Code Monkey home page Code Monkey logo

airbus_ship_detection's Introduction

kaggle competition: airbus ship detection challenge

what is EncodedPixels?

  • It is the way to express the location of pixels containing an object, like a list in one dimension, instead of using two dimensions or coordenates. If the object is on the row 1, between pixels 5 and 5, you can express it like : 5 5 , and like this for every row.

Data Prepare

  • Delete useless images without ships
  • Add index for ships existence(0 or 1)
  • drop and split train & valid set

Step 1 Detect ship existence - classification_ships_UResnet34.py

  • Do transfer learning with Resnet34
  • Load training and valid set
  • Image size 256 x 256, RGB data

Step 2-1 ship semantic segmentationn - train.py

  • Use Unet Base on ResNet34 model
  • Load training and valid set
  • Image size 256 x 256, RGB data

Step 2-2 ship semantic segmentationn - train_v2.py

  • Use Unet Base on ResNet34 model
  • Use pre-trained from Step 1
  • Load training and valid set
  • Image size 256 x 256, RGB data

Submission result with predict ship + Unet34 - submit.py

Submission

Ref.

  1. Simple transfer Learning detect Ship exist (Keras)

  2. U-Net base on ResNet34 Transfer learning (Keras)

  3. Unet34 (dice 0.87+)

  4. Fine-tuning ResNet34 on ship detection

  5. My weights file

airbus_ship_detection's People

Contributors

kuobrian avatar

Watchers

avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.