Skip to content

ykamikawa/tf-keras-PSPNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

keras-PSPNet

Pyramid Scene persing Network is a model of semantic segmentation based on Fully Comvolutional Network. This repository contains the implementation of learning and testing in keras and tensorflow.

Architecutre

  • atrous convalution
  • residual module
  • pyramid pooling module

Prerequirements

  • python3.6
  • opencv for python
  • keras,tensorflow

Usage

train

  • Segmentation involveing multiple categories

    python train.py --options

  • Segmentation of mask image

    python train_mask.py --options

    • options
      • image dir
      • mask image dir
      • batchsize, nb_epochs, epoch_per_steps, input_configs
      • class weights
      • device num

test

  • Input test image

  • responce json format involving category name and color(pixel based prediction)

    python predict.py --input_path [path/to//input_imahge]

About

PSPNet for Semantic Segmentation with tensorflow and keras

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages