Class: Google::Apis::VideointelligenceV1p1beta1::GoogleCloudVideointelligenceV1p1beta1LabelDetectionConfig

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
generated/google/apis/videointelligence_v1p1beta1/classes.rb,
generated/google/apis/videointelligence_v1p1beta1/representations.rb,
generated/google/apis/videointelligence_v1p1beta1/representations.rb

Overview

Config for LABEL_DETECTION.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudVideointelligenceV1p1beta1LabelDetectionConfig

Returns a new instance of GoogleCloudVideointelligenceV1p1beta1LabelDetectionConfig.



2825
2826
2827
 
# File 'generated/google/apis/videointelligence_v1p1beta1/classes.rb', line 2825

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#frame_confidence_threshold ⇒ Float

The confidence threshold we perform filtering on the labels from frame-level detection. If not set, it is set to 0.4 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model. Corresponds to the JSON property frameConfidenceThreshold

Returns:

  • (Float) 


2794
2795
2796
 
# File 'generated/google/apis/videointelligence_v1p1beta1/classes.rb', line 2794

def frame_confidence_threshold
  @frame_confidence_threshold
end

#label_detection_mode ⇒ String

What labels should be detected with LABEL_DETECTION, in addition to video- level labels or segment-level labels. If unspecified, defaults to SHOT_MODE. Corresponds to the JSON property labelDetectionMode

Returns:

  • (String) 


2800
2801
2802
 
# File 'generated/google/apis/videointelligence_v1p1beta1/classes.rb', line 2800

def label_detection_mode
  @label_detection_mode
end

#model ⇒ String

Model to use for label detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest". Corresponds to the JSON property model

Returns:

  • (String) 


2806
2807
2808
 
# File 'generated/google/apis/videointelligence_v1p1beta1/classes.rb', line 2806

def model
  @model
end

#stationary_camera ⇒ Boolean Also known as: stationary_camera?

Whether the video has been shot from a stationary (i.e., non-moving) camera. When set to true, might improve detection accuracy for moving objects. Should be used with SHOT_AND_FRAME_MODE enabled. Corresponds to the JSON property stationaryCamera

Returns:

  • (Boolean) 


2813
2814
2815
 
# File 'generated/google/apis/videointelligence_v1p1beta1/classes.rb', line 2813

def stationary_camera
  @stationary_camera
end

#video_confidence_threshold ⇒ Float

The confidence threshold we perform filtering on the labels from video-level and shot-level detections. If not set, it's set to 0.3 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model. Corresponds to the JSON property videoConfidenceThreshold

Returns:

  • (Float) 


2823
2824
2825
 
# File 'generated/google/apis/videointelligence_v1p1beta1/classes.rb', line 2823

def video_confidence_threshold
  @video_confidence_threshold
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



2830
2831
2832
2833
2834
2835
2836
 
# File 'generated/google/apis/videointelligence_v1p1beta1/classes.rb', line 2830

def update!(**args)
  @frame_confidence_threshold = args[:frame_confidence_threshold] if args.key?(:frame_confidence_threshold)
  @label_detection_mode = args[:label_detection_mode] if args.key?(:label_detection_mode)
  @model = args[:model] if args.key?(:model)
  @stationary_camera = args[:stationary_camera] if args.key?(:stationary_camera)
  @video_confidence_threshold = args[:video_confidence_threshold] if args.key?(:video_confidence_threshold)
end