Class Google::Cloud::AIPlatform::V1::Schema::Predict::Params::ImageSegmentationPredictionParams (v0.1.0)

Stay organized with collections Save and categorize content based on your preferences.

Prediction model parameters for Image Segmentation.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#confidence_threshold

def confidence_threshold() -> ::Float
Returns
  • (::Float) — When the model predicts category of pixels of the image, it will only provide predictions for pixels that it is at least this much confident about. All other pixels will be classified as background. Default value is 0.5.

#confidence_threshold=

def confidence_threshold=(value) -> ::Float
Parameter
  • value (::Float) — When the model predicts category of pixels of the image, it will only provide predictions for pixels that it is at least this much confident about. All other pixels will be classified as background. Default value is 0.5.
Returns
  • (::Float) — When the model predicts category of pixels of the image, it will only provide predictions for pixels that it is at least this much confident about. All other pixels will be classified as background. Default value is 0.5.