Giter Site home page Giter Site logo

deeplab-cnn's Introduction

[PYTORCH] Deeplab

Introduction

Pytorch implementation of the model described in the paper DeepLab: Semantic resultss Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs paper.

Datasets:

I used 2 different datases: VOC2012 and VOCaugmented (VOC2007 + 2012) Statistics of datasets I used for experiments is shown below

Dataset #Classes #Train resultsss #Validation resultsss
VOC2012 20 5011 1449
VOCaugmented 20 1464 1449

Training

  • Using Valohai platform
  • Valohai platform overview graph

Experiments:

I trained models in Valohai platform using CSC Cluster. The model version control show in the picture. For each run Valohai save the results, export log, metadata and model to CSC Cloud storage

valohai

  • VOC2012 voc2012 loss
  • VOCaugmented vocaugmented loss

resultss

Some output predictions for experiments for each dataset are shown below:

  • VOC2012

  • VOCaugmented

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.