An open source library and framework for deep learning on satellite and aerial imagery.
Features:
rastervision run
CLI cmd (#2136)
.py
file with a get_config()
function)Fixes:
rastervision_aws_sagemaker
to API reference on RTD (#2117)RasterSource.get_chip_by_map_window()
take all RasterSource.get_chip()
args (#2136)DistributedDataParallel
(#2136)S3FileSystem.list_paths()
only list direct children (#2136)RequestPayer
arg to some s3-related boto3
API calls (#2136)Maintenance:
rastervision run sagemaker ...
You can even run training over multiple instances with multiple GPUs. See Running on AWS SageMaker for more details.predict
command.
rastervision predict_scene <model_bundle_uri> <scene_config_uri> [--predict_options_uri <predict_options_uri>]
pip install rastervision==0.30.0
https://pypi.org/project/rastervision/0.30.0/
docker pull quay.io/azavea/raster-vision:pytorch-0.30
Full changelog: https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21-3
Highlights
chip_sz
in StatsTransform.from_raster_sources()
(#1933)pip install rastervision==0.21.3
https://pypi.org/project/rastervision/0.21.3/
Notes
pip
installation is only guaranteed to work with Python 3.10.docker pull quay.io/azavea/raster-vision:pytorch-0.21
Full changelog: https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21-2
Highlights
pip install rastervision==0.21.2
https://pypi.org/project/rastervision/0.21.2/
Notes
pip
installation is only guaranteed to work with Python 3.10.docker pull quay.io/azavea/raster-vision:pytorch-0.21
https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21-1
pip install rastervision==0.21.1
https://pypi.org/project/rastervision/0.21.1/
Notes
pip
installation is only guaranteed to work with Python 3.10.docker pull quay.io/azavea/raster-vision:pytorch-0.21
https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21
pip install rastervision==0.21
https://pypi.org/project/rastervision/0.21/
Notes
pip
installation is only guaranteed to work with Python 3.10. Anaconda is highly recommended.docker pull quay.io/azavea/raster-vision:pytorch-0.21
This is a dummy release to trigger the generation of a DOI on Zenodo.
https://docs.rastervision.io/en/0.20/changelog.html#raster-vision-0-20-2
pip install rastervision==0.20.2
https://pypi.org/project/rastervision/0.20.2/
Notes
pip
installation is only guaranteed to work with Python 3.9. Anaconda is highly recommended.docker pull quay.io/azavea/raster-vision:pytorch-0.20
https://docs.rastervision.io/en/0.20/changelog.html#raster-vision-0-20-1
pip install rastervision==0.20.1
https://pypi.org/project/rastervision/0.20.1/
Notes
pip
installation is only guaranteed to work with Python 3.9. Anaconda is highly recommended.docker pull quay.io/azavea/raster-vision:pytorch-0.20
https://docs.rastervision.io/en/0.20/changelog.html#raster-vision-0-20-0
pip install rastervision==0.20
https://pypi.org/project/rastervision/0.20/
Notes
pip
installation is only guaranteed to work with Python 3.9. Anaconda is highly recommended.gdal
installation while installing rastervision_gdal_vsi
, you can
gdal
via conda install -c conda-forge gdal==3.5.2
rastervision_gdal_vsi
pip install \
rastervision_pipeline==0.20 \
rastervision_aws_s3==0.20 \
rastervision_aws_batch==0.20 \
rastervision_core==0.20 \
rastervision_pytorch_learner==0.20 \
rastervision_pytorch_backend==0.20
docker pull quay.io/azavea/raster-vision:pytorch-0.20