Git Product home page Git Product logo

hrnetv2_keras_tensorflow_semisupervised's Introduction

Multiclass Semantic Segmentation HRNetV2 in Keras / Tensorflow

This repository serves as an educational example of implementing HRNetV2 in Keras / Tensorflow, including all supporting code one would need to apply it to arbitrary datasets. Datasets for training and validation are specified with text files pointing to original images, as well as color map segmentation masks. Color maps for each class are specified by a text file with "R G B" values on each line. Simple augmentation is supported for both training and inference steps. Loading pre-trained models for finetuning is included. Inference code is included that will generate output color maps that can be easily visualized.

Changelog:

  • Added code in segment_mc_semi.py to include a consistency loss on a supplied unlabeled dataset for semi-supervised learning.
  • Added code in segment_mc.py to apply HRNet to arbitrary datasets specified by simple text files for training/validation and color maps.
  • Removed other usage examples. Please refer to original repository for prior interface.

hrnetv2_keras_tensorflow_semisupervised's People

Contributors

noelcodella avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.