Skip to main content

EarthNet Minicuber

Project description

earthnet-minicuber

A Python library for creating EarthNet-style minicubes.

This library currently creates minicubes over Africa as they will be used in DeepCube Horizon 2020 project Use Case 1. It is developed by the EarthNet Team.

It is currently under development, thus do expect bugs and please report them!

Installation

Prerequisites (We use an Anaconda environment):

conda create -n minicuber python=3.10 gdal cartopy -c conda-forge
conda deactivate
conda activate minicuber
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
pip install scipy matplotlib seaborn netCDF4 xarray zarr dask shapely pillow pandas s3fs fsspec boto3 psycopg2 pystac-client stackstac planetary-computer rasterio[s3] rioxarray odc-algo segmentation-models-pytorch folium ipykernel ipywidgets

Install this package with PyPI:

pip install earthnet-minicuber

or install this package in developing mode with

git clone https://github.com/earthnet2021/earthnet-minicuber.git
cd earthnet-minicuber
pip install -e .

or directly with

pip install git+https://github.com/earthnet2021/earthnet-minicuber.git

Tutorial

See notebooks/example.ipynb for an usage example.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

earthnet-minicuber-0.1.0.tar.gz (26.5 kB view hashes)

Uploaded Source

Built Distribution

earthnet_minicuber-0.1.0-py3-none-any.whl (38.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page