Yolov7 instance segmentation

YOLOv7InstanceSegmentation

Bases: InstanceSegmentationBaseOnnxRoboflowInferenceModel

YOLOv7 Instance Segmentation ONNX Inference Model.

This class is responsible for performing instance segmentation using the YOLOv7 model with ONNX runtime.

Methods:

Name	Description
predict	Performs inference on the given image using the ONNX session.

Source code in inference/models/yolov7/yolov7_instance_segmentation.py

class YOLOv7InstanceSegmentation(InstanceSegmentationBaseOnnxRoboflowInferenceModel):
    """YOLOv7 Instance Segmentation ONNX Inference Model.

    This class is responsible for performing instance segmentation using the YOLOv7 model
    with ONNX runtime.

    Methods:
        predict: Performs inference on the given image using the ONNX session.
    """

    def predict(self, img_in: np.ndarray, **kwargs) -> Tuple[np.ndarray, np.ndarray]:
        """Performs inference on the given image using the ONNX session.

        Args:
            img_in (np.ndarray): Input image as a NumPy array.

        Returns:
            Tuple[np.ndarray, np.ndarray]: Tuple containing two NumPy arrays representing the predictions and protos.
        """
        with self._session_lock:
            predictions = run_session_via_iobinding(
                self.onnx_session, self.input_name, img_in
            )
        protos = predictions[4]
        predictions = predictions[0]
        return predictions, protos

predict(img_in, **kwargs)

Performs inference on the given image using the ONNX session.

Parameters:

Name	Type	Description	Default
img_in	ndarray	Input image as a NumPy array.	required

Returns:

Type	Description
Tuple[ndarray, ndarray]	Tuple[np.ndarray, np.ndarray]: Tuple containing two NumPy arrays representing the predictions and protos.

Source code in inference/models/yolov7/yolov7_instance_segmentation.py

def predict(self, img_in: np.ndarray, **kwargs) -> Tuple[np.ndarray, np.ndarray]:
    """Performs inference on the given image using the ONNX session.

    Args:
        img_in (np.ndarray): Input image as a NumPy array.

    Returns:
        Tuple[np.ndarray, np.ndarray]: Tuple containing two NumPy arrays representing the predictions and protos.
    """
    with self._session_lock:
        predictions = run_session_via_iobinding(
            self.onnx_session, self.input_name, img_in
        )
    protos = predictions[4]
    predictions = predictions[0]
    return predictions, protos