pyflink.multimodal.expression.ImageExpressionAccessor.detect_objects

ImageExpressionAccessor.detect_objects(*, model: str = 'yolov8n', confidence: float = 0.05, imgsz: int = 640, iou: float = 0.5, model_sharing: Optional[Literal['process', 'shared']] = None, concurrency: Optional[int] = None, batch_size: Optional[int] = None, num_gpus: Optional[float] = None, gpu_type: Optional[str] = None) → pyflink.table.expression.Expression

Detect objects in image values.

Equivalent to image_detect_objects(). See that function for full parameter details.

Parameters

• model – Object detection model name or path.

• confidence – Minimum detection confidence.

• imgsz – Inference image size.

• iou – IoU threshold used for non-maximum suppression.

• model_sharing – Optional model sharing mode.

• concurrency – Optional execution concurrency for this operation. None uses the framework default.

• batch_size – Optional inference batch size.

• num_gpus – Optional number of GPUs requested for model inference.

• gpu_type – Optional GPU type requested for model inference.

Returns

A DataFrame expression that produces ARRAY<ROW> object detections with label, x, y, w, h, and confidence fields.