Fix typos (#1963)

docs/changelog.rst

@@ -409,7 +409,7 @@ Raster Vision 0.11
 Features
 ~~~~~~~~
 
-- Added the possibility for chip classification to use data augmentors from the albumentations libary to enhance the training data. `#859 <https://github.com/azavea/raster-vision/pull/859>`__
+- Added the possibility for chip classification to use data augmentors from the albumentations library to enhance the training data. `#859 <https://github.com/azavea/raster-vision/pull/859>`__
 - Updated the Quickstart doc with pytorch docker image and model `#863 <https://github.com/azavea/raster-vision/pull/863>`__
 - Added the possibility to deal with class imbalances through oversampling. `#868 <https://github.com/azavea/raster-vision/pull/868>`__
 

docs/conf.py

@@ -283,7 +283,7 @@ def setup(app: 'Sphinx') -> None:
 
 # The name of the Pygments (syntax highlighting) style to use.
 #
-# To see all availabel values:
+# To see all available values:
 # >>> from pygments.styles import get_all_styles
 # >>> styles = list(get_all_styles())
 #

docs/setup/gpu.rst

@@ -51,7 +51,7 @@ or use the ``--gpu`` option with the ``docker/run`` script.
 Running on AWS EC2
 ------------------
 
-The simplest way to run Raster Vision on an AWS GPU is by starting a GPU-enabled EC2 instance such as a p3.2xlarge using the `Deep Learning AMI <https://aws.amazon.com/machine-learning/amis/>`_. We have tested this using the "Deep Learning AMI GPU PyTorch 1.11.0 (Ubuntu 20.04)" with id ``ami-0c968d7ef8a4b0c34``. After SSH'ing into the instance, Raster Vision can be installed with ``pip``, and code can be transfered to this instance with a tool such as ``rsync``.
+The simplest way to run Raster Vision on an AWS GPU is by starting a GPU-enabled EC2 instance such as a p3.2xlarge using the `Deep Learning AMI <https://aws.amazon.com/machine-learning/amis/>`_. We have tested this using the "Deep Learning AMI GPU PyTorch 1.11.0 (Ubuntu 20.04)" with id ``ami-0c968d7ef8a4b0c34``. After SSH'ing into the instance, Raster Vision can be installed with ``pip``, and code can be transferred to this instance with a tool such as ``rsync``.
 
 .. _aws batch setup:
 

docs/usage/tutorials/reading_vector_data.ipynb

@@ -533,7 +533,7 @@
     "tags": []
    },
    "source": [
-    "Just like we can tansform rasters by specifying a series of :class:`RasterTransformers <raster_transformer.raster_transformer.RasterTransformer>`, we can specify :class:`VectorTransformers <vector_transformer.vector_transformer.VectorTransformer>` to transform vector data."
+    "Just like we can transform rasters by specifying a series of :class:`RasterTransformers <raster_transformer.raster_transformer.RasterTransformer>`, we can specify :class:`VectorTransformers <vector_transformer.vector_transformer.VectorTransformer>` to transform vector data."
    ]
   },
   {

rastervision_core/rastervision/core/box.py

@@ -369,7 +369,7 @@ def get_windows(self,
         padding.
 
         Each of size, stride, and padding can be either a positive int or
-        a tuple `(vertical-componet, horizontal-component)` of positive ints.
+        a tuple `(vertical-component, horizontal-component)` of positive ints.
 
         Padding currently only applies to the right and bottom edges.
 
@@ -379,14 +379,14 @@ def get_windows(self,
             stride (Union[PosInt, Tuple[PosInt, PosInt]]): Step size between
                 windows. Can be 2-tuple (h_step, w_step) or positive int.
             padding (Optional[Union[PosInt, Tuple[PosInt, PosInt]]], optional):
-                Optional padding to accomodate windows that overflow the
+                Optional padding to accommodate windows that overflow the
                 extent. Can be 2-tuple (h_pad, w_pad) or non-negative int.
                 If None, will be set to (size[0]//2, size[1]//2).
                 Defaults to None.
             pad_direction (Literal['both', 'start', 'end']): If 'end', only pad
                 ymax and xmax (bottom and right). If 'start', only pad ymin and
                 xmin (top and left). If 'both', pad all sides. Has no effect if
-                paddiong is zero. Defaults to 'end'.
+                padding is zero. Defaults to 'end'.
 
         Returns:
             List[Box]: List of Box objects.

rastervision_core/rastervision/core/data/class_config.py

@@ -92,7 +92,7 @@ def ensure_null_class(self) -> None:
         null_class_name = DEFAULT_NULL_CLASS_NAME
         null_class_color = DEFAULT_NULL_CLASS_COLOR
 
-        # This might seeem redundant given the null class validator above, but
+        # This might seem redundant given the null class validator above, but
         # is actually important. Sometimes there can be multiple ClassConfig
         # instances that reference the same list objects for names and colors
         # (not clear why this happens). This means that

rastervision_core/rastervision/core/data/label/semantic_segmentation_labels.py

@@ -129,7 +129,7 @@ def transform_shape(x, y, z=None):
                 window_aoi = transform(transform_shape, window_aoi)
                 window_aois.append(window_aoi)
 
-        # If window does't overlap with any AOI, then it won't be in
+        # If window doesn't overlap with any AOI, then it won't be in
         # new_labels.
         if window_aois:
             # If window intersects with AOI, set pixels outside the

rastervision_core/rastervision/core/data/label/tfod_utils/np_box_list.py

@@ -113,7 +113,7 @@ def get_coordinates(
         return tuple(boxes.T)
 
     def _is_valid_boxes(self, data: np.ndarray) -> bool:
-        """Check whether data fullfills the format of N*[ymin, xmin, ymax, xmin].
+        """Check whether data fulfills the format of N*[ymin, xmin, ymax, xmin].
 
         Args:
             data (np.ndarray): Box coords as a [N, 4] numpy array.

rastervision_core/rastervision/core/data/label_source/object_detection_label_source.py

@@ -27,7 +27,7 @@ def __init__(self,
             bbox (Optional[Box], optional): User-specified crop of the extent.
                 If None, the full extent available in the source file is used.
             ioa_thresh (Optional[float], optional): IOA threshold to apply when
-                retieving labels for a window. Defaults to None.
+                retrieving labels for a window. Defaults to None.
             clip (bool, optional): Clip bounding boxes to window limits when
                 retrieving labels for a window. Defaults to False.
         """
@@ -52,7 +52,7 @@ def get_labels(self,
 
         Returns:
             ObjectDetectionLabels: Labels with sufficient overlap with the
-            window. The returned labels are in global coods (i.e. coords wihtin
+            window. The returned labels are in global coods (i.e. coords within
             the full extent of the source).
         """
         if window is None:

rastervision_core/rastervision/core/data/label_store/label_store.py

@@ -14,7 +14,7 @@ def save(self, labels):
         """Save.
 
         Args:
-           labels - Labels to be saved, the type of which will be dependant on the type
+           labels - Labels to be saved, the type of which will be dependent on the type
                     of pipeline.
         """
         pass

rastervision_core/rastervision/core/data/raster_source/rasterio_source.py

@@ -134,7 +134,7 @@ def crs_transformer(self) -> RasterioCRSTransformer:
         return self._crs_transformer
 
     def _set_info_from_chip(self):
-        """Read 1x1 chip to get info not statically inferrable."""
+        """Read 1x1 chip to get info not statically inferable."""
         test_chip = self.get_chip(Box(0, 0, 1, 1))
         self._dtype = test_chip.dtype
         self._num_channels = test_chip.shape[-1]
@@ -183,7 +183,7 @@ def get_chip(self,
                 channel_order (if specified). So if this is an RGB image and
                 channel_order=[2, 1, 0], then using bands=[0] will return the
                 B-channel. Defaults to None.
-            out_shape (Optional[Tuple[int, ...]], optional): (hieght, width) of
+            out_shape (Optional[Tuple[int, ...]], optional): (height, width) of
                 the output chip. If None, no resizing is done.
                 Defaults to None.
 

rastervision_core/rastervision/core/data/raster_source/xarray_source.py

@@ -121,7 +121,7 @@ def crs_transformer(self) -> RasterioCRSTransformer:
         return self._crs_transformer
 
     def _set_info_from_chip(self):
-        """Read 1x1 chip to get info not statically inferrable."""
+        """Read 1x1 chip to get info not statically inferable."""
         test_chip = self.get_chip(Box(0, 0, 1, 1))
         self._dtype = test_chip.dtype
         self._num_channels = test_chip.shape[-1]
@@ -168,7 +168,7 @@ def get_chip(self,
                 channel_order (if specified). So if this is an RGB image and
                 channel_order=[2, 1, 0], then using bands=[0] will return the
                 B-channel. Defaults to None.
-            out_shape (Optional[Tuple[int, ...]], optional): (hieght, width) of
+            out_shape (Optional[Tuple[int, ...]], optional): (height, width) of
                 the output chip. If None, no resizing is done.
                 Defaults to None.
 

rastervision_core/rastervision/core/data/utils/factory.py

@@ -41,7 +41,7 @@ def make_ss_scene(image_uri: Union[str, List[str]],
         label_vector_default_class_id (Optional[int], optional): If using
             label_vector_uri and all polygons in that file belong to the same
             class and they do not contain a `class_id` property, then use this
-            argument to map all of the polgons to the appropriate class ID.
+            argument to map all of the polygons to the appropriate class ID.
             See docs for ClassInferenceTransformer for more details.
             Defaults to None.
         image_raster_source_kw (dict, optional): Additional arguments to pass
@@ -152,7 +152,7 @@ def make_cc_scene(image_uri: Union[str, List[str]],
         label_vector_default_class_id (Optional[int], optional): If using
             label_vector_uri and all polygons in that file belong to the same
             class and they do not contain a `class_id` property, then use this
-            argument to map all of the polgons to the appropriate class ID.
+            argument to map all of the polygons to the appropriate class ID.
             See docs for ClassInferenceTransformer for more details.
             Defaults to None.
         image_raster_source_kw (dict, optional): Additional arguments to pass
@@ -243,7 +243,7 @@ def make_od_scene(image_uri: Union[str, List[str]],
         label_vector_default_class_id (Optional[int], optional): If using
             label_vector_uri and all polygons in that file belong to the same
             class and they do not contain a `class_id` property, then use this
-            argument to map all of the polgons to the appropriate class ID.
+            argument to map all of the polygons to the appropriate class ID.
             See docs for ClassInferenceTransformer for more details.
             Defaults to None.
         image_raster_source_kw (dict, optional): Additional arguments to pass

rastervision_core/rastervision/core/data/utils/geojson.py

@@ -118,9 +118,9 @@ def geoms_to_geojson(geoms: Iterable['BaseGeometry'],
 
 def geom_to_feature(geom: 'BaseGeometry',
                     properties: Optional[dict] = None) -> dict:
-    """Serialize a single shapely geomety to a GeoJSON Feature."""
-    geomety = mapping(geom)
-    feature = geometry_to_feature(geomety, properties=properties)
+    """Serialize a single shapely geometry to a GeoJSON Feature."""
+    geometry = mapping(geom)
+    feature = geometry_to_feature(geometry, properties=properties)
     return feature
 
 
@@ -251,7 +251,7 @@ def pixel_to_map_coords(geojson: dict,
 def simplify_polygons(geojson: dict) -> dict:
     """Simplify polygon geometries by applying ``.buffer(0)``.
 
-    For Polygon geomtries, ``.buffer(0)`` can do the following:
+    For Polygon geometries, ``.buffer(0)`` can do the following:
 
     1.  *Sometimes* break up a polygon with "bowties" into multiple polygons.
         (See https://github.com/shapely/shapely/issues/599.)

rastervision_core/rastervision/core/data/utils/raster.py

@@ -13,7 +13,7 @@ def fill_overflow(bbox: Box,
         bbox (Box): Bounding box.
         window (Box): Window corresponding to the ``chip``.
         chip (np.ndarray): (H, W, C) array.
-        fill_value (int, optional): Value to set oveflowing pixels to.
+        fill_value (int, optional): Value to set overflowing pixels to.
             Defaults to 0.
 
     Returns:

rastervision_core/rastervision/core/data/utils/rasterio.py

@@ -47,7 +47,7 @@ def write_bbox(path: str, arr: np.ndarray, bbox: Box, crs_wkt: str, **kwargs):
     Args:
         path (str): GeoTiff path.
         arr (np.ndarray): (H, W[, C]) Array to write.
-        bbox (Box): Bouding box in map coords to georeference the GeoTiff to.
+        bbox (Box): Bounding box in map coords to georeference the GeoTiff to.
         crs_wkt (str): CRS in WKT format.
     """
     if arr.ndim == 2:
@@ -182,7 +182,7 @@ def read_window(
             Defaults to None.
         is_masked (bool): If True, read a masked array from rasterio.
             Defaults to False.
-        out_shape (Optional[Tuple[int, int]]): (hieght, width) of the output
+        out_shape (Optional[Tuple[int, int]]): (height, width) of the output
             chip. If None, no resizing is done. Defaults to None.
 
     Returns:

rastervision_core/rastervision/core/data/utils/vectorization.py

@@ -23,7 +23,7 @@ def mask_to_polygons(mask: np.ndarray, transform: Optional[rio.Affine] = None
     Args:
         mask (np.ndarray): The mask containing buildings to polygonize.
         transform (Optional[rio.Affine]): Affine transform to use during
-            polygonization. Deafults to None (i.e. identity transform).
+            polygonization. Defaults to None (i.e. identity transform).
 
     Returns:
         Iterator[BaseGeometry]: Generator of shapely polygons.
@@ -61,7 +61,7 @@ def mask_to_building_polygons(
     Args:
         mask (np.ndarray): The mask containing buildings to polygonize.
         transform (Optional[rio.Affine]): Affine transform to use during
-            polygonization. Deafults to None (i.e. identity transform).
+            polygonization. Defaults to None (i.e. identity transform).
         min_area (float): Minimum area (in pixels^2) of anything that can be
             considered to be a building or cluster of buildings. The goal is to
             distinguish between buildings and artifacts. Components with area

rastervision_core/rastervision/core/evaluation/classification_evaluation.py

@@ -86,7 +86,7 @@ def merge(self,
         Args:
             other (ClassificationEvaluation): Evaluation to merge into this one
             scene_id (Optional[str], optional): ID of scene. If specified,
-                (a copy of) ``other`` will be saved and be availabel in
+                (a copy of) ``other`` will be saved and be available in
                 ``to_json()``'s output. Defaults to None.
         """
         if self.conf_mat is None:

rastervision_core/rastervision/core/evaluation/object_detection_evaluation.py

@@ -16,7 +16,7 @@ def compute_metrics(
         pred_labels: 'ObjectDetectionLabels',
         num_classes: int,
         iou_thresh: float = 0.5) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
-    """Compute per-class true positves, false positives, and false negatives.
+    """Compute per-class true positives, false positives, and false negatives.
 
     Does the following:
 

rastervision_core/rastervision/core/rv_pipeline/rv_pipeline.py

@@ -177,7 +177,7 @@ def predict(self, split_ind=0, num_splits=1):
 
         This uses a sliding window.
         """
-        # Cache backend so subsquent calls will be faster. This is useful for
+        # Cache backend so subsequent calls will be faster. This is useful for
         # the predictor.
         if self.backend is None:
             self.backend = self.config.backend.build(self.config, self.tmp_dir)

rastervision_core/rastervision/core/utils/stac.py

@@ -74,7 +74,7 @@ def parse_stac(stac_uri: str, item_limit: Optional[int] = None) -> List[dict]:
         stac_uri (str): Path to the STAC catalog JSON file.
 
     Returns:
-        List[dict]: A lsit of dicts with keys: "label_uri", "image_uris",
+        List[dict]: A list of dicts with keys: "label_uri", "image_uris",
         "label_bbox", "image_bbox", "bboxes_intersect", and "aoi_geometry".
         Each dict corresponds to one label item and its associated image
         assets in the STAC catalog.
@@ -145,7 +145,7 @@ def read_stac(uri: str, extract_dir: Optional[str] = None,
         Exception: If multiple catalog.json's are found inside the zip file.
 
     Returns:
-        List[dict]: A lsit of dicts with keys: "label_uri", "image_uris",
+        List[dict]: A list of dicts with keys: "label_uri", "image_uris",
         "label_bbox", "image_bbox", "bboxes_intersect", and "aoi_geometry".
         Each dict corresponds to one label item and its associated image
         assets in the STAC catalog.

rastervision_pipeline/rastervision/pipeline/version.py

@@ -1,2 +1,2 @@
-"""Library verison"""
+"""Library version"""
 __version__ = '0.21.4-dev'

rastervision_pytorch_backend/rastervision/pytorch_backend/examples/README.md

@@ -4,7 +4,7 @@ The `test.py` script provides some useful commands for running the examples and
 It supports the following commands:
 - `run` - run an example either remotely or locally
 - `compare` - compare the outputs of the `eval` stage of two runs of the same example
-- `collect` - dowload the output of one or more commands (like `train`, `eval`, `bundle`, etc.) produced by a run of an example
+- `collect` - download the output of one or more commands (like `train`, `eval`, `bundle`, etc.) produced by a run of an example
 - `predict` - download the model bundle produced by a run of an example and use it to make predictions on a sample image
 - `upload` - upload model bundle, eval, sample image, sample predictions, and training logs to the model zoo
 

rastervision_pytorch_backend/rastervision/pytorch_backend/examples/chip_classification/spacenet_rio_data_prep.ipynb

@@ -85,7 +85,7 @@
    "source": [
     "## Use the AOI to determine what images are inside the training set\n",
     "\n",
-    "Here we compare the AOI to the image extents to deteremine which images we can use for training and validation. We're using `rasterio`'s ability to read the metadata from raster data on S3 without downloading the whole image"
+    "Here we compare the AOI to the image extents to determine which images we can use for training and validation. We're using `rasterio`'s ability to read the metadata from raster data on S3 without downloading the whole image"
    ]
   },
   {

rastervision_pytorch_backend/rastervision/pytorch_backend/examples/test.py

@@ -147,7 +147,7 @@ def test():
 @click.option('--remote', is_flag=True, default=False)
 @click.option(
     '--commands',
-    help='Space-separated string with RV commansd to run.',
+    help='Space-separated string with RV command to run.',
     default=None)
 @click.option(
     '--overrides',

rastervision_pytorch_backend/rastervision/pytorch_backend/examples/tiny_spacenet.py

@@ -71,7 +71,7 @@ def make_scene(scene_id: str, image_uri: str, label_uri: str,
         ignore_crs_field=True,
         # The geoms in the label GeoJSON do not have a "class_id" property, so
         # classes must be inferred. Since all geoms are for the building class,
-        # this is easy to do: we just assing the building class ID to all of
+        # this is easy to do: we just assign the building class ID to all of
         # them.
         transformers=[
             ClassInferenceTransformerConfig(

rastervision_pytorch_learner/rastervision/pytorch_learner/dataset/classification_dataset.py

@@ -65,7 +65,7 @@ def make_cc_geodataset(cls,
         label_vector_default_class_id (Optional[int], optional): If using
             label_vector_uri and all polygons in that file belong to the same
             class and they do not contain a `class_id` property, then use this
-            argument to map all of the polgons to the appropriate class ID.
+            argument to map all of the polygons to the appropriate class ID.
             See docs for ClassInferenceTransformer for more details.
             Defaults to None.
         image_raster_source_kw (dict, optional): Additional arguments to pass

rastervision_pytorch_learner/rastervision/pytorch_learner/dataset/dataset.py

@@ -83,8 +83,8 @@ def __getitem__(self, key) -> Tuple[torch.Tensor, torch.Tensor]:
                 y = torch.from_numpy(y)
 
         if y is None:
-            # Ideally, y should be None to semantically convery the absence of
-            # any label, but PyTorch's defauult collate function doesn't handle
+            # Ideally, y should be None to semantically convey the absence of
+            # any label, but PyTorch's default collate function doesn't handle
             # None values.
             y = torch.tensor(np.nan)