository is based largely on the mx-rcnn implementation of Faster RCNN available here.

Github: https://github.com/TuSimple/mx-maskrcnn

Mask R-CNN for Object Detection and Segmentation

This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone.

Getting Started

  • demo.ipynb Is the easiest way to start. It shows an example of using a model pre-trained on MS COCO to segment objects in your own images. It includes code to run object detection and instance segmentation on arbitrary images.

  • train_shapes.ipynb shows how to train Mask R-CNN on your own dataset. This notebook introduces a toy dataset (Shapes) to demonstrate training on a new dataset.

  • (model.pyutils.pyconfig.py): These files contain the main Mask RCNN implementation.

  • inspect_data.ipynb. This notebook visualizes the different pre-processing steps to prepare the training data.

  • inspect_model.ipynb This notebook goes in depth into the steps performed to detect and segment objects. It provides visualizations of every step of the pipeline.

  • inspect_weights.ipynb This notebooks inspects the weights of a trained model and looks for anomalies and odd patterns.

Model: https://github.com/matterport/Mask_RCNN/blob/master/mrcnn/model.py

Github: https://github.com/matterport/Mask_RCNN

i-segmentationmask-rcnn
How helpful was this page?