VisionInference QML Type

Runs AI inference on incoming video frames. More...

• List of all members, including inherited members

Properties

• labels : string
• mode : string
• model : string
• module : string
• name : string

Detailed Description

VisionInference is an InferenceStep that runs a vision model, such as a classifier or detector, on the frames it receives and produces structured results. Place it after an InferenceVideoSource in an InferenceFlow, and connect its output to an InferenceResultParser to interpret the results.

Configure the step with the model to run and the labels that name the model's output classes. The name property selects a named backend variant, and module and mode are passed to the backend as options. When the QML component completes, the step creates the underlying C++ QVisionInference with these values.

See also InferenceStep, InferenceVideoSource, and InferenceResultParser.

Property Documentation

labels : string

This property holds the path to the file that names the model's output classes.

The default value is an empty string.

See also model.

mode : string

This property holds the inference mode used by the backend.

The default value is an empty string.

See also module.

model : string

This property holds the model that the step runs, given as a file path or identifier.

The default value is an empty string.

See also labels.

module : string

This property holds the backend module that runs the inference.

The default value is an empty string.

See also mode.

name : string

This property holds the name of the inference step.

When a backend provider is registered under this name, the factory prefers it when creating the underlying step.

The default value is an empty string.