Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/CosmiQ/solaris
CosmiQ Works Geospatial Machine Learning Analysis Toolkit
https://github.com/CosmiQ/solaris
computervision deeplearning geo geospatial gis machinelearning python
Last synced: 3 months ago
JSON representation
CosmiQ Works Geospatial Machine Learning Analysis Toolkit
- Host: GitHub
- URL: https://github.com/CosmiQ/solaris
- Owner: CosmiQ
- License: apache-2.0
- Created: 2019-04-30T18:59:39.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2022-10-20T19:01:33.000Z (about 2 years ago)
- Last Synced: 2024-07-20T03:27:12.492Z (4 months ago)
- Topics: computervision, deeplearning, geo, geospatial, gis, machinelearning, python
- Language: Python
- Homepage: https://solaris.readthedocs.io
- Size: 26.9 MB
- Stars: 411
- Watchers: 31
- Forks: 112
- Open Issues: 93
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE.txt
Awesome Lists containing this project
README
An open source ML pipeline for overhead imagery by CosmiQ Works
## This is a beta version of Solaris which may continue to develop. Please report any bugs through issues!
- [Documentation](#documentation)
- [Installation Instructions](#installation-instructions)
- [Dependencies](#dependencies)
- [License](#license)
---
This repository provides the source code for the CosmiQ Works `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
- Performing semantic and instance segmentation, object detection, and related tasks using deep learning models designed specifically for overhead image analysis
- Evaluating performance of deep learning model predictions
## Documentation
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!
## Installation Instructions
_coming soon_: One-command installation from conda-forge.
We recommend creating a `conda` environment with the dependencies defined in [environment.yml](./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 .
```
#### pip
The package also exists on[ PyPI](https://pypi.org), but note that some of the dependencies, specifically [rtree](https://github.com/Toblerity/rtree) and [gdal](https://www.gdal.org), 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](https://libspatialindex.org), 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](https://rasterio.readthedocs.io/en/stable/installation.html) provides OS-specific install instructions. Simply follow their install instructions, replacing `pip install rasterio` with `pip install solaris` at the end.
## Dependencies
All dependencies can be found in the requirements file [./requirements.txt](requirements.txt) or
[environment.yml](./environment.yml)
## License
See [LICENSE](./LICENSE.txt).