ObjectDetectionLabels#

class ObjectDetectionLabels[source]#

Bases: Labels

A set of boxes and associated class_ids and scores.

Implemented using the Tensorflow Object Detection API’s BoxList class.

__init__(npboxes: ndarray, class_ids: ndarray, scores: ndarray = None)[source]#

Construct a set of object detection labels.

Parameters

npboxes (ndarray) – float numpy array of size nx4 with cols ymin, xmin, ymax, xmax. Should be in pixel coordinates within the global frame of reference.
class_ids (ndarray) – int numpy array of size n with class ids
scores (ndarray) – float numpy array of size n

Methods

`__init__`(npboxes, class_ids[, scores])	Construct a set of object detection labels.
`assert_equal`(expected_labels)
`concatenate`(labels1, labels2)	Return concatenation of labels.
`filter_by_aoi`(aoi_polygons)	Return a copy of these labels filtered by given AOI polygons.
`from_boxlist`(boxlist)	Make ObjectDetectionLabels from BoxList object.
`from_geojson`(geojson[, bbox, ioa_thresh, clip])	Convert GeoJSON to ObjectDetectionLabels object.
`from_predictions`(windows, predictions)	Instantiate from windows and their corresponding predictions.
`get_boxes`()	Return list of Boxes.
`get_class_ids`()
`get_npboxes`()
`get_overlapping`(labels, window[, ...])	Return subset of labels that overlap with window.
`get_scores`()
`global_to_local`(npboxes, window)	Convert from global to local coordinates.
`local_to_global`(npboxes, window)	Convert from local to global coordinates.
`local_to_normalized`(npboxes, window)	Convert from local to normalized coordinates.
`make_empty`()	Instantiate an empty instance of this class.
`normalized_to_local`(npboxes, window)	Convert from normalized to local coordinates.
`prune_duplicates`(labels, score_thresh, ...)	Remove duplicate boxes via non-maximum suppression.
`save`(uri, class_config, crs_transformer[, bbox])	Save labels as a GeoJSON file.
`to_boxlist`()
`to_dict`([round_boxes])	Returns a dict version of these labels.

__add__(other: Self) → Self[source]#

Add labels to these labels.

Returns a concatenation of this and the other labels.

Parameters: other (Self) –
Return type: Self

__getitem__(window: Box) → Self[source]#

Parameters: window (Box) –
Return type: Self

__init__(npboxes: ndarray, class_ids: ndarray, scores: ndarray = None)[source]#

Construct a set of object detection labels.

Parameters

npboxes (ndarray) – float numpy array of size nx4 with cols ymin, xmin, ymax, xmax. Should be in pixel coordinates within the global frame of reference.
class_ids (ndarray) – int numpy array of size n with class ids
scores (ndarray) – float numpy array of size n

__setitem__(window: Box, item: dict[str, numpy.ndarray])[source]#

Parameters

window (Box) –
item (dict[str, numpy.ndarray]) –

assert_equal(expected_labels: Self)[source]#

Parameters: expected_labels (Self) –

static concatenate(labels1: Self, labels2: Self) → Self[source]#

Return concatenation of labels.

Parameters

labels1 (Self) –
labels2 (Self) –

Return type

Self

filter_by_aoi(aoi_polygons: Iterable[Polygon])[source]#

Return a copy of these labels filtered by given AOI polygons.

Parameters: aoi_polygons (Iterable[Polygon]) – List of AOI polygons to filter by, in pixel coordinates.

static from_boxlist(boxlist: NpBoxList)[source]#

Make ObjectDetectionLabels from BoxList object.

Parameters: boxlist (NpBoxList) –

static from_geojson(geojson: dict, bbox: rastervision.core.box.Box | None = None, ioa_thresh: float = 0.8, clip: bool = True) → Self[source]#

Convert GeoJSON to ObjectDetectionLabels object.

If bbox is provided, filter out the boxes that lie “more than a little bit” outside the bbox.

Parameters

geojson (dict) – normalized GeoJSON (see VectorSource)
bbox (rastervision.core.box.Box | None) – in pixel coords
ioa_thresh (float) –
clip (bool) –

Returns

ObjectDetectionLabels

Return type

Self

classmethod from_predictions(windows: Iterable[Box], predictions: Iterable[Any]) → Self#

Instantiate from windows and their corresponding predictions.

This makes no assumptions about the type or format of the predictions. Subclasses should implement the __setitem__ method to correctly handle the predictions.

Parameters

windows (Iterable[Box]) – Boxes in pixel coords, specifying chips in the raster.
predictions (Iterable[Any]) – The model predictions for each chip specified by the windows.

Returns

An object of the Label subclass on which this method is called.

Return type

Labels

get_boxes() → list[rastervision.core.box.Box][source]#

Return list of Boxes.

Return type: list[rastervision.core.box.Box]

get_class_ids() → ndarray[source]#

Return type: ndarray

get_npboxes() → ndarray[source]#

Return type: ndarray

static get_overlapping(labels: Self, window: Box, ioa_thresh: float = 0.5, clip: bool = False) → Self[source]#

Return subset of labels that overlap with window.

Parameters

labels (Self) – Labels
window (Box) – Window
ioa_thresh (float) – The minimum intersection-over-area (IOA) for a box to be considered as overlapping. For each box, IOA is defined as the area of the intersection of the box with the window over the area of the box.
clip (bool) – If True, clip label boxes to the window.

Return type

Self

get_scores() → ndarray[source]#

Return type: ndarray

static global_to_local(npboxes: ndarray, window: Box)[source]#

Convert from global to local coordinates.

The global coordinates are row/col within the extent of a RasterSource. The local coordinates are row/col within the window frame of reference.

Parameters

npboxes (ndarray) –
window (Box) –

static local_to_global(npboxes: ndarray, window: Box)[source]#

Convert from local to global coordinates.

The local coordinates are row/col within the window frame of reference. The global coordinates are row/col within the extent of a RasterSource.

Parameters

npboxes (ndarray) –
window (Box) –

static local_to_normalized(npboxes: ndarray, window: Box)[source]#

Convert from local to normalized coordinates.

The local coordinates are row/col within the window frame of reference. Normalized coordinates range from 0 to 1 on each (height/width) axis.

Parameters

npboxes (ndarray) –
window (Box) –

classmethod make_empty() → Self[source]#

Instantiate an empty instance of this class.

Returns: An object of the Label subclass on which this method is called.
Return type: Labels

static normalized_to_local(npboxes: ndarray, window: Box)[source]#

Convert from normalized to local coordinates.

Normalized coordinates range from 0 to 1 on each (height/width) axis. The local coordinates are row/col within the window frame of reference.

Parameters

npboxes (ndarray) –
window (Box) –

static prune_duplicates(labels: Self, score_thresh: float, merge_thresh: float, max_output_size: int | None = None) → Self[source]#

Remove duplicate boxes via non-maximum suppression.

Parameters

labels (Self) – Labels whose boxes are to be pruned.
score_thresh (float) – Prune boxes with score less than this threshold.
merge_thresh (float) – Prune boxes with intersection-over-union (IOU) greater than this threshold.
max_output_size (int | None) – Maximum number of retained boxes. If None, this is set to len(abels). Defaults to None.

Returns

Pruned labels.

Return type

ObjectDetectionLabels

save(uri: str, class_config: ClassConfig, crs_transformer: CRSTransformer, bbox: rastervision.core.box.Box | None = None) → None[source]#

Save labels as a GeoJSON file.

Parameters

uri (str) – URI of the output file.
class_config (ClassConfig) – ClassConfig to map class IDs to names.
crs_transformer (CRSTransformer) – CRSTransformer to convert from pixel-coords to map-coords before saving.
bbox (rastervision.core.box.Box | None) – User-specified crop of the extent. Must be provided if the corresponding RasterSource has bbox != extent.

Return type

None

to_boxlist() → NpBoxList[source]#

Return type: NpBoxList

to_dict(round_boxes: bool = True) → dict[source]#

Returns a dict version of these labels.

The Dict has a Box as a key, and a tuple of (class_id, score) as the values.

Parameters: round_boxes (bool) –
Return type: dict