Giter Club home page Giter Club logo

capsule-attention-networks's Introduction

capsule-attention-networks

Capsule networks to identify crop type of satellite imagery with 88% accuracy at 30x30m resolution. Preprint available on arxiv.

Model F1-Score
SVM 31.1
CNN 56.7
LSTM 74.5
CapsAttn 85.6

Data

The data set was provided in Rubworm and Korner (2017), comprising 26 Sentinel 2A images taken during 2016 of a 102 x 42 km area in Munich, Germany. The 10 m bands (2 blue, 3 green, 4 red, 8 near-infrared) and 20 m bands (11 short-wave-infrared-1, 12 short-wave- infrared-2) down-sampled to 10 m resolution were extracted from 406,000 points of interest were within the data set. Input data was formatted to 3 x 3 px neighborhoods for each of the 26 time steps with an approximate 75, 5, and 20 percent train, validation, and test ratio.

Ground truth labels were provided by the Bavarian Ministry of Agriculture, totalling 19 classes with at least 400 occur- rences (corn, corn, meadow, asparagus, rape, hops, summer oats, winter spelt, fallow, winter wheat, winter barley, winter rye, beans, winter triticale, summer barley, peas, potatoes, soybeans, and sugar beets). Sample points were additionally classified into cloud, water, snow, and cloud shadow, as well as an other category for non-agricultural pixels.

Architecture overview

Overview of approach

Results

Confusion matrix

Project Organization

├── LICENSE
├── Makefile           <- Makefile with commands like `make data` or `make train`
├── README.md
├── data
│   ├── external       <- Data from third party sources.
│   ├── interim        <- Intermediate data that has been transformed.
│   ├── processed      <- The final, canonical data sets for modeling.
│   └── raw            <- The original, immutable data dump.
│
├── docs               <- A default Sphinx project; see sphinx-doc.org for details
│
├── models             <- Trained and serialized models, model predictions, or model summaries
│
├── notebooks          <- Jupyter notebooks.
│    │
├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.
│   └── figures        <- Generated graphics and figures to be used in reporting
│
├── requirements.txt   <- The requirements file for reproducing the analysis environment
│
├── setup.py           <- makes project pip installable (pip install -e .) so src can be imported
├── src                <- Source code for use in this project.
│   ├── __init__.py    <- Makes src a Python module
│   │
│   ├── data           <- Scripts to download or generate data
│   │   └── make_dataset.py
│   │
│   ├── features       <- Scripts to turn raw data into features for modeling
│   │   └── build_features.py
│   │
│   ├── models         <- Scripts to train models and then use trained models to make
│   │   │                 predictions
│   │   ├── predict_model.py
│   │   └── train_model.py
│   │
│   └── visualization  <- Scripts to create exploratory and results oriented visualizations
│       └── visualize.py
│
└── tox.ini            <- tox file with settings for running tox

capsule-attention-networks's People

Contributors

johnmbrandt avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  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.