rastervision
An open source library and framework for deep learning on satellite and aerial imagery.
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
✓Committers with academic emails
1 of 37 committers (2.7%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (18.7%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
An open source library and framework for deep learning on satellite and aerial imagery.
Basic Info
- Host: GitHub
- Owner: azavea
- License: other
- Language: Python
- Default Branch: master
- Homepage: https://docs.rastervision.io
- Size: 90.4 MB
Statistics
- Stars: 2,161
- Watchers: 71
- Forks: 392
- Open Issues: 39
- Releases: 23
Topics
Metadata Files
README.md
Raster Vision is an open source Python library and framework for building computer vision models on satellite, aerial, and other large imagery sets (including oblique drone imagery).
It has built-in support for chip classification, object detection, and semantic segmentation with backends using PyTorch.
As a library, Raster Vision provides a full suite of utilities for dealing with all aspects of a geospatial deep learning workflow: reading geo-referenced data, training models, making predictions, and writing out predictions in geo-referenced formats.
As a low-code framework, Raster Vision allows users (who don't need to be experts in deep learning!) to quickly and repeatably configure experiments that execute a machine learning pipeline including: analyzing training data, creating training chips, training models, creating predictions, evaluating models, and bundling the model files and configuration for easy deployment.
Raster Vision also has built-in support for running experiments in the cloud using AWS Batch as well as AWS Sagemaker.
See the documentation for more details.
Installation
For more details, see the Setup documentation.
Install via pip
You can install Raster Vision directly via pip.
sh
pip install rastervision
Use Pre-built Docker Image
Alternatively, you may use a Docker image. Docker images are published to quay.io (see the tags tab).
We publish a new tag per merge into master, which is tagged with the first 7 characters of the commit hash. To use the latest version, pull the latest suffix, e.g. raster-vision:pytorch-latest. Git tags are also published, with the Github tag name as the Docker tag suffix.
Build Docker Image
You can also build a Docker image from scratch yourself. After cloning this repo, run docker/build, and run then the container using docker/run.
Usage Examples and Tutorials
Non-developers may find it easiest to use Raster Vision as a low-code framework where Raster Vision handles all the complexities and the user only has to configure a few parameters. The Quickstart guide is a good entry-point into this. More advanced examples can be found on the Examples page.
For developers and those looking to dive deeper or combine Raster Vision with their own code, the best starting point is Usage Overview, followed by Basic Concepts and Tutorials.
Contact and Support
You can ask questions and talk to developers (let us know what you're working on!) at: * Discussion Forum * Mailing List
Developing
To set up the development environment:
- For and clone the repo and navigate to it.
- Create and activate a new Python virtual environment via your environment manager of choice (mamba, uv, pyenv, etc.).
- Run scripts/setup_dev_env.sh to install all Raster Vision plugins in editable mode along with all the dependencies.
Contributing
For more information, see Contributing.
We are happy to take contributions! It is best to get in touch with the maintainers about larger features or design changes before starting the work, as it will make the process of accepting changes smoother.
Everyone who contributes code to Raster Vision will be asked to sign a Contributor License Agreement. See Contributing for instructions.
Licenses
Raster Vision is licensed under the Apache 2 license. See license here.
3rd party licenses for all dependecies used by Raster Vision can be found here.
Owner
- Name: Azavea
- Login: azavea
- Kind: organization
- Location: Philadelphia, PA
- Website: https://www.azavea.com
- Repositories: 383
- Profile: https://github.com/azavea
Geospatial software engineering for good
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "Azavea/Element 84, Robert Cheetham" city: "Philadelphia, PA" title: "Raster Vision: An open source library and framework for deep learning on satellite and aerial imagery (2017-2023)." doi: 10.5281/zenodo.8018177 url: "https://github.com/azavea/raster-vision"
GitHub Events
Total
- Issues event: 3
- Watch event: 91
- Delete event: 34
- Issue comment event: 95
- Push event: 13
- Pull request event: 92
- Fork event: 11
- Create event: 36
Last Year
- Issues event: 3
- Watch event: 91
- Delete event: 34
- Issue comment event: 95
- Push event: 13
- Pull request event: 92
- Fork event: 11
- Create event: 36
Committers
Last synced: 8 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Lewis Fishgold | l****h@g****m | 1,095 |
| ahassan@azavea.com | a****3@g****m | 990 |
| lossyrob | r****e@g****m | 331 |
| James McClain | j****n@a****m | 331 |
| dependabot[bot] | 4****] | 65 |
| Simon Kassel | s****l@a****m | 35 |
| jpolchlo | j****k@a****m | 21 |
| Unknown | a****o@g****m | 16 |
| Joe Morrison | j****n@a****m | 13 |
| James Santucci | j****i@g****m | 8 |
| lmbak | b****s@g****m | 7 |
| Bborie Park | b****k@g****g | 3 |
| Nathan Holeman | n****n@g****m | 3 |
| Rocky Breslow | r****w@a****m | 3 |
| Taylor Nation | t****4@g****m | 3 |
| Bborie Park | d****s@g****m | 2 |
| Per Liedman | p****r@l****t | 2 |
| Umang Kalra | u****0@g****m | 2 |
| Ammar Sani | a****c@g****m | 1 |
| Jerome Maleski | j****i@g****m | 1 |
| Kelly Innes | k****s@a****m | 1 |
| Chris Brown | c****n@a****m | 1 |
| Ashwin Nair | a****r@i****g | 1 |
| Kevin Mentzer | k****r@e****m | 1 |
| Andreas Meier | 5****3 | 1 |
| Chuck McCallum | m****c | 1 |
| Cole Kettler | me@c****m | 1 |
| Eugene Cheipesh | e****h@g****m | 1 |
| Grigory Pomadchin | g****n@g****m | 1 |
| Matt Bertrand | m****t@m****u | 1 |
| and 7 more... | ||
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 4 months ago
All Time
- Total issues: 54
- Total pull requests: 533
- Average time to close issues: 11 months
- Average time to close pull requests: 27 days
- Total issue authors: 24
- Total pull request authors: 13
- Average comments per issue: 2.65
- Average comments per pull request: 1.05
- Merged pull requests: 183
- Bot issues: 0
- Bot pull requests: 346
Past Year
- Issues: 7
- Pull requests: 96
- Average time to close issues: 1 day
- Average time to close pull requests: 29 days
- Issue authors: 6
- Pull request authors: 5
- Average comments per issue: 2.0
- Average comments per pull request: 0.64
- Merged pull requests: 15
- Bot issues: 0
- Bot pull requests: 80
Top Authors
Issue Authors
- AdeelH (10)
- lewfish (7)
- lcoandrade (4)
- chrisjkuch (4)
- jamesmcclain (3)
- skylning (3)
- robmarkcole (2)
- bdevoghel (2)
- dependabot[bot] (2)
- S-AQ (2)
- bnascimento (2)
- zejian99 (1)
- diogoamore (1)
- echeipesh (1)
- ylfmsn (1)
Pull Request Authors
- dependabot[bot] (494)
- AdeelH (218)
- jamesmcclain (7)
- mentzerk (2)
- giswqs (2)
- keves1 (2)
- Haoyu-Gao (2)
- ZhipengXue97 (2)
- cpuah (1)
- bdevoghel (1)
- NripeshN (1)
- BryanQuigley (1)
- mmcs-work (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 15
-
Total downloads:
- pypi 24,905 last-month
-
Total dependent packages: 23
(may contain duplicates) -
Total dependent repositories: 14
(may contain duplicates) - Total versions: 155
- Total maintainers: 2
pypi.org: rastervision
An open source framework for deep learning on satellite and aerial imagery
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
pypi.org: rastervision-pipeline
The main rastervision package for configuring, defining, and running pipelines
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-pipeline.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
pypi.org: rastervision-core
A rastervision plugin that adds geospatial machine learning pipelines
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-core.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
pypi.org: rastervision-pytorch-learner
A rastervision plugin that adds PyTorch training pipelines
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-pytorch-learner.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
pypi.org: rastervision-aws-s3
A rastervision plugin that adds an AWS S3 file system
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-aws-s3.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
pypi.org: rastervision-pytorch-backend
A rastervision plugin that adds PyTorch backends for rastervision.core pipelines
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-pytorch-backend.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
pypi.org: rastervision-aws-batch
A rastervision plugin that adds an AWS Batch pipeline runner
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-aws-batch.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
proxy.golang.org: github.com/azavea/raster-vision
- Documentation: https://pkg.go.dev/github.com/azavea/raster-vision#section-documentation
- License: other
-
Latest release: v0.31.1
published over 1 year ago
Rankings
pypi.org: rastervision-gdal-vsi
A rastervision plugin that adds a GDAL VSI file system
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-gdal-vsi.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
conda-forge.org: rastervision-pipeline
- Homepage: https://github.com/azavea/raster-vision
- License: Apache-2.0
-
Latest release: 0.13.1
published over 4 years ago
Rankings
conda-forge.org: rastervision-aws-batch
- Homepage: https://github.com/azavea/raster-vision
- License: Apache-2.0
-
Latest release: 0.13.1
published about 4 years ago
Rankings
conda-forge.org: rastervision-aws-s3
- Homepage: https://github.com/azavea/raster-vision
- License: Apache-2.0
-
Latest release: 0.13.1
published about 4 years ago
Rankings
conda-forge.org: rastervision-core
- Homepage: https://github.com/azavea/raster-vision
- License: Apache-2.0
-
Latest release: 0.13.1
published over 4 years ago
Rankings
conda-forge.org: rastervision-gdal-vsi
- Homepage: https://github.com/azavea/raster-vision
- License: Apache-2.0
-
Latest release: 0.13.1
published about 4 years ago
Rankings
pypi.org: rastervision-aws-sagemaker
A rastervision plugin that adds an AWS SageMaker pipeline runner
- Homepage: https://github.com/azavea/raster-vision
- Documentation: https://rastervision-aws-sagemaker.readthedocs.io/
- License: Apache License 2.0
-
Latest release: 0.31.1
published over 1 year ago
Rankings
Maintainers (2)
Dependencies
- rastervision ==0.13
- x.strip *
- Pallets-Sphinx-Themes *
- Sphinx *
- actions/checkout v2 composite
- codecov/codecov-action v2 composite
- actions/checkout v2 composite
- codecov/codecov-action v2 composite
- nvidia/cuda ${CUDA_VERSION}-cudnn8-runtime-ubuntu${UBUNTU_VERSION} build
- {{cookiecutter.parent_docker_image}} latest build
- awscli ==1.29.8
- boto3 ==1.28.8
- rastervision_pipeline ==0.21.4
- x.strip *
- awscli ==1.29.8
- boto3 ==1.28.8
- rastervision_pipeline ==0.21.4
- tqdm ==4.65.0
- x.strip *
- boto3 ==1.28.8
- geopandas ==0.13.2
- numpy ==1.25.0
- opencv-python-headless ==4.6.0.66
- pillow ==10.0.1
- pyproj ==3.4.0
- pystac ==1.6.1
- rasterio ==1.3.7
- rastervision_pipeline ==0.21.4
- scikit-image ==0.21.0
- scikit-learn ==1.2.2
- scipy ==1.10.1
- shapely ==2.0.1
- tqdm ==4.65.0
- xarray ==2023.2.0
- x.strip *
- gdal >=3.4.1,<=3.6.3
- rastervision_pipeline ==0.21.4
- x.strip *
- click ==8.1.3
- everett ==3.2.0
- pydantic ==1.10.7
- six ==1.16.
- tqdm ==4.65.0
- typing_extensions ==4.6.3
- x.strip *
- rastervision_aws_s3 ==0.21.4
- rastervision_core ==0.21.4
- rastervision_pipeline ==0.21.4
- rastervision_pytorch_learner ==0.21.4
- x.strip *
- albumentations ==1.3.0
- cython ==0.29.35
- matplotlib ==3.7.1
- numpy ==1.25.0
- onnx ==1.14.0
- onnxruntime-gpu ==1.15.0
- opencv-python-headless ==4.6.0.66
- pillow ==10.0.1
- psutil ==5.9.3
- pycocotools ==2.0.7
- rastervision_core ==0.21.4
- rastervision_pipeline ==0.21.4
- tensorboard ==2.13.0
- torch ==2.0.1
- torchvision ==0.15.2
- tqdm ==4.65.0
- triangle ==20220202
- x.strip *
- coverage ==7.2.0 development
- flake8 ==5.0.4 development
- jupyter ==1.0.0 development
- jupyter_contrib_nbextensions ==0.7.0 development
- jupyterlab ==4.0.4 development
- moto ==4.0.8 development
- seaborn ==0.12.2 development
- sphinx-autobuild ==2021.3.14 development
- unify ==0.5 development
- yapf ==0.23.0 development
- rastervision_aws_batch ==0.21.4
- rastervision_aws_s3 ==0.21.4
- rastervision_core ==0.21.4
- rastervision_pipeline ==0.21.4
- rastervision_pytorch_backend ==0.21.4
- rastervision_pytorch_learner ==0.21.4
- x.strip *
- rastervision_pipeline ==0.21.4
- sagemaker ==2.196.0
- x.strip *