Skip to content

tangjiashan7/mmdetection-cascade-mask-rcnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Cascade-Mask-RCNN

Cascade Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow, based on matterport mrcnn.

This repository is based on matterport's Mask RCNN, All codes are the same as matterport except 'mrcnn/model.py', I add my cascade architecture into this file . Therefore, the usage methods are also the same as the existing Mask RCNN work , which based on matterport from GitHub or blogs.

Introduction

MMDetection is an open source object detection toolbox based on PyTorch. It is a part of the mmd project.

The master branch works with PyTorch 1.3+. The old v1.x branch works with PyTorch 1.1 to 1.4, but v2.0 is strongly recommended for faster speed, higher performance, better design and more friendly usage.

Installation

Models are developed in Pytorch based mmdetection

Learn more about READMEs note:Pytorch 1.6.0 ##description Image analysis system

##Traning python tools/train.py configs/cascade_rcnn_r50_fpn_1x_coco.py --gpus 1 --validate --work_dir work_dirs

test

python tools/test.py configscascade_rcnn_r50_fpn_1x_coco.py work_dirs/your chieckpoint --out ./result/result_100.pkl --eval bbox --show

##dataset publaynet PubLayNet PubLayNet is a large dataset of document images, of which the layout is annotated with both bounding boxes and polygonal segmentations. For more information, see PubLayNet

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published