Skip to content
CosmiQ Works Geospatial Machine Learning Analysis Toolkit
Branch: master
Clone or download
Latest commit 2ce946e May 31, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.github/ISSUE_TEMPLATE Update issue templates May 31, 2019
docker Update nvidia/cuda Docker tag to v9.2 (#106) May 29, 2019
docs
old_docs restructuring solaris Apr 19, 2019
old_setup restructuring solaris Apr 19, 2019
solaris version bump: improved setup.py May 29, 2019
static adding solaris logo May 31, 2019
tests Iss105 inf debug (#109) May 29, 2019
.gitattributes restructuring solaris Apr 19, 2019
.gitignore initial commit Apr 19, 2019
.travis.yml fixing python version support - remove 3.5 Apr 30, 2019
LICENSE.txt initial commit Apr 19, 2019
MANIFEST.in Inference tiling and image stitching (#88) May 29, 2019
PULL_REQUEST_TEMPLATE.md Update PULL_REQUEST_TEMPLATE.md May 24, 2019
README.md fixing header 2 May 31, 2019
environment.yml Iss105 inf debug (#109) May 29, 2019
readthedocs-environment.yml added PyTorch and Keras DataGenerators (#52) May 29, 2019
readthedocs.yml restructuring solaris Apr 19, 2019
renovate.json debugging renovate config file May 23, 2019
requirements.txt Update dependency numpy to v1.16.4 May 29, 2019
setup.py Merge branch 'master' of https://github.com/CosmiQ/solaris May 29, 2019

README.md

Solaris

An open source ML pipeline for overhead imagery by CosmiQ Works

PyPI python version PyPI build docs license

This package is under active development. Check back soon for updates!


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

Installation Instructions

We recommend creating a conda environment with the dependencies defined in environment.yml before installing solaris. After cloning the repository:

cd solaris
conda env create -n solaris -f environment.yml
conda activate solaris
pip install .

pip

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 dependency using conda before installing from PyPI.

conda install -c conda-forge rtree gdal=2.4.1

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 online resources may help with specific use cases.

Once you have that dependency set up, install as usual using pip:

pip install solaris

Dependencies

All dependencies can be found in the docker file Dockerfile or environment.yml

License

See LICENSE.

You can’t perform that action at this time.