fiftyone.utils.iou

module documentation

(source)

Intersection over union (IoU) utilities.

Function	`compute_bbox_iou`	Computes the IoU between the given ground truth and predicted detections.
Function	`compute_ious`	Computes the pairwise IoUs between the predicted and ground truth objects.
Function	`compute_max_ious`	Populates an attribute on each label in the given spatial field(s) that records the max IoU between the object and another object in the same sample/frame.
Function	`compute_segment_ious`	Computes the pairwise IoUs between the predicted and ground truth temporal detections.
Function	`find_duplicates`	Returns IDs of duplicate labels in the given field of the collection, as defined as labels with an IoU greater than a chosen threshold with another label in the field.
Variable	`sg`	Undocumented
Variable	`so`	Undocumented
Function	`_compute_bbox_ious`	Undocumented
Function	`_compute_keypoint_similarities`	Undocumented
Function	`_compute_mask_ious`	Undocumented
Function	`_compute_max_ious`	Undocumented
Function	`_compute_object_keypoint_similarity`	Undocumented
Function	`_compute_polygon_ious`	Undocumented
Function	`_compute_polyline_similarities`	Undocumented
Function	`_compute_segment_ious`	Undocumented
Function	`_extract_max_ious`	Undocumented
Function	`_find_duplicates`	Undocumented
Function	`_find_duplicates_greedy`	Undocumented
Function	`_find_duplicates_simple`	Undocumented
Function	`_get_bbox_dim`	Undocumented
Function	`_get_detection_box`	Undocumented
Function	`_get_labels`	Undocumented
Function	`_get_poly_box`	Undocumented
Function	`_masks_to_polylines`	Undocumented
Function	`_polylines_to_detections`	Undocumented
Function	`_polylines_to_shapely`	Undocumented

def compute_bbox_iou(gt, pred, gt_crowd=False): (source) ¶

Computes the IoU between the given ground truth and predicted detections.

Parameters
gt	a `fiftyone.core.labels.Detection`
pred	a `fiftyone.core.labels.Detection`
gt_crowd:`False`	whether the ground truth object is a crowd
Returns
the IoU, in `[0, 1]`

def compute_ious(preds, gts, iscrowd=None, classwise=False, use_masks=False, use_boxes=False, tolerance=None, sparse=False, error_level=1): (source) ¶

Computes the pairwise IoUs between the predicted and ground truth objects.

For polylines, IoUs are computed as solid shapes when filled=True` and "IoUs" are computed using `object keypoint similarity <https://cocodataset.org/#keypoints-eval>`_ when ``filled=False.

For keypoints, "IoUs" are computed via object keypoint similarity.

Parameters
preds	a list of predicted `fiftyone.core.labels.Detection`, `fiftyone.core.labels.Polyline`, or `fiftyone.core.labels.Keypoints` instances
gts	a list of ground truth `fiftyone.core.labels.Detection`, `fiftyone.core.labels.Polyline`, or `fiftyone.core.labels.Keypoints` instances
iscrowd:`None`	an optional name of a boolean attribute or boolean function to apply to each label that determines whether a ground truth object is a crowd. If provided, the area of the predicted object is used as the "union" area for IoU calculations involving crowd objects
classwise:`False`	whether to consider objects with different `label` values as always non-overlapping (True) or to compute IoUs for all objects regardless of label (False)
use_masks:`False`	whether to compute IoUs using the instances masks in the `mask` attribute of the provided objects, which must be `fiftyone.core.labels.Detection` instances
use_boxes:`False`	whether to compute IoUs using the bounding boxes of the provided `fiftyone.core.labels.Polyline` instances rather than using their actual geometries
tolerance:`None`	a tolerance, in pixels, when generating approximate polylines for instance masks. Typical values are 1-3 pixels
sparse:`False`	whether to return a sparse dict of non-zero IoUs rather than a full matrix
error_level:1	the error level to use when manipulating instance masks or polylines. Valid values are: 0: raise geometric errors that are encountered 1: log warnings if geometric errors are encountered 2: ignore geometric errors If `error_level > 0`, any calculation that raises a geometric error will default to an IoU of 0
Returns
a `num_preds x num_gts` array of IoUs when `sparse=False`, or a dict of the form `d[pred.id] = [(gt.id, iou), ...]` when `sparse=True`

def compute_max_ious(sample_collection, label_field, other_field=None, iou_attr='max_iou', id_attr=None, progress=None, **kwargs): (source) ¶

Populates an attribute on each label in the given spatial field(s) that records the max IoU between the object and another object in the same sample/frame.

If other_field is provided, IoUs are computed between objects in label_field and other_field.

If no other_field is provided, IoUs are computed between objects in label_field alone, excluding the object itself.

Parameters
sample_collection	a `fiftyone.core.collections.SampleCollection`
label_field	a label field of type `fiftyone.core.labels.Detections`, `fiftyone.core.labels.Polylines`, or `fiftyone.core.labels.Keypoints`
other_field:`None`	another label field of type `fiftyone.core.labels.Detections`, `fiftyone.core.labels.Polylines`, or `fiftyone.core.labels.Keypoints`
iou_attr:"max_iou"	the label attribute in which to store the max IoU
id_attr:`None`	an optional attribute in which to store the label ID of the maximum overlapping label
progress:`None`	whether to render a progress bar (True/False), use the default value `fiftyone.config.show_progress_bars` (None), or a progress callback function to invoke instead
**kwargs	optional keyword arguments for `compute_ious`

def compute_segment_ious(preds, gts, sparse=False): (source) ¶

Computes the pairwise IoUs between the predicted and ground truth temporal detections.

Parameters
preds	a list of predicted `fiftyone.core.labels.TemporalDetection` instances
gts	a list of ground truth `fiftyone.core.labels.TemporalDetection` instances
sparse:`False`	whether to return a sparse dict of non-zero IoUs rather than a full matrix
Returns
a `num_preds x num_gts` array of segment IoUs when `sparse=False`, or a dict of the form `d[pred.id] = [(gt.id, iou), ...]` when `sparse=True`

def find_duplicates(sample_collection, label_field, iou_thresh=0.999, method='simple', progress=None, **kwargs): (source) ¶

Returns IDs of duplicate labels in the given field of the collection, as defined as labels with an IoU greater than a chosen threshold with another label in the field.

The following duplicate removal methods are supported:

method="simple": mark the latter label in every pair of labels whose IoU exceeds the threshold. This may remove more labels than the greedy method
method="greedy": apply a greedy method to mark the fewest number of labels as duplicate such that no non-duplicate labels have IoU greater than the specified threshold. This method is more computationally expensive than the simple method

Parameters
sample_collection	a `fiftyone.core.collections.SampleCollection`
label_field	a label field of type `fiftyone.core.labels.Detections`, `fiftyone.core.labels.Polylines`, or `fiftyone.core.labels.Keypoints`
iou_thresh:0.999	the IoU threshold to use to determine whether labels are duplicates
method:"simple"	the duplicate removal method to use. The supported values are `("simple", "greedy")`
progress:`None`	whether to render a progress bar (True/False), use the default value `fiftyone.config.show_progress_bars` (None), or a progress callback function to invoke instead
**kwargs	optional keyword arguments for `compute_ious`
Returns
a list of IDs of duplicate labels

sg = (source) ¶

Undocumented

so = (source) ¶

Undocumented

def _compute_bbox_ious(preds, gts, iscrowd=None, classwise=False, sparse=False): (source) ¶

Undocumented

def _compute_keypoint_similarities(preds, gts, classwise=False, sparse=False): (source) ¶

Undocumented

def _compute_mask_ious(preds, gts, tolerance, error_level, iscrowd=None, classwise=False, sparse=False): (source) ¶

Undocumented

def _compute_max_ious(doc, field1, field2, **kwargs): (source) ¶

Undocumented

def _compute_object_keypoint_similarity(gtp, predp): (source) ¶

Undocumented

def _compute_polygon_ious(preds, gts, error_level, iscrowd=None, classwise=False, gt_crowds=None, sparse=False): (source) ¶

Undocumented

def _compute_polyline_similarities(preds, gts, classwise=False, sparse=False): (source) ¶

Undocumented

def _compute_segment_ious(preds, gts, sparse=False): (source) ¶

Undocumented

def _extract_max_ious(ious, labels1, labels2): (source) ¶

Undocumented

def _find_duplicates(doc, field, iou_thresh, method, **kwargs): (source) ¶

Undocumented

def _find_duplicates_greedy(ious, iou_thresh): (source) ¶

Undocumented

def _find_duplicates_simple(ious, iou_thresh): (source) ¶

Undocumented

def _get_bbox_dim(detection): (source) ¶

Undocumented

def _get_detection_box(det, dimension=None): (source) ¶

Undocumented

def _get_labels(doc, field): (source) ¶

Undocumented

def _get_poly_box(x): (source) ¶

Undocumented

def _masks_to_polylines(detections, tolerance, error_level): (source) ¶

Undocumented

def _polylines_to_detections(polylines): (source) ¶

Undocumented

def _polylines_to_shapely(polylines, error_level): (source) ¶

Undocumented