ObjectDetectionTpFpFn#
- class ObjectDetectionTpFpFn[source]#
Calculate the TP, FP, FN and runs an evaluating function on the result.
- Parameters
- iou_thres: float, default: 0.5
Threshold of the IoU.
- confidence_thres: float, default: 0.5
Threshold of the confidence.
- evaluating_function: Union[Callable, str], default: “recall”
will run on each class result i.e func(tp, fp, fn)
- __init__(*args, iou_thres: float = 0.5, confidence_thres: float = 0.5, evaluating_function: Union[Callable, str] = 'recall', averaging_method='per_class', **kwargs)[source]#
- __new__(*args, **kwargs)#
Attributes
Methods
|
Attaches current metric to provided engine. |
Get a single result from group_class_detection_label and return a matrix of IoUs. |
|
|
Helper method to compute metric's value and put into the engine. |
Compute metric value. |
|
|
Detaches current metric from the engine and no metric's computation is done during the run. |
|
Get detections object of single image and should return confidence for each detection. |
Get detection object of single image and should return area for each detection. |
|
Get labels object of single image and should return area for each label. |
|
Group detection and labels in dict of format {class_id: {'detected' [...], 'ground_truth': [...] }}. |
|
|
Checks if current metric is attached to provided engine. |
Helper method to update metric's computation. |
|
|
Method replaces internal state of the class with provided state dict data. |
Reset metric state. |
|
|
Helper method to start data gathering for metric's computation. |
Method returns state dict with attributes of the metric specified in its _state_dict_all_req_keys attribute. |
|
|
Update metric with batch of samples. |