/Mask_RCNN

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

Primary LanguagePythonOtherNOASSERTION

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.

Instance Segmentation Sample

The repository includes:

  • Source code of Mask R-CNN built on FPN and ResNet101.
  • Training code for MS COCO
  • Pre-trained weights for MS COCO
  • Jupyter notebooks to visualize the detection pipeline at every step
  • ParallelModel class for multi-GPU training
  • Evaluation on MS COCO metrics (AP)
  • Example of training on your own dataset

Requirements

Python 3.4, Nvidia Cuda, cudNN, TensorFlow GPU 1.3, Keras 2.0.8 and other common packages listed in requirements.txt.

This is fork of Matterplot Mask R-CNN

You can use it for detection an objects in the video or web-cam using OpenCV

Installation

  1. Clone this repository
  2. Install dependencies 
    pip3 install -r requirements.txt
  3. Download pre-trained COCO weights (mask_rcnn_coco.h5) from the releases page.
  4. Start help 
    python detector.py --help