Releases: azavea/raster-vision
Raster Vision v0.30.1
Changelog
Features:
- Allow passing pipeline configs as JSON files to the
rastervision run
CLI cmd (#2136)- (as an alternative to the traditional method of passing a
.py
file with aget_config()
function)
- (as an alternative to the traditional method of passing a
Fixes:
- Add
rastervision_aws_sagemaker
to API reference on RTD (#2117) - Let
RasterSource.get_chip_by_map_window()
take allRasterSource.get_chip()
args (#2136) - Make repr more concise for some configs (#2136)
- Misc config serialization fixes and improvements (#2136)
- Avoid double-wrapping model in
DistributedDataParallel
(#2136) - Make
S3FileSystem.list_paths()
only list direct children (#2136) - Add missing
RequestPayer
arg to some s3-relatedboto3
API calls (#2136) - Fix incorrect path in RV pipeline examples doc (#2138)
Maintenance:
Raster Vision v0.30
Changelog
- Full changelog: https://docs.rastervision.io/en/0.30/changelog.html#raster-vision-0-30
- Migration guide: https://docs.rastervision.io/en/0.30/migration/v0-21_to_v0-30.html
Highlights
- Easier installation: Raster Vision no longer requires exact versions of dependencies, which means it can more easily be installed alongside other packages.
- AWS SageMaker support: you can now run Raster Vision jobs on SageMaker via
You can even run training over multiple instances with multiple GPUs. See Running on AWS SageMaker for more details.
rastervision run sagemaker ...
- Distributed training support: Raster Vision Learners now support distributed training (both multi-node and multi-GPU) via PyTorch DDP. If your machine has multiple GPUs, Raster Vision will now automatically use them all during training.
- New CLI command, predict_scene, that allows greater configurability than the
predict
command.rastervision predict_scene <model_bundle_uri> <scene_config_uri> [--predict_options_uri <predict_options_uri>]
- New tutorial: Predicting with an ONNX model.
PyPI
pip install rastervision==0.30.0
https://pypi.org/project/rastervision/0.30.0/
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.30
Raster Vision 0.21.3
Changelog
Full changelog: https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21-3
Highlights
- Features:
- Allow reading pre-chipped datasets with non-RGB TIFF chips (#1932)
- Bug fixes:
- Normalize pixel values in the Spacenet Vegas examples (#1930)
- Account for bbox when saving predictions (#1931)
- Bug fix: ensure SS datasets always return label array with correct dtype (#1954)
- Fix bug in Visualizer when plotting temporal data w/ batch size 1 (#1958)
- Allow specifying
chip_sz
inStatsTransform.from_raster_sources()
(#1933) - Misc. minor fixes (#1933)
- Docs:
- Update release instructions to simplify patch release process (#1934)
- Maintenance:
- Bump pillow to address CVE-2023-4863 (#1952)
- Update CI and release workflows to free up disk space before building docker image (#1953, #1959)
Pypi
pip install rastervision==0.21.3
https://pypi.org/project/rastervision/0.21.3/
Notes
- The
pip
installation is only guaranteed to work with Python 3.10.
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.21
Raster Vision 0.21.2
Changelog
Full changelog: https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21-2
Highlights
- Features:
- Save model weights for each epoch (#1921) (@mmcs-work)
- Bug fixes:
Pypi
pip install rastervision==0.21.2
https://pypi.org/project/rastervision/0.21.2/
Notes
- The
pip
installation is only guaranteed to work with Python 3.10.
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.21
Raster Vision 0.21.1
Changelog
https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21-1
Pypi
pip install rastervision==0.21.1
https://pypi.org/project/rastervision/0.21.1/
Notes
- The
pip
installation is only guaranteed to work with Python 3.10.
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.21
Raster Vision 0.21
Highlights
- Raster Vision can now consume imagery from STAC APIs
- Tutorial: Imagery from STAC API + labels from OSM
- Raster Vision can now work with temporal data
- Tutorial: Working with time-series of images
- Raster Vision can now export and use models in ONNX format
Changelog
https://docs.rastervision.io/en/0.21/changelog.html#raster-vision-0-21
Pypi
pip install rastervision==0.21
https://pypi.org/project/rastervision/0.21/
Notes
- The
pip
installation is only guaranteed to work with Python 3.10. Anaconda is highly recommended.
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.21
Raster Vision 0.20.2
This is a dummy release to trigger the generation of a DOI on Zenodo.
Raster Vision 0.20.2
Changelog
https://docs.rastervision.io/en/0.20/changelog.html#raster-vision-0-20-2
Pypi
pip install rastervision==0.20.2
https://pypi.org/project/rastervision/0.20.2/
Notes
- The
pip
installation is only guaranteed to work with Python 3.9. Anaconda is highly recommended.
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.20
Raster Vision 0.20.1
Changelog
https://docs.rastervision.io/en/0.20/changelog.html#raster-vision-0-20-1
Pypi
pip install rastervision==0.20.1
https://pypi.org/project/rastervision/0.20.1/
Notes
- The
pip
installation is only guaranteed to work with Python 3.9. Anaconda is highly recommended.
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.20
Raster Vision 0.20
Changelog
https://docs.rastervision.io/en/0.20/changelog.html#raster-vision-0-20-0
Pypi
pip install rastervision==0.20
https://pypi.org/project/rastervision/0.20/
Notes
- The
pip
installation is only guaranteed to work with Python 3.9. Anaconda is highly recommended. - If you encounter problems with
gdal
installation while installingrastervision_gdal_vsi
, you can- try installing
gdal
viaconda install -c conda-forge gdal==3.5.2
- install all Raster Vision plugins except
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
- try installing
Docker image
docker pull quay.io/azavea/raster-vision:pytorch-0.20