= R"pydeepstream(
Holds information of object metadata in the frame.
:ivar class_id: *int*, Index of the object class infered by the primary detector/classifier
:ivar object_id: *int*, Unique ID for tracking the object.
:ivar unique_component_id: *int*, Unique id of the component that generates the object metadata.
:ivar confidence: *float*, Holds a confidence value for the object, set by the inference component.
Confidence will be set to -0.1, if "Group Rectangles" mode of clustering is chosen since the algorithm does not preserve confidence values.
Also, for objects found by tracker and not inference component, confidence will be set to -0.1
:ivar tracker_confidence: *float*, Holds a confidence value for the object, set by the tracker component.
:ivar rect_params: :class:`NvOSD_RectParams`, Structure containing the positional parameters of the object in the frame.
Can also be used to overlay borders / semi-transparent boxes on top of objects. See :class:`NvOSD_RectParams`
:ivar mask_params: :class:`NvOSD_MaskParams`, Mask parameters for the object. This mask is overlaid over the object See :class:`NvOSD_MaskParams`
:ivar text_params: :class:`NvOSD_TextParams`, Text for describing the object. See :class:`NvOSD_TextParams`
:ivar label: *str*, Label describing the class of the detected object.
:ivar classifier_items: *iterator* Iterator over items of type :class:`ClassifierMetadata` in use in the current object.
:ivar tensor_items: *iterator* Iterator over items of type :class:`UserMetadata` in use in the current object as items of type :class:`TensorOutputUserMetadata`
Each item *user_meta* can be called as :class:`TensorOutputUserMetadata` by calling *user_meta.as_tensor_output()*.
:ivar obj_reid_items: *iterator* Iterator over ReID user metadata items of type :class:`UserMetadata`.
Each item *user_meta* can be cast to :class:`ObjectReidUserMetadata` by calling *user_meta.as_obj_reid()*.)pydeepstream"