Class: Google::Cloud::VideoIntelligence::V1::LabelDetectionConfig
- Inherits:
-
Object
- Object
- Google::Cloud::VideoIntelligence::V1::LabelDetectionConfig
- Extended by:
- Protobuf::MessageExts::ClassMethods
- Includes:
- Protobuf::MessageExts
- Defined in:
- proto_docs/google/cloud/videointelligence/v1/video_intelligence.rb
Overview
Config for LABEL_DETECTION.
Instance Attribute Summary collapse
-
#frame_confidence_threshold ⇒ ::Float
The confidence threshold we perform filtering on the labels from frame-level detection.
-
#label_detection_mode ⇒ ::Google::Cloud::VideoIntelligence::V1::LabelDetectionMode
What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels.
-
#model ⇒ ::String
Model to use for label detection.
-
#stationary_camera ⇒ ::Boolean
Whether the video has been shot from a stationary (i.e., non-moving) camera.
-
#video_confidence_threshold ⇒ ::Float
The confidence threshold we perform filtering on the labels from video-level and shot-level detections.
Instance Attribute Details
#frame_confidence_threshold ⇒ ::Float
Returns 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.
136 137 138 139 |
# File 'proto_docs/google/cloud/videointelligence/v1/video_intelligence.rb', line 136 class LabelDetectionConfig include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#label_detection_mode ⇒ ::Google::Cloud::VideoIntelligence::V1::LabelDetectionMode
Returns What labels should be detected with LABEL_DETECTION, in addition to
video-level labels or segment-level labels.
If unspecified, defaults to SHOT_MODE
.
136 137 138 139 |
# File 'proto_docs/google/cloud/videointelligence/v1/video_intelligence.rb', line 136 class LabelDetectionConfig include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#model ⇒ ::String
Returns Model to use for label detection. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".
136 137 138 139 |
# File 'proto_docs/google/cloud/videointelligence/v1/video_intelligence.rb', line 136 class LabelDetectionConfig include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#stationary_camera ⇒ ::Boolean
Returns 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.
136 137 138 139 |
# File 'proto_docs/google/cloud/videointelligence/v1/video_intelligence.rb', line 136 class LabelDetectionConfig include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#video_confidence_threshold ⇒ ::Float
Returns 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.
136 137 138 139 |
# File 'proto_docs/google/cloud/videointelligence/v1/video_intelligence.rb', line 136 class LabelDetectionConfig include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |