Reference documentation and code samples for the AI Platform Data Labeling Service V1beta1 API class Google::Cloud::DataLabeling::V1beta1::PrCurve::ConfidenceMetricsEntry.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#confidence_threshold
def confidence_threshold() -> ::Float-
(::Float) — Threshold used for this entry.
For classification tasks, this is a classification threshold: a predicted label is categorized as positive or negative (in the context of this point on the PR curve) based on whether the label's score meets this threshold.
For image object detection (bounding box) tasks, this is the [intersection-over-union
(IOU)](/vision/automl/object-detection/docs/evaluate#intersection-over-union) threshold for the context of this point on the PR curve.
#confidence_threshold=
def confidence_threshold=(value) -> ::Float-
value (::Float) — Threshold used for this entry.
For classification tasks, this is a classification threshold: a predicted label is categorized as positive or negative (in the context of this point on the PR curve) based on whether the label's score meets this threshold.
For image object detection (bounding box) tasks, this is the [intersection-over-union
(IOU)](/vision/automl/object-detection/docs/evaluate#intersection-over-union) threshold for the context of this point on the PR curve.
-
(::Float) — Threshold used for this entry.
For classification tasks, this is a classification threshold: a predicted label is categorized as positive or negative (in the context of this point on the PR curve) based on whether the label's score meets this threshold.
For image object detection (bounding box) tasks, this is the [intersection-over-union
(IOU)](/vision/automl/object-detection/docs/evaluate#intersection-over-union) threshold for the context of this point on the PR curve.
#f1_score
def f1_score() -> ::Float- (::Float) — Harmonic mean of recall and precision.
#f1_score=
def f1_score=(value) -> ::Float- value (::Float) — Harmonic mean of recall and precision.
- (::Float) — Harmonic mean of recall and precision.
#f1_score_at1
def f1_score_at1() -> ::Float- (::Float) — The harmonic mean of recall_at1 and precision_at1.
#f1_score_at1=
def f1_score_at1=(value) -> ::Float- value (::Float) — The harmonic mean of recall_at1 and precision_at1.
- (::Float) — The harmonic mean of recall_at1 and precision_at1.
#f1_score_at5
def f1_score_at5() -> ::Float- (::Float) — The harmonic mean of recall_at5 and precision_at5.
#f1_score_at5=
def f1_score_at5=(value) -> ::Float- value (::Float) — The harmonic mean of recall_at5 and precision_at5.
- (::Float) — The harmonic mean of recall_at5 and precision_at5.
#precision
def precision() -> ::Float- (::Float) — Precision value.
#precision=
def precision=(value) -> ::Float- value (::Float) — Precision value.
- (::Float) — Precision value.
#precision_at1
def precision_at1() -> ::Float- (::Float) — Precision value for entries with label that has highest score.
#precision_at1=
def precision_at1=(value) -> ::Float- value (::Float) — Precision value for entries with label that has highest score.
- (::Float) — Precision value for entries with label that has highest score.
#precision_at5
def precision_at5() -> ::Float- (::Float) — Precision value for entries with label that has highest 5 scores.
#precision_at5=
def precision_at5=(value) -> ::Float- value (::Float) — Precision value for entries with label that has highest 5 scores.
- (::Float) — Precision value for entries with label that has highest 5 scores.
#recall
def recall() -> ::Float- (::Float) — Recall value.
#recall=
def recall=(value) -> ::Float- value (::Float) — Recall value.
- (::Float) — Recall value.
#recall_at1
def recall_at1() -> ::Float- (::Float) — Recall value for entries with label that has highest score.
#recall_at1=
def recall_at1=(value) -> ::Float- value (::Float) — Recall value for entries with label that has highest score.
- (::Float) — Recall value for entries with label that has highest score.
#recall_at5
def recall_at5() -> ::Float- (::Float) — Recall value for entries with label that has highest 5 scores.
#recall_at5=
def recall_at5=(value) -> ::Float- value (::Float) — Recall value for entries with label that has highest 5 scores.
- (::Float) — Recall value for entries with label that has highest 5 scores.