kandekar007 / MASK-RCNN

segmentation and object detection for Google RVC 2020

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

MASK-RCNN

segmentation and object detection for Google RVC 2020

DATA

The train and validation sets of images and their ground truth (bounding boxes and labels) should be downloaded from Open Images Challenge page. Please note that the test images used in this competition is independent from those released as part of the Open Images Dataset. Total images: 9999

MASK-RCNN Architecture

alt text Total Classes used: 200

Mobilenet pretrained weights used.

About

segmentation and object detection for Google RVC 2020


Languages

Language:Jupyter Notebook 99.1%Language:Python 0.9%