Skip to content

onnx

onnx

Attributes

__all__ module-attribute 

__all__ = ['YOLOSegmentationMixin', 'YOLOv5SegmentationPipeline']

Classes

YOLOSegmentationMixin

Bases: YOLODetectionMixin

Shared YOLOv5 segmentation logic (ONNX version).

YOLOv5SegmentationPipeline 

YOLOv5SegmentationPipeline(runtime: ONNXRuntime, image_size: tuple[int, int] = (640, 640), stride: int = 32, conf_threshold: float = 0.25, iou_threshold: float = 0.45, class_names: dict[int, str] | None = None, batch_strategy: BatchStrategy[ndarray, tuple[ndarray, ndarray]] | None = None)

Bases: YOLOSegmentationMixin, Pipeline[ndarray, tuple[ndarray, ndarray], list[SegmentationOutput]]

YOLOv5 instance segmentation pipeline (ONNX version).

Source code in inferflow/pipeline/segmentation/onnx.py 
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
def __init__(
    self,
    runtime: ONNXRuntime,
    image_size: tuple[int, int] = (640, 640),
    stride: int = 32,
    conf_threshold: float = 0.25,
    iou_threshold: float = 0.45,
    class_names: dict[int, str] | None = None,
    batch_strategy: BatchStrategy[np.ndarray, tuple[np.ndarray, np.ndarray]] | None = None,
):
    super().__init__(runtime=runtime, batch_strategy=batch_strategy)

    self.image_size = image_size
    self.stride = stride
    self.conf_threshold = conf_threshold
    self.iou_threshold = iou_threshold
    self.class_names = class_names or {}

    self._runtime = runtime

    self._original_size = None
    self._padding = None
Attributes
image_size instance-attribute 
image_size = image_size
stride instance-attribute 
stride = stride
conf_threshold instance-attribute 
conf_threshold = conf_threshold
iou_threshold instance-attribute 
iou_threshold = iou_threshold
class_names instance-attribute 
class_names = class_names or {}
Functions
preprocess 
preprocess(input: ImageInput) -> ndarray

Preprocess image for YOLOv5-Seg.

Source code in inferflow/pipeline/segmentation/onnx.py 
116
117
118
119
def preprocess(self, input: ImageInput) -> np.ndarray:
    """Preprocess image for YOLOv5-Seg."""
    image = self._convert_to_numpy(input)
    return self._preprocess_numpy(image)
postprocess 
postprocess(raw: tuple[ndarray, ndarray]) -> list[SegmentationOutput]

Postprocess YOLOv5-Seg output.

Source code in inferflow/pipeline/segmentation/onnx.py 
121
122
123
124
def postprocess(self, raw: tuple[np.ndarray, np.ndarray]) -> list[SegmentationOutput]:
    """Postprocess YOLOv5-Seg output."""
    detections, protos = raw
    return self._postprocess_segmentation(detections, protos)

Functions