fiftyone.utils.eval.openimages.OpenImagesDetectionResults

class documentation

class OpenImagesDetectionResults(DetectionResults): (source)

Class that stores the results of an Open Images detection evaluation.

Parameters
samples	the `fiftyone.core.collections.SampleCollection` used
config	the `OpenImagesEvaluationConfig` used
eval_key	the evaluation key
matches	a list of `(gt_label, pred_label, iou, pred_confidence, gt_id, pred_id)` matches. Either label can be `None` to indicate an unmatched object
precision	a dict of per-class precision values
recall	a dict of per-class recall values
classes	the list of possible classes
thresholds	an optional dict of per-class decision thresholds
missing	a missing label string. Any unmatched objects are given this label for evaluation purposes
custom_metrics	an optional dict of custom metrics
backend	a `OpenImagesEvaluation` backend

Method	`__init__`	Undocumented
Method	`mAP`	Computes Open Images-style mean average precision (mAP) for the specified classes.
Method	`plot_pr_curves`	Plots precision-recall (PR) curves for the detection results.
Instance Variable	`precision`	Undocumented
Instance Variable	`recall`	Undocumented
Instance Variable	`thresholds`	Undocumented
Class Method	`_from_dict`	Subclass implementation of `from_dict`.
Method	`_validate_classes`	Undocumented
Instance Variable	`_classwise_AP`	Undocumented

Inherited from DetectionResults:

Instance Variable ious Undocumented

Method	`confusion_matrix`	Generates a confusion matrix for the results via `sklearn:sklearn.metrics.confusion_matrix`.
Method	`metrics`	Computes classification metrics for the results, including accuracy, precision, recall, and F-beta score.
Method	`plot_confusion_matrix`	Plots a confusion matrix for the evaluation results.
Method	`print_metrics`	Prints the metrics computed via `metrics`.
Method	`print_report`	Prints a classification report for the results via `sklearn:sklearn.metrics.classification_report`.
Method	`report`	Generates a classification report for the results via `sklearn:sklearn.metrics.classification_report`.
Instance Variable	`confs`	Undocumented
Instance Variable	`weights`	Undocumented
Instance Variable	`ypred`	Undocumented
Instance Variable	`ypred_ids`	Undocumented
Instance Variable	`ytrue`	Undocumented
Instance Variable	`ytrue_ids`	Undocumented
Method	`_confusion_matrix`	Undocumented
Method	`_parse_classes`	Undocumented

Method	`add_custom_metrics`	Computes the given custom metrics and adds them to these results.
Method	`_get_custom_metrics`	Undocumented
Method	`_print_metrics`	Undocumented

Class Method	`from_dict`	Builds a `BaseRunResults` from a JSON dict representation of it.
Static Method	`base_results_cls`	Returns the results class for the given run type.
Method	`attributes`	Returns the list of class attributes that will be serialized by `serialize`.
Method	`save`	Saves the results to the database.
Method	`save_config`	Saves these results config to the database.
Property	`cls`	The fully-qualified name of this `BaseRunResults` class.
Property	`config`	The `BaseRunConfig` for these results.
Property	`key`	The run key for these results.
Property	`samples`	The `fiftyone.core.collections.SampleCollection` associated with these results.
Instance Variable	`_backend`	Undocumented
Instance Variable	`_config`	Undocumented
Instance Variable	`_key`	Undocumented
Instance Variable	`_samples`	Undocumented

def __init__(self, samples, config, eval_key, matches, precision, recall, classes, thresholds=None, missing=None, custom_metrics=None, backend=None): (source) ¶

overrides fiftyone.utils.eval.detection.DetectionResults.__init__

Undocumented

Computes Open Images-style mean average precision (mAP) for the specified classes.

See this page for more details about Open Images-style mAP.

Parameters
classes:`None`	a list of classes for which to compute mAP
Returns
the mAP in `[0, 1]`

def plot_pr_curves(self, classes=None, num_points=101, backend='plotly', **kwargs): (source) ¶

Plots precision-recall (PR) curves for the detection results.

Parameters
classes:`None`	a list of classes to generate curves for. By default, the top 3 AP classes will be plotted
num_points:101	the number of linearly spaced recall values to plot
backend:"plotly"	the plotting backend to use. Supported values are `("plotly", "matplotlib")`
**kwargs	keyword arguments for the backend plotting method: "plotly" backend: `fiftyone.core.plots.plotly.plot_pr_curves` "matplotlib" backend: `fiftyone.core.plots.matplotlib.plot_pr_curves`
Returns
`one` of the following	a `fiftyone.core.plots.plotly.PlotlyNotebookPlot`, if you are working in a notebook context and the plotly backend is used a plotly or matplotlib figure, otherwise

Undocumented

Undocumented

Undocumented

@classmethod
def _from_dict(cls, d, samples, config, eval_key, **kwargs): (source) ¶

overrides fiftyone.utils.eval.detection.DetectionResults._from_dict

Subclass implementation of from_dict.

Parameters
d	a JSON dict
samples	the `fiftyone.core.collections.SampleCollection` for the run
config	the `BaseRunConfig` for the run
eval_key	Undocumented
key	the run key
**kwargs	Undocumented
Returns
a `BaseRunResults`

def _validate_classes(self, classes): (source) ¶

Undocumented

Undocumented