This is a beta version of solaris which may continue to develop. Please report any bugs through issues!
- This is a beta version of solaris which may continue to develop. Please report any bugs through issues!
- - License
- Documentation
- Installation Instructions
- Dependencies
- License
Solaris is an open source GeoAI ML toolkit for preprocessing and post processing workflows that are common to machine learning with geospatial imagery. It handles common functionality for preprocessing geotiffs and vector formats into formats that deep learning frameworks can interpret. It also handles post-processing and evaluating detection results, making it easier to compare different models. See the ROADMAP.md for a description of how v0.5 differs from v0.4 of solaris.
This repository provides the source code for the solaris project, which provides software tools for:
- Tiling large-format overhead images and vector labels
- Converting between geospatial raster and vector formats and machine learning-compatible formats
- Evaluating performance of deep learning model predictions, including semantic and instance segmentation, object detection, and related tasks
The full documentation for solaris can be found at https://solaris.readthedocs.io, and includes:
- A summary of
solaris - Installation instructions
- API Documentation
- Tutorials for common uses
The documentation is still being improved, so if a tutorial you need isn't there yet, check back soon or post an issue!
coming soon: One-command installation from conda-forge.
We recommend creating a conda environment with the dependencies defined in environment.yml before installing solaris. After cloning the repository:
cd solaris
If you're installing on a system with GPU access:
conda env create -n solaris -f environment-gpu.yml
Otherwise:
conda env create -n solaris -f environment.yml
Finally, regardless of your installation environment:
conda activate solaris
pip install .
The package also exists on PyPI, but note that some of the dependencies, specifically rtree and gdal, are challenging to install without anaconda. We therefore recommend installing at least those dependencies using conda before installing from PyPI.
conda install -c conda-forge rtree gdal=2.4.1
pip install solaris
If you don't want to use conda, you can install libspatialindex, then pip install rtree. Installing GDAL without conda can be very difficult and approaches vary dramatically depending upon the build environment and version, but the rasterio install documentation provides OS-specific install instructions. Simply follow their install instructions, replacing pip install rasterio with pip install solaris at the end.
All dependencies can be found in the requirements file ./requirements.txt or environment.yml
See LICENSE.