Rastervision

------------------

This release brings some exciting new functionality to Raster Vision.

Highlights:

- Raster Vision can now consume imagery from STAC APIs via the newly-added :class:`.XarraySource` (see tutorial: :doc:`usage/tutorials/stac_plus_osm`).
- Raster Vision can now consume temporal data i.e. time series of images via :class:`.TemporalMultiRasterSource` and :class:`.XarraySource` (see tutorial: :doc:`usage/tutorials/temporal`).
- The model-bundles produced by now additionally include the model exported in the ONNX format and Raster Vision will use an ONNX runtime to make predictions if ``RASTERVISION_USE_ONNX=1`` is set.

API changes:

- To crop the extent of a :class:`.RasterSource` (or :class:`.LabelSource`), you now have to specify ``bbox`` instead of ``extent``. The term "extent", as used in the codebase, has also been redefined to always be the box ``Box(0, 0, height, width)``, where ``height`` and ``width`` are the height and width of the ``bbox``.
- :class:`.GeoJSONVectorSource` can now take a list of URIs, allowing geometries to be read from multiple files.
- :class:`.VectorOutputConfig` (and subclasses) no longer require ``uri`` to be specified.

Features
~~~~~~~~

- Add ``XarraySource`` to make it easier to consume imagery fetched from a STAC API (`1764 <https://github.com/azavea/raster-vision/pull/1764>`__)
- Add experimental ONNX support (`1792 <https://github.com/azavea/raster-vision/pull/1792>`__)
- Add support for temporal data (`1803 <https://github.com/azavea/raster-vision/pull/1803>`__, `#1815 <https://github.com/azavea/raster-vision/pull/1815>`__)


Fixes/minor improvements/refactoring
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

- Improve efficiency of positive-window sampling in ``ObjectDetectionRandomWindowGeoDataset`` by filtering labels by AOI (`1705 <https://github.com/azavea/raster-vision/pull/1705>`__)
- Misc object detection fixes and improvements (`1711 <https://github.com/azavea/raster-vision/pull/1711>`__)
- Allow ``GeoJSONVectorSource`` to accept multiple URIs (`1712 <https://github.com/azavea/raster-vision/pull/1712>`__)
- Allow specifying extra args for default model in ``ModelConfig`` (`1713 <https://github.com/azavea/raster-vision/pull/1713>`__)
- Ensure ``RasterSource`` and ``LabelSource`` extents match up in ``Scene`` (`1740 <https://github.com/azavea/raster-vision/pull/1740>`__)
- Allow all constituent object detection losses to be logged (`1716 <https://github.com/azavea/raster-vision/pull/1716>`__)
- Remove the ``uri`` field from ``VectorOutputConfig`` (`1762 <https://github.com/azavea/raster-vision/pull/1762>`__)
- Fix bugs related to extent-cropping (`1774 <https://github.com/azavea/raster-vision/pull/1774>`__, `#1786 <https://github.com/azavea/raster-vision/pull/1786>`__, `#1793 <https://github.com/azavea/raster-vision/pull/1793>`__)
- Fix legend placement in ``SemanticSegmentationVisualizer`` plots (`1783 <https://github.com/azavea/raster-vision/pull/1783>`__)
- Misc. refactoring and fixes (`1838 <https://github.com/azavea/raster-vision/pull/1838>`__)
- Update tutorial notebooks + misc. minor changes (`1839 <https://github.com/azavea/raster-vision/pull/1839>`__)
- Improve geometry-related validation in ``Scene`` and ``GeoJSONVectorSource`` and fix a bug in ``AoiSampler`` (`1856 <https://github.com/azavea/raster-vision/pull/1856>`__)

Development/maintenance
~~~~~~~~~~~~~~~~~~~~~~~

- Disable PDF build of docs (`1714 <https://github.com/azavea/raster-vision/pull/1714>`__)
- Improve Codecov exclusion settings, add some more unit tests, and add a unit test README (`1717 <https://github.com/azavea/raster-vision/pull/1717>`__)
- Fix CI errors (`1763 <https://github.com/azavea/raster-vision/pull/1763>`__)
- Factor out numpy-like array indexing implementation and add unit tests (`1765 <https://github.com/azavea/raster-vision/pull/1765>`__)
- Remove deprecated ``codecov`` dependency (`1775 <https://github.com/azavea/raster-vision/pull/1775>`__)
- Add ``CITATION.cff`` (`1789 <https://github.com/azavea/raster-vision/pull/1789>`__, `#1790 <https://github.com/azavea/raster-vision/pull/1790>`__)
- Minor refactoring of ``learner.py`` for readability (`1791 <https://github.com/azavea/raster-vision/pull/1791>`__)
- Conform to new torchvision API for specifying pretrained weights (`1794 <https://github.com/azavea/raster-vision/pull/1794>`__)
- Use more concise cross-referencing syntax in docs (`1809 <https://github.com/azavea/raster-vision/pull/1809>`__)
- Misc. documentation improvements (`1840 <https://github.com/azavea/raster-vision/pull/1840>`__)
- Update dependencies (`1749 <https://github.com/azavea/raster-vision/pull/1749>`__, `#1756 <https://github.com/azavea/raster-vision/pull/1756>`__, `#1760 <https://github.com/azavea/raster-vision/pull/1760>`__, `#1761 <https://github.com/azavea/raster-vision/pull/1761>`__, `#1797 <https://github.com/azavea/raster-vision/pull/1797>`__, `#1798 <https://github.com/azavea/raster-vision/pull/1798>`__, `#1799 <https://github.com/azavea/raster-vision/pull/1799>`__, `#1805 <https://github.com/azavea/raster-vision/pull/1805>`__, `#1811 <https://github.com/azavea/raster-vision/pull/1811>`__)
- Pre-release fixes and improvements (`1857 <https://github.com/azavea/raster-vision/pull/1857>`__)

----

--------------------

* Bump ``triangle`` from version ``20200424`` to ``20220202`` in ``rastervision_pytorch_learner`` (`1580 <https://github.com/azavea/raster-vision/pull/1580>`__)
* Update example plugin ``__init__.py`` files to include ``registry.set_plugin_version()`` calls (`1665 <https://github.com/azavea/raster-vision/pull/1665>`__)
* Add error handling for empty ``DataLoader`` in ``Visualizer.get_batch()`` (`1672 <https://github.com/azavea/raster-vision/pull/1672>`__)
* Only set default stride if stride value is missing in ``GeoDataWindowConfig`` (`1674 <https://github.com/azavea/raster-vision/pull/1674>`__)
* Minor doc and type-hint fixes and refactoring for OD (`1675 <https://github.com/azavea/raster-vision/pull/1675>`__, `#1676 <https://github.com/azavea/raster-vision/pull/1676>`__)

----

--------------------

Fixes
~~~~~

* Do not install ``rastervision_gdal_vsi`` by default (`1622 <https://github.com/azavea/raster-vision/pull/1622>`__)
* Do not set ``cfg.model.pretrained=False`` in ``Learner.from_model_bundle()`` (`1626 <https://github.com/azavea/raster-vision/pull/1626>`__)
* Fix docker build errors (`1629 <https://github.com/azavea/raster-vision/pull/1629>`__)
* Documentation:

* Improve docstrings for most commonly used classes and configs (`1630 <https://github.com/azavea/raster-vision/pull/1630>`__)
* Minor textual fixes for the pre-chipped datasets tutorial (`1623 <https://github.com/azavea/raster-vision/pull/1623>`__)
* Add comment about password for the ISPRS Potsdam dataset (`1627 <https://github.com/azavea/raster-vision/pull/1627>`__)

* README:

* fix broken links (`1608 <https://github.com/azavea/raster-vision/pull/1608>`__)
* make CV-tasks image slightly smaller (`1624 <https://github.com/azavea/raster-vision/pull/1624>`__)

----

------------------

This release brings major improvements to Raster Vision's **usability** as well as its **usefulness**.

Whereas previously Raster Vision was a **framework** where users could configure a *pipeline* and then let it run, it is now *also* a **library** from which users can pick individual components and use them to build new things.

We have also significantly improved the documentation. Most notably, it now contains detailed :doc:`tutorial notebooks <usage/tutorials/index>` as well a full :doc:`API reference <api_reference/index>`. The documentation for the Raster Vision pipeline, which used to make up most of the documentation in previous versions, is now located in the :doc:`framework/index` section.

In terms of features, some highlights are:

- Support for multiband imagery, introduced in v0.13 for semantic segmentation, is now also available for chip classification and object detection. (`1345 <https://github.com/azavea/raster-vision/pull/1345>`__)
- Improved data fusion: the :class:`~rastervision.core.data.raster_source.multi_raster_source.MultiRasterSource` can now combine :class:`RasterSources <rastervision.core.data.raster_source.raster_source.RasterSource>` with varying extents and resolutions. (`1308 <https://github.com/azavea/raster-vision/pull/1308>`__)
- You can now discard edges of predicted chips in semantic segmentation in order to reduce boundary artifacts (`1486 <https://github.com/azavea/raster-vision/pull/1486>`__). This can be used *in addition* to the `previously introduced <https://github.com/azavea/raster-vision/pull/1057>`__ ability to average overlapping regions in adjacent chips.
- Progress-bars will now be shown for all downloads and uploads as well as other time-consuming operations that take longer than 5 seconds.
- Improved caching of downloads: Raster Vision can now cache downloads. Also a bug that caused Raster Vision to download the same image multiple times has been fixed, resulting in significant speedups.

.. warning:: This release breaks backward-compatibility with previous versions.

Features
~~~~~~~~

- Extend multiband support to all tasks (`1345 <https://github.com/azavea/raster-vision/pull/1345>`__)
- Add support for external models for object detection (`1337 <https://github.com/azavea/raster-vision/pull/1337>`__)
- Allow ``MultiRasterSource`` to read from sub raster sources with non-identical extents and resolutions (`1308 <https://github.com/azavea/raster-vision/pull/1308>`__)
- Allow discarding edges of predicted chips in semantic segmentation (`1486 <https://github.com/azavea/raster-vision/pull/1486>`__)
- Add numpy-like array indexing and slicing to ``RasterSource`` and ``LabelSource`` (`1470 <https://github.com/azavea/raster-vision/pull/1470>`__)
- Make ``RandomWindowGeoDataset`` more efficient when sampling chips from scenes with sparse AOIs (`1225 <https://github.com/azavea/raster-vision/pull/1225>`__)
- Add support for Albumentations' lambda transforms (`1368 <https://github.com/azavea/raster-vision/pull/1368>`__)
- Provide grouping mechanism for scenes and use it in the ``analyze`` and ``eval`` stages (`1375 <https://github.com/azavea/raster-vision/pull/1375>`__)
- Update STAC-reading functionality to make it compatible with STAC v1.0.* (`1243 <https://github.com/azavea/raster-vision/pull/1243>`__)
- Add progress bars for downloads and uploads (`1343 <https://github.com/azavea/raster-vision/pull/1343>`__)
- Allow caching downloads (`1450 <https://github.com/azavea/raster-vision/pull/1450>`__)

Refactoring
~~~~~~~~~~~

- Refactor ``Learner`` and related configs to be more flexible and easier to use in a notebook (`1413 <https://github.com/azavea/raster-vision/pull/1413>`__)
- Refactor to make it easier to programmatically make predictions on new scenes (`1434 <https://github.com/azavea/raster-vision/pull/1434>`__)
- Refactor: make ``Evaluator`` easier to use independently (`1438 <https://github.com/azavea/raster-vision/pull/1438>`__)
- Refactor vector data handling (`1437 <https://github.com/azavea/raster-vision/pull/1437>`__, `#1461 <https://github.com/azavea/raster-vision/pull/1461>`__)
- Add ``GeoDataset.from_uris()`` for convenient initialization of ``GeoDatasets`` (`1462 <https://github.com/azavea/raster-vision/pull/1462>`__, `#1588 <https://github.com/azavea/raster-vision/pull/1588>`__)
- Add ``Labels.save()`` convenience method (`1486 <https://github.com/azavea/raster-vision/pull/1486>`__)
- Factor out dataset visualization into a ``Visualizer`` class (`1476 <https://github.com/azavea/raster-vision/pull/1476>`__)
- Replace ``STRTree`` with GeoPandas ``GeoDataFrame``-based spatial joins in ``ChipClassificaitonLabelSource`` and ``RasterizedSource`` (`1470 <https://github.com/azavea/raster-vision/pull/1470>`__)
- Remove ``ActivateMixin`` entirely (`1470 <https://github.com/azavea/raster-vision/pull/1470>`__)
- Remove the ``mask-to-polygons`` dependency (`1470 <https://github.com/azavea/raster-vision/pull/1470>`__)

Documentation
~~~~~~~~~~~~~

- Update documentation site (`1501 <https://github.com/azavea/raster-vision/pull/1501>`__, `#1589 <https://github.com/azavea/raster-vision/pull/1589>`__)
- Refactor documentation (`1561 <https://github.com/azavea/raster-vision/pull/1561>`__)
- Add tutorial notebooks (`1470 <https://github.com/azavea/raster-vision/pull/1470>`__, `#1506 <https://github.com/azavea/raster-vision/pull/1506>`__, `#1586 <https://github.com/azavea/raster-vision/pull/1586>`__, `#1546 <https://github.com/azavea/raster-vision/pull/1546>`__)
- Add code of conduct (`1160 <https://github.com/azavea/raster-vision/pull/1160>`__)

Fixes
~~~~~

- Speed up ``RGBClassTransformer`` by an order of magnitude (`1485 <https://github.com/azavea/raster-vision/pull/1485>`__)
- Fix ``rastervision_pipeline`` entry point to ensure commands from other plugins are available (`1250 <https://github.com/azavea/raster-vision/pull/1250>`__)
- Fix incorrect F1 scores when aggregating evals for scenes in the eval stage (`1386 <https://github.com/azavea/raster-vision/pull/1386>`__)
- Fix bug in semantic segmentation prediction output paths (`1354 <https://github.com/azavea/raster-vision/pull/1354>`__)
- Do not zero out null class pixels when creating semantic segmentation training chips (`1556 <https://github.com/azavea/raster-vision/pull/1556>`__)
- Fix a bug in ``DataConfig`` validation and refactor ``ClassConfig`` (`1436 <https://github.com/azavea/raster-vision/pull/1436>`__)
- Fix `1052 <https://github.com/azavea/raster-vision/pull/1052>`__ (`#1451 <https://github.com/azavea/raster-vision/pull/1451>`__)
- Fix `991 <https://github.com/azavea/raster-vision/pull/991>`__ and `#1452 <https://github.com/azavea/raster-vision/pull/1452>`__ (`#1484 <https://github.com/azavea/raster-vision/pull/1484>`__)
- Fix `1430 <https://github.com/azavea/raster-vision/pull/1430>`__ (`#1495 <https://github.com/azavea/raster-vision/pull/1495>`__)
- Misc. fixes (`1260 <https://github.com/azavea/raster-vision/pull/1260>`__, `#1281 <https://github.com/azavea/raster-vision/pull/1281>`__, `#1453 <https://github.com/azavea/raster-vision/pull/1453>`__)

Development/maintenance
~~~~~~~~~~~~~~~~~~~~~~~

- Make the semantic segmentation integration test more deterministic (`1261 <https://github.com/azavea/raster-vision/pull/1261>`__)
- Migrate from Travis to GitHub Actions (`1218 <https://github.com/azavea/raster-vision/pull/1218>`__)
- Add Github issue templates (`1242 <https://github.com/azavea/raster-vision/pull/1242>`__, `#1288 <https://github.com/azavea/raster-vision/pull/1288>`__, `#1420 <https://github.com/azavea/raster-vision/pull/1420>`__)
- Switch from Gitter to Github Discussions (`1464 <https://github.com/azavea/raster-vision/pull/1464>`__, `#1465 <https://github.com/azavea/raster-vision/pull/1465>`__)
- Update cloudformation template to allow use of on-demand GPU instances (`1482 <https://github.com/azavea/raster-vision/pull/1482>`__)
- Add option to build ARM64 Docker image (`1545 <https://github.com/azavea/raster-vision/pull/1545>`__, `#1559 <https://github.com/azavea/raster-vision/pull/1559>`__)
- Make ``docker/run`` automatically find a free port for Jupyter server if the default port is already taken (`1558 <https://github.com/azavea/raster-vision/pull/1558>`__)
- Set tutorial-notebooks path as the default jupyter path in ``docker/run`` (`1595 <https://github.com/azavea/raster-vision/pull/1595>`__)

----

--------------------

Bug Fixes
~~~~~~~~~

* Fix image plot by adding default plot transform `1144 <https://github.com/azavea/raster-vision/pull/1144>`__

------------------

This release presents a major jump in Raster Vision's power and flexibility. The most significant changes are:

Support arbitrary models and loss functions (`985 <https://github.com/azavea/raster-vision/pull/985>`__, `#992 <https://github.com/azavea/raster-vision/pull/992>`__)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Raster Vision is no longer restricted to using the built in models and loss functions. It is now possible to import models and loss functions from a GitHub repo or a URI or a zip file as long as they interface correctly with RV's learner code. This means that you can now easily swap models in your existing training pipelines, allowing you to take advantage of the latest models or to make customizations that help with your specific task; all with minimal changes.

This is made possible by PyTorch's ``hub`` module.

Currently not supported for Object Detection.

Support for multiband images (even with Transfer Learning) (`972 <https://github.com/azavea/raster-vision/pull/972>`__)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

It is now possible to train on imagery with more than 3 channels. Raster Vision automatically modifies the model to be able to accept more than 3 channels. If using pretrained models, the pre-learned weights are retained.

The model modification cannot be performed automatically when using an external model. But as long as the external model supports multiband inputs, it will work correctly with RV.

Currently only supported for Semantic Segmentation.

Support for reading directly from raster sources during training without chipping (`1046 <https://github.com/azavea/raster-vision/pull/1046>`__)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

It is no longer necessary to go through a ``chip`` stage to produce a training dataset. You can instead provide the ``DatasetConfig`` directly to the PyTorch backend and RV will sample training chips on the fly during training. All the examples now use this as the default. Check them out to see how to use this feature.

Support for arbitrary Albumentations transforms (`1001 <https://github.com/azavea/raster-vision/pull/1001>`__)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

It is now possible to supply an arbitrarily complicated Albumentations transform for data augmentation. In the ``DataConfig`` subclasses, you can specify a ``base_transform`` that is applied every time (i.e. in training, validation, and prediction), an ``aug_transform`` that is only applied during training, and a ``plot_transform`` (via ``PlotOptions``) to ensure that sample images are plotted correctly (e.g. use ``plot_transform`` to rescale a normalized image to 0-1).

Allow streaming reads from Rasterio sources (`1020 <https://github.com/azavea/raster-vision/pull/1020>`__)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

It is now possible to stream chips from a remote ``RasterioSource`` without first downloading the entire file. To enable, set ``allow_streaming=True`` in the ``RasterioSourceConfig``.

Analyze stage no longer necessary when using non-uint8 rasters (`972 <https://github.com/azavea/raster-vision/pull/972>`__)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

It is no longer necessary to go through an ``analyze`` stage to be able to convert non-``uint8`` rasters to ``uint8`` chips. Chips can now be stored as ``numpy`` arrays, and will be normalized to ``float`` during training/prediction based on their specific data type. See ``spacenet_vegas.py`` for example usage.

Currently only supported for Semantic Segmentation.

Features
~~~~~~~~

* Add support for multiband images `972 <https://github.com/azavea/raster-vision/pull/972>`__
* Add support for vector output to predict command `980 <https://github.com/azavea/raster-vision/pull/980>`__
* Add support for weighted loss for classification and semantic segmentation `977 <https://github.com/azavea/raster-vision/pull/977>`__
* Add multi raster source `978 <https://github.com/azavea/raster-vision/pull/978>`__
* Add support for fetching and saving external model definitions `985 <https://github.com/azavea/raster-vision/pull/985>`__
* Add support for external loss definitions `992 <https://github.com/azavea/raster-vision/pull/992>`__
* Upgrade to pyproj 2.6 `1000 <https://github.com/azavea/raster-vision/pull/1000>`__
* Add support for arbitrary albumentations transforms `1001 <https://github.com/azavea/raster-vision/pull/1001>`__
* Minor tweaks to regression learner `1013 <https://github.com/azavea/raster-vision/pull/1013>`__
* Add ability to specify number of PyTorch reader processes `1008 <https://github.com/azavea/raster-vision/pull/1008>`__
* Make img_sz specifiable `1012 <https://github.com/azavea/raster-vision/pull/1012>`__
* Add ignore_last_class capability to segmentation `1017 <https://github.com/azavea/raster-vision/pull/1017>`__
* Add filtering capability to segmentation sliding window chip generation `1018 <https://github.com/azavea/raster-vision/pull/1018>`__
* Add raster transformer to remove NaNs from float rasters, add raster transformers to cast to arbitrary numpy types `1016 <https://github.com/azavea/raster-vision/pull/1016>`__
* Add plot options for regression `1023 <https://github.com/azavea/raster-vision/pull/1023>`__
* Add ability to use fewer channels w/ pretrained models `1026 <https://github.com/azavea/raster-vision/pull/1026>`__
* Remove 4GB file size limit from VSI file system, allow streaming reads `1020 <https://github.com/azavea/raster-vision/pull/1020>`__
* Add reclassification transformer for segmentation label rasters `1024 <https://github.com/azavea/raster-vision/pull/1024>`__
* Allow filtering out chips based on proportion of NODATA pixels `1025 <https://github.com/azavea/raster-vision/pull/1025>`__
* Allow ignore_last_class to take either a boolean or the literal 'force'; in the latter case validation of that argument is skipped so that it can be used with external loss functions `1027 <https://github.com/azavea/raster-vision/pull/1027>`__
* Add ability to crop raster source extent `1030 <https://github.com/azavea/raster-vision/pull/1030>`__
* Accept immediate geometries in SceneConfig `1033 <https://github.com/azavea/raster-vision/pull/1033>`__
* Only perform normalization on unsigned integer types `1028 <https://github.com/azavea/raster-vision/pull/1028>`__
* Make group_uris specifiable and add group_train_sz_rel `1035 <https://github.com/azavea/raster-vision/pull/1035>`__
* Make number of training and dataloader previews independent of batch size `1038 <https://github.com/azavea/raster-vision/pull/1038>`__
* Allow continuing training from a model bundle `1022 <https://github.com/azavea/raster-vision/pull/1022>`__
* Allow reading directly from raster source during training without chipping `1046 <https://github.com/azavea/raster-vision/pull/1046>`__
* Remove external commands (obsoleted by external architectures and loss functions) `1047 <https://github.com/azavea/raster-vision/pull/1047>`__
* Allow saving SS predictions as probabilities `1057 <https://github.com/azavea/raster-vision/pull/1057>`__
* Update CUDA version from 10.1 to 10.2 `1115 <https://github.com/azavea/raster-vision/pull/1115>`__
* Add integration tests for the nochip functionality `1116 <https://github.com/azavea/raster-vision/pull/1116>`__
* Update examples to make use of the nochip functionality by default `1116 <https://github.com/azavea/raster-vision/pull/1116>`__

Bug Fixes
~~~~~~~~~~~~

* Update all relevant saved URIs in config before instantiating Pipeline `993 <https://github.com/azavea/raster-vision/pull/993>`__
* Pass verbose flag to batch jobs `988 <https://github.com/azavea/raster-vision/pull/988>`__
* Fix: Ensure Integer class_id `990 <https://github.com/azavea/raster-vision/pull/990>`__
* Use ``--ipc=host`` by default when running the docker container `1077 <https://github.com/azavea/raster-vision/pull/1077>`__

----