View source on GitHub
Arize class to map up to 3 columns (bounding_boxes_coordinates_column_name, categories_column_name, and scores_column_name) to a single object detection prediction or actual column.
class ObjectDetectionColumnNames(
bounding_boxes_coordinates_column_name: str
categories_column_name: str
scores_column_name: Optional[str] = None
)
| Parameters | Data Type | Expected Type In Column | Description |
|---|---|---|---|
bounding_boxes_coordinates_column_name | str | The contents of this column must be List[List[float]] | (Required) Column name containing the coordinates of the rectangular outline that locates an object within an image or video. Pascal VOC format required. |
categories_column_name | str | The contents of this column must be List[str] | (Required) Column name containing the predefined classes or labels used by the model to classify the detected objects. |
scores_column_name | str | The contents of this column must be List[float] | (Optional*) Column name containing the confidence scores that the model assigns to its predictions, indicating how certain the model is that the predicted class is contained within the bounding box. * This parameter is not applicable to actual (ground truth) labels and is only applicable when defining object_detection_prediction_column_names |
Code Example
| Index | prediction_bboxes | actual_bboxes | prediction_categories | actual_categories | prediction_scores |
|---|---|---|---|---|---|
0 | [[50.43, 109.49, 538.21... | [[55.39, 107.72, 539.25, 362.9], [554.41, 194.... | [bus] | [bus, person, person] | [0.9997552] |
object_detection_prediction_column_names = ObjectDetectionColumnNames(
(bounding_boxes_coordinates_column_name = "prediction_bboxes"),
(categories_column_name = "prediction_categories"),
(scores_column_name = "prediction_scores")
);
object_detection_actual_column_names = ObjectDetectionColumnNames(
(bounding_boxes_coordinates_column_name = "actual_bboxes"),
(categories_column_name = "actual_categories")
);