Class VideoActionRecognitionPredictionParams (0.4.0)

VideoActionRecognitionPredictionParams(
    mapping=None, *, ignore_unknown_fields=False, **kwargs
)

Prediction model parameters for Video Action Recognition.

Attributes

NameDescription
confidence_threshold float
The Model only returns predictions with at least this confidence score. Default value is 0.0
max_predictions int
The model only returns up to that many top, by confidence score, predictions per frame of the video. If this number is very high, the Model may return fewer predictions per frame. Default value is 50.

Inheritance

builtins.object > proto.message.Message > VideoActionRecognitionPredictionParams