Class: Google::Cloud::AutoML::V1beta1::BoundingBoxMetricsEntry
- Inherits:
-
Object
- Object
- Google::Cloud::AutoML::V1beta1::BoundingBoxMetricsEntry
- Extended by:
- Protobuf::MessageExts::ClassMethods
- Includes:
- Protobuf::MessageExts
- Defined in:
- proto_docs/google/cloud/automl/v1beta1/detection.rb
Overview
Bounding box matching model metrics for a single intersection-over-union threshold and multiple label match confidence thresholds.
Defined Under Namespace
Classes: ConfidenceMetricsEntry
Instance Attribute Summary collapse
-
#confidence_metrics_entries ⇒ ::Array<::Google::Cloud::AutoML::V1beta1::BoundingBoxMetricsEntry::ConfidenceMetricsEntry>
Output only.
-
#iou_threshold ⇒ ::Float
Output only.
-
#mean_average_precision ⇒ ::Float
Output only.
Instance Attribute Details
#confidence_metrics_entries ⇒ ::Array<::Google::Cloud::AutoML::V1beta1::BoundingBoxMetricsEntry::ConfidenceMetricsEntry>
Returns Output only. Metrics for each label-match confidence_threshold from 0.05,0.10,...,0.95,0.96,0.97,0.98,0.99. Precision-recall curve is derived from them.
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
# File 'proto_docs/google/cloud/automl/v1beta1/detection.rb', line 81 class BoundingBoxMetricsEntry include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Metrics for a single confidence threshold. # @!attribute [rw] confidence_threshold # @return [::Float] # Output only. The confidence threshold value used to compute the metrics. # @!attribute [rw] recall # @return [::Float] # Output only. Recall under the given confidence threshold. # @!attribute [rw] precision # @return [::Float] # Output only. Precision under the given confidence threshold. # @!attribute [rw] f1_score # @return [::Float] # Output only. The harmonic mean of recall and precision. class ConfidenceMetricsEntry include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end |
#iou_threshold ⇒ ::Float
Returns Output only. The intersection-over-union threshold value used to compute this metrics entry.
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
# File 'proto_docs/google/cloud/automl/v1beta1/detection.rb', line 81 class BoundingBoxMetricsEntry include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Metrics for a single confidence threshold. # @!attribute [rw] confidence_threshold # @return [::Float] # Output only. The confidence threshold value used to compute the metrics. # @!attribute [rw] recall # @return [::Float] # Output only. Recall under the given confidence threshold. # @!attribute [rw] precision # @return [::Float] # Output only. Precision under the given confidence threshold. # @!attribute [rw] f1_score # @return [::Float] # Output only. The harmonic mean of recall and precision. class ConfidenceMetricsEntry include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end |
#mean_average_precision ⇒ ::Float
Returns Output only. The mean average precision, most often close to au_prc.
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
# File 'proto_docs/google/cloud/automl/v1beta1/detection.rb', line 81 class BoundingBoxMetricsEntry include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods # Metrics for a single confidence threshold. # @!attribute [rw] confidence_threshold # @return [::Float] # Output only. The confidence threshold value used to compute the metrics. # @!attribute [rw] recall # @return [::Float] # Output only. Recall under the given confidence threshold. # @!attribute [rw] precision # @return [::Float] # Output only. Precision under the given confidence threshold. # @!attribute [rw] f1_score # @return [::Float] # Output only. The harmonic mean of recall and precision. class ConfidenceMetricsEntry include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end end |