Code Monkey home page Code Monkey logo

cs634_final_project's Introduction

CS634_final_project

Approach: Firstly a convolutional neural network is used to segment the image, using the bounding boxes directly as a mask. Secondly connected components is used to separate multiple areas of predicted pneumonia. Finally a bounding box is simply drawn around every connected component.

Network: The network consists of a number of residual blocks with convolutions and downsampling blocks with max pooling. At the end of the network a single upsampling layer converts the output to the same shape as the input. As the input to the network is 256 by 256 (instead of the original 1024 by 1024) and the network downsamples a number of times without any meaningful upsampling (the final upsampling is just to match in 256 by 256 mask) the final prediction is very crude. If the network downsamples 4 times the final bounding boxes can only change with at least 16 pixels.

We also make some change to the origin images. 1.Change input image size to 320x320. 2.Added transpose convolutions to allow greater flexibility in final predictions as per note above. 3.Usu cross-validation using StratifiedKFold or KFold.

cs634_final_project's People

Contributors

owlma avatar

Watchers

James Cloos avatar

Forkers

yxl2333

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.