跳至内容

参考资料 ultralytics/utils/ops.py

备注

该文件可在https://github.com/ultralytics/ultralytics/blob/main/ ultralytics/utils/ops .py。如果您发现问题,请通过提交 Pull Request🛠️ 帮助修复。谢谢🙏!



ultralytics.utils.ops.Profile

垒球 ContextDecorator

YOLOv8 Profile 类。使用 @Profile() 作为装饰器,或使用 "with Profile(): "作为上下文管理器。

示例
from ultralytics.utils.ops import Profile

with Profile(device=device) as dt:
    pass  # slow operation here

print(dt)  # prints "Elapsed time is 9.5367431640625e-07 s"
源代码 ultralytics/utils/ops.py
class Profile(contextlib.ContextDecorator):
    """
    YOLOv8 Profile class. Use as a decorator with @Profile() or as a context manager with 'with Profile():'.

    Example:
        ```python
        from ultralytics.utils.ops import Profile

        with Profile(device=device) as dt:
            pass  # slow operation here

        print(dt)  # prints "Elapsed time is 9.5367431640625e-07 s"
        ```
    """

    def __init__(self, t=0.0, device: torch.device = None):
        """
        Initialize the Profile class.

        Args:
            t (float): Initial time. Defaults to 0.0.
            device (torch.device): Devices used for model inference. Defaults to None (cpu).
        """
        self.t = t
        self.device = device
        self.cuda = bool(device and str(device).startswith("cuda"))

    def __enter__(self):
        """Start timing."""
        self.start = self.time()
        return self

    def __exit__(self, type, value, traceback):  # noqa
        """Stop timing."""
        self.dt = self.time() - self.start  # delta-time
        self.t += self.dt  # accumulate dt

    def __str__(self):
        """Returns a human-readable string representing the accumulated elapsed time in the profiler."""
        return f"Elapsed time is {self.t} s"

    def time(self):
        """Get current time."""
        if self.cuda:
            torch.cuda.synchronize(self.device)
        return time.time()

__enter__()

开始时间

源代码 ultralytics/utils/ops.py
def __enter__(self):
    """Start timing."""
    self.start = self.time()
    return self

__exit__(type, value, traceback)

停止计时。

源代码 ultralytics/utils/ops.py
def __exit__(self, type, value, traceback):  # noqa
    """Stop timing."""
    self.dt = self.time() - self.start  # delta-time
    self.t += self.dt  # accumulate dt

__init__(t=0.0, device=None)

初始化 Profile 类。

参数

名称 类型 说明 默认值
t float

初始时间。默认为 0.0。

0.0
device device

用于模型推理的设备。默认为 "无"(cpu)。

None
源代码 ultralytics/utils/ops.py
def __init__(self, t=0.0, device: torch.device = None):
    """
    Initialize the Profile class.

    Args:
        t (float): Initial time. Defaults to 0.0.
        device (torch.device): Devices used for model inference. Defaults to None (cpu).
    """
    self.t = t
    self.device = device
    self.cuda = bool(device and str(device).startswith("cuda"))

__str__()

返回一个人类可读字符串,表示剖析器中的累计耗时。

源代码 ultralytics/utils/ops.py
def __str__(self):
    """Returns a human-readable string representing the accumulated elapsed time in the profiler."""
    return f"Elapsed time is {self.t} s"

time()

获取当前时间

源代码 ultralytics/utils/ops.py
def time(self):
    """Get current time."""
    if self.cuda:
        torch.cuda.synchronize(self.device)
    return time.time()



ultralytics.utils.ops.segment2box(segment, width=640, height=640)

将 1 个段落标签转换为 1 个方框标签,并应用内部图像约束,即 (xy1, xy2, ...)转换为 (xyxy)。

参数

名称 类型 说明 默认值
segment Tensor

分段标签

所需
width int

图像的宽度。默认为 640

640
height int

图像的高度。默认为 640

640

返回:

类型 说明
ndarray

段的最小和最大 x 值和 y 值。

源代码 ultralytics/utils/ops.py
def segment2box(segment, width=640, height=640):
    """
    Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy).

    Args:
        segment (torch.Tensor): the segment label
        width (int): the width of the image. Defaults to 640
        height (int): The height of the image. Defaults to 640

    Returns:
        (np.ndarray): the minimum and maximum x and y values of the segment.
    """
    x, y = segment.T  # segment xy
    inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
    x = x[inside]
    y = y[inside]
    return (
        np.array([x.min(), y.min(), x.max(), y.max()], dtype=segment.dtype)
        if any(x)
        else np.zeros(4, dtype=segment.dtype)
    )  # xyxy



ultralytics.utils.ops.scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None, padding=True, xywh=False)

将边界框(默认格式为 xyxy)从其最初指定的图像形状(img1_shape)调整为不同图像形状(img0_shape)。 形状(img1_shape)调整为不同图像的形状(img0_shape)。

参数

名称 类型 说明 默认值
img1_shape tuple

边界框的图像形状,格式为(高、宽)。

所需
boxes Tensor

图像中物体的边界框,格式为 (x1, y1, x2, y2)

所需
img0_shape tuple

目标图像的形状,格式为(高、宽)。

所需
ratio_pad tuple

的元组(ratio, pad),用于缩放方框。如果未提供,将根据两幅图像的尺寸差来计算比率和垫值。 将根据两幅图像的尺寸差来计算。

None
padding bool

如果为 True,则假定方框是基于yolo 样式增强的图像。如果为 False,则进行常规 重新缩放。

True
xywh bool

方框格式是否为 xywh,默认为假。

False

返回:

名称 类型 说明
boxes Tensor

按比例缩放的边界框,格式为 (x1, y1, x2, y2)

源代码 ultralytics/utils/ops.py
def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None, padding=True, xywh=False):
    """
    Rescales bounding boxes (in the format of xyxy by default) from the shape of the image they were originally
    specified in (img1_shape) to the shape of a different image (img0_shape).

    Args:
        img1_shape (tuple): The shape of the image that the bounding boxes are for, in the format of (height, width).
        boxes (torch.Tensor): the bounding boxes of the objects in the image, in the format of (x1, y1, x2, y2)
        img0_shape (tuple): the shape of the target image, in the format of (height, width).
        ratio_pad (tuple): a tuple of (ratio, pad) for scaling the boxes. If not provided, the ratio and pad will be
            calculated based on the size difference between the two images.
        padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
            rescaling.
        xywh (bool): The box format is xywh or not, default=False.

    Returns:
        boxes (torch.Tensor): The scaled bounding boxes, in the format of (x1, y1, x2, y2)
    """
    if ratio_pad is None:  # calculate from img0_shape
        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
        pad = (
            round((img1_shape[1] - img0_shape[1] * gain) / 2 - 0.1),
            round((img1_shape[0] - img0_shape[0] * gain) / 2 - 0.1),
        )  # wh padding
    else:
        gain = ratio_pad[0][0]
        pad = ratio_pad[1]

    if padding:
        boxes[..., 0] -= pad[0]  # x padding
        boxes[..., 1] -= pad[1]  # y padding
        if not xywh:
            boxes[..., 2] -= pad[0]  # x padding
            boxes[..., 3] -= pad[1]  # y padding
    boxes[..., :4] /= gain
    return clip_boxes(boxes, img0_shape)



ultralytics.utils.ops.make_divisible(x, divisor)

返回能被给定除数整除的最接近的数字。

参数

名称 类型 说明 默认值
x int

能被整除的数字。

所需
divisor int | Tensor

除数。

所需

返回:

类型 说明
int

能被除数整除的最近的数。

源代码 ultralytics/utils/ops.py
def make_divisible(x, divisor):
    """
    Returns the nearest number that is divisible by the given divisor.

    Args:
        x (int): The number to make divisible.
        divisor (int | torch.Tensor): The divisor.

    Returns:
        (int): The nearest number divisible by the divisor.
    """
    if isinstance(divisor, torch.Tensor):
        divisor = int(divisor.max())  # to int
    return math.ceil(x / divisor) * divisor



ultralytics.utils.ops.nms_rotated(boxes, scores, threshold=0.45)

用于 obbs 的 NMS,由 probiou 和 fast-nms 提供支持。

参数

名称 类型 说明 默认值
boxes Tensor

(N, 5), xywhr.

所需
scores Tensor

(N, ).

所需
threshold float

Iou 门槛。

0.45

返回:

源代码 ultralytics/utils/ops.py
def nms_rotated(boxes, scores, threshold=0.45):
    """
    NMS for obbs, powered by probiou and fast-nms.

    Args:
        boxes (torch.Tensor): (N, 5), xywhr.
        scores (torch.Tensor): (N, ).
        threshold (float): Iou threshold.

    Returns:
    """
    if len(boxes) == 0:
        return np.empty((0,), dtype=np.int8)
    sorted_idx = torch.argsort(scores, descending=True)
    boxes = boxes[sorted_idx]
    ious = batch_probiou(boxes, boxes).triu_(diagonal=1)
    pick = torch.nonzero(ious.max(dim=0)[0] < threshold).squeeze_(-1)
    return sorted_idx[pick]



ultralytics.utils.ops.non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False, labels=(), max_det=300, nc=0, max_time_img=0.05, max_nms=30000, max_wh=7680, in_place=True, rotated=False)

对一组盒子执行非最大抑制 (NMS),支持每个盒子的掩码和多个标签。

参数

名称 类型 说明 默认值
prediction Tensor

形状为(batch_size、num_classes + 4 + num_masks、num_boxes)的tensor 包含预测的方框、类和掩码。tensor 的格式应为 模型输出的格式,如YOLO 。

所需
conf_thres float

置信度阈值,低于该值将被过滤掉。 有效值在 0.0 和 1.0 之间。

0.25
iou_thres float

IoU 阈值,低于此阈值的方框将在 NMS 期间被过滤掉。 有效值介于 0.0 和 1.0 之间。

0.45
classes List[int]

要考虑的类别索引列表。如果无,将考虑所有类别。

None
agnostic bool

如果为 True,则模型与类的数量无关,所有类都将被视为一个。 类将被视为一个。

False
multi_label bool

如果为 True,则每个方框可以有多个标签。

False
labels List[List[Union[int, float, Tensor]]]

列表,其中每个内 列表包含给定图像的先验标签。列表格式应为 格式,每个标签为一个元组(class_index, x1, y1, x2, y2)。

()
max_det int

NMS 后保留的最大箱数。

300
nc int

模型输出的类别数。之后的任何指数都将被视为掩码。

0
max_time_img float

处理一幅图像的最长时间(秒)。

0.05
max_nms int

输入 torchvision.ops.nms() 的最大方框数。

30000
max_wh int

最大方框宽度和高度(以像素为单位)。

7680
in_place bool

如果为 True,输入预测结果tensor 将被就地修改。

True

返回:

类型 说明
List[Tensor]

长度为 batch_size 的列表,其中每个元素都是tensor 的 形状(num_boxes, 6 + num_masks),其中包含保留的方框,列有 (x1, y1, x2, y2, confidence, class, mask1, mask2, ...)。

源代码 ultralytics/utils/ops.py
def non_max_suppression(
    prediction,
    conf_thres=0.25,
    iou_thres=0.45,
    classes=None,
    agnostic=False,
    multi_label=False,
    labels=(),
    max_det=300,
    nc=0,  # number of classes (optional)
    max_time_img=0.05,
    max_nms=30000,
    max_wh=7680,
    in_place=True,
    rotated=False,
):
    """
    Perform non-maximum suppression (NMS) on a set of boxes, with support for masks and multiple labels per box.

    Args:
        prediction (torch.Tensor): A tensor of shape (batch_size, num_classes + 4 + num_masks, num_boxes)
            containing the predicted boxes, classes, and masks. The tensor should be in the format
            output by a model, such as YOLO.
        conf_thres (float): The confidence threshold below which boxes will be filtered out.
            Valid values are between 0.0 and 1.0.
        iou_thres (float): The IoU threshold below which boxes will be filtered out during NMS.
            Valid values are between 0.0 and 1.0.
        classes (List[int]): A list of class indices to consider. If None, all classes will be considered.
        agnostic (bool): If True, the model is agnostic to the number of classes, and all
            classes will be considered as one.
        multi_label (bool): If True, each box may have multiple labels.
        labels (List[List[Union[int, float, torch.Tensor]]]): A list of lists, where each inner
            list contains the apriori labels for a given image. The list should be in the format
            output by a dataloader, with each label being a tuple of (class_index, x1, y1, x2, y2).
        max_det (int): The maximum number of boxes to keep after NMS.
        nc (int, optional): The number of classes output by the model. Any indices after this will be considered masks.
        max_time_img (float): The maximum time (seconds) for processing one image.
        max_nms (int): The maximum number of boxes into torchvision.ops.nms().
        max_wh (int): The maximum box width and height in pixels.
        in_place (bool): If True, the input prediction tensor will be modified in place.

    Returns:
        (List[torch.Tensor]): A list of length batch_size, where each element is a tensor of
            shape (num_boxes, 6 + num_masks) containing the kept boxes, with columns
            (x1, y1, x2, y2, confidence, class, mask1, mask2, ...).
    """

    # Checks
    assert 0 <= conf_thres <= 1, f"Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0"
    assert 0 <= iou_thres <= 1, f"Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0"
    if isinstance(prediction, (list, tuple)):  # YOLOv8 model in validation model, output = (inference_out, loss_out)
        prediction = prediction[0]  # select only inference output

    bs = prediction.shape[0]  # batch size
    nc = nc or (prediction.shape[1] - 4)  # number of classes
    nm = prediction.shape[1] - nc - 4
    mi = 4 + nc  # mask start index
    xc = prediction[:, 4:mi].amax(1) > conf_thres  # candidates

    # Settings
    # min_wh = 2  # (pixels) minimum box width and height
    time_limit = 2.0 + max_time_img * bs  # seconds to quit after
    multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)

    prediction = prediction.transpose(-1, -2)  # shape(1,84,6300) to shape(1,6300,84)
    if not rotated:
        if in_place:
            prediction[..., :4] = xywh2xyxy(prediction[..., :4])  # xywh to xyxy
        else:
            prediction = torch.cat((xywh2xyxy(prediction[..., :4]), prediction[..., 4:]), dim=-1)  # xywh to xyxy

    t = time.time()
    output = [torch.zeros((0, 6 + nm), device=prediction.device)] * bs
    for xi, x in enumerate(prediction):  # image index, image inference
        # Apply constraints
        # x[((x[:, 2:4] < min_wh) | (x[:, 2:4] > max_wh)).any(1), 4] = 0  # width-height
        x = x[xc[xi]]  # confidence

        # Cat apriori labels if autolabelling
        if labels and len(labels[xi]) and not rotated:
            lb = labels[xi]
            v = torch.zeros((len(lb), nc + nm + 4), device=x.device)
            v[:, :4] = xywh2xyxy(lb[:, 1:5])  # box
            v[range(len(lb)), lb[:, 0].long() + 4] = 1.0  # cls
            x = torch.cat((x, v), 0)

        # If none remain process next image
        if not x.shape[0]:
            continue

        # Detections matrix nx6 (xyxy, conf, cls)
        box, cls, mask = x.split((4, nc, nm), 1)

        if multi_label:
            i, j = torch.where(cls > conf_thres)
            x = torch.cat((box[i], x[i, 4 + j, None], j[:, None].float(), mask[i]), 1)
        else:  # best class only
            conf, j = cls.max(1, keepdim=True)
            x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres]

        # Filter by class
        if classes is not None:
            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]

        # Check shape
        n = x.shape[0]  # number of boxes
        if not n:  # no boxes
            continue
        if n > max_nms:  # excess boxes
            x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence and remove excess boxes

        # Batched NMS
        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
        scores = x[:, 4]  # scores
        if rotated:
            boxes = torch.cat((x[:, :2] + c, x[:, 2:4], x[:, -1:]), dim=-1)  # xywhr
            i = nms_rotated(boxes, scores, iou_thres)
        else:
            boxes = x[:, :4] + c  # boxes (offset by class)
            i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
        i = i[:max_det]  # limit detections

        # # Experimental
        # merge = False  # use merge-NMS
        # if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
        #     # Update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
        #     from .metrics import box_iou
        #     iou = box_iou(boxes[i], boxes) > iou_thres  # iou matrix
        #     weights = iou * scores[None]  # box weights
        #     x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
        #     redundant = True  # require redundant detections
        #     if redundant:
        #         i = i[iou.sum(1) > 1]  # require redundancy

        output[xi] = x[i]
        if (time.time() - t) > time_limit:
            LOGGER.warning(f"WARNING ⚠️ NMS time limit {time_limit:.3f}s exceeded")
            break  # time limit exceeded

    return output



ultralytics.utils.ops.clip_boxes(boxes, shape)

获取边界框列表和形状(高度、宽度),并将边界框剪切到形状上。

参数

名称 类型 说明 默认值
boxes Tensor

要剪切的边界框

所需
shape tuple

图像的形状

所需

返回:

类型 说明
Tensor | ndarray

剪切盒

源代码 ultralytics/utils/ops.py
def clip_boxes(boxes, shape):
    """
    Takes a list of bounding boxes and a shape (height, width) and clips the bounding boxes to the shape.

    Args:
        boxes (torch.Tensor): the bounding boxes to clip
        shape (tuple): the shape of the image

    Returns:
        (torch.Tensor | numpy.ndarray): Clipped boxes
    """
    if isinstance(boxes, torch.Tensor):  # faster individually (WARNING: inplace .clamp_() Apple MPS bug)
        boxes[..., 0] = boxes[..., 0].clamp(0, shape[1])  # x1
        boxes[..., 1] = boxes[..., 1].clamp(0, shape[0])  # y1
        boxes[..., 2] = boxes[..., 2].clamp(0, shape[1])  # x2
        boxes[..., 3] = boxes[..., 3].clamp(0, shape[0])  # y2
    else:  # np.array (faster grouped)
        boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, shape[1])  # x1, x2
        boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0])  # y1, y2
    return boxes



ultralytics.utils.ops.clip_coords(coords, shape)

将线条坐标剪切到图像边界。

参数

名称 类型 说明 默认值
coords Tensor | ndarray

线条坐标列表。

所需
shape tuple

一个整数元组,表示图像的大小,格式为(高、宽)。

所需

返回:

类型 说明
Tensor | ndarray

剪切坐标

源代码 ultralytics/utils/ops.py
def clip_coords(coords, shape):
    """
    Clip line coordinates to the image boundaries.

    Args:
        coords (torch.Tensor | numpy.ndarray): A list of line coordinates.
        shape (tuple): A tuple of integers representing the size of the image in the format (height, width).

    Returns:
        (torch.Tensor | numpy.ndarray): Clipped coordinates
    """
    if isinstance(coords, torch.Tensor):  # faster individually (WARNING: inplace .clamp_() Apple MPS bug)
        coords[..., 0] = coords[..., 0].clamp(0, shape[1])  # x
        coords[..., 1] = coords[..., 1].clamp(0, shape[0])  # y
    else:  # np.array (faster grouped)
        coords[..., 0] = coords[..., 0].clip(0, shape[1])  # x
        coords[..., 1] = coords[..., 1].clip(0, shape[0])  # y
    return coords



ultralytics.utils.ops.scale_image(masks, im0_shape, ratio_pad=None)

获取蒙版,并将其调整为原始图像大小。

参数

名称 类型 说明 默认值
masks ndarray

调整大小和填充的蒙版/图像,[h, w, num]/[h, w, 3]。

所需
im0_shape tuple

原始图像形状

所需
ratio_pad tuple

填充与原始图像的比例。

None

返回:

名称 类型 说明
masks Tensor

退回的面具。

源代码 ultralytics/utils/ops.py
def scale_image(masks, im0_shape, ratio_pad=None):
    """
    Takes a mask, and resizes it to the original image size.

    Args:
        masks (np.ndarray): resized and padded masks/images, [h, w, num]/[h, w, 3].
        im0_shape (tuple): the original image shape
        ratio_pad (tuple): the ratio of the padding to the original image.

    Returns:
        masks (torch.Tensor): The masks that are being returned.
    """
    # Rescale coordinates (xyxy) from im1_shape to im0_shape
    im1_shape = masks.shape
    if im1_shape[:2] == im0_shape[:2]:
        return masks
    if ratio_pad is None:  # calculate from im0_shape
        gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1])  # gain  = old / new
        pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2  # wh padding
    else:
        # gain = ratio_pad[0][0]
        pad = ratio_pad[1]
    top, left = int(pad[1]), int(pad[0])  # y, x
    bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0])

    if len(masks.shape) < 2:
        raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}')
    masks = masks[top:bottom, left:right]
    masks = cv2.resize(masks, (im0_shape[1], im0_shape[0]))
    if len(masks.shape) == 2:
        masks = masks[:, :, None]

    return masks



ultralytics.utils.ops.xyxy2xywh(x)

将边界框坐标从 (x1, y1, x2, y2) 格式转换为 (x, y, width, height) 格式,其中 (x1, y1) 为左上角,(x2, y2) 为右下角。 为左上角,(x2, y2) 为右下角。

参数

名称 类型 说明 默认值
x ndarray | Tensor

输入的边界框坐标,格式为 (x1, y1, x2, y2)。

所需

返回:

名称 类型 说明
y ndarray | Tensor

边界框坐标,格式为(x、y、宽、高)。

源代码 ultralytics/utils/ops.py
def xyxy2xywh(x):
    """
    Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height) format where (x1, y1) is the
    top-left corner and (x2, y2) is the bottom-right corner.

    Args:
        x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x1, y1, x2, y2) format.

    Returns:
        y (np.ndarray | torch.Tensor): The bounding box coordinates in (x, y, width, height) format.
    """
    assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}"
    y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x)  # faster than clone/copy
    y[..., 0] = (x[..., 0] + x[..., 2]) / 2  # x center
    y[..., 1] = (x[..., 1] + x[..., 3]) / 2  # y center
    y[..., 2] = x[..., 2] - x[..., 0]  # width
    y[..., 3] = x[..., 3] - x[..., 1]  # height
    return y



ultralytics.utils.ops.xywh2xyxy(x)

将边界框坐标从 (x, y, width, height) 格式转换为 (x1, y1, x2, y2) 格式,其中 (x1, y1) 为左上角,(x2, y2) 为右下角。 为左上角,(x2, y2) 为右下角。

参数

名称 类型 说明 默认值
x ndarray | Tensor

输入的边界框坐标,格式为(x、y、宽、高)。

所需

返回:

名称 类型 说明
y ndarray | Tensor

边界框坐标,格式为 (x1, y1, x2, y2)。

源代码 ultralytics/utils/ops.py
def xywh2xyxy(x):
    """
    Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the
    top-left corner and (x2, y2) is the bottom-right corner.

    Args:
        x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x, y, width, height) format.

    Returns:
        y (np.ndarray | torch.Tensor): The bounding box coordinates in (x1, y1, x2, y2) format.
    """
    assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}"
    y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x)  # faster than clone/copy
    dw = x[..., 2] / 2  # half-width
    dh = x[..., 3] / 2  # half-height
    y[..., 0] = x[..., 0] - dw  # top left x
    y[..., 1] = x[..., 1] - dh  # top left y
    y[..., 2] = x[..., 0] + dw  # bottom right x
    y[..., 3] = x[..., 1] + dh  # bottom right y
    return y



ultralytics.utils.ops.xywhn2xyxy(x, w=640, h=640, padw=0, padh=0)

将归一化边界框坐标转换为像素坐标。

参数

名称 类型 说明 默认值
x ndarray | Tensor

边界框坐标。

所需
w int

图像宽度。默认为 640

640
h int

图像的高度。默认为 640

640
padw int

填充宽度。默认为 0

0
padh int

填充高度。默认为 0

0

返回值: y (np.ndarray |torch.Tensor):边界框的坐标,格式为 [x1, y1, x2, y2] 其中 x1,y1 是边界框的左上角,x2,y2 是边界框的右下角。

源代码 ultralytics/utils/ops.py
def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
    """
    Convert normalized bounding box coordinates to pixel coordinates.

    Args:
        x (np.ndarray | torch.Tensor): The bounding box coordinates.
        w (int): Width of the image. Defaults to 640
        h (int): Height of the image. Defaults to 640
        padw (int): Padding width. Defaults to 0
        padh (int): Padding height. Defaults to 0
    Returns:
        y (np.ndarray | torch.Tensor): The coordinates of the bounding box in the format [x1, y1, x2, y2] where
            x1,y1 is the top-left corner, x2,y2 is the bottom-right corner of the bounding box.
    """
    assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}"
    y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x)  # faster than clone/copy
    y[..., 0] = w * (x[..., 0] - x[..., 2] / 2) + padw  # top left x
    y[..., 1] = h * (x[..., 1] - x[..., 3] / 2) + padh  # top left y
    y[..., 2] = w * (x[..., 0] + x[..., 2] / 2) + padw  # bottom right x
    y[..., 3] = h * (x[..., 1] + x[..., 3] / 2) + padh  # bottom right y
    return y



ultralytics.utils.ops.xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0)

将边界框坐标从 (x1, y1, x2, y2) 格式转换为 (x, y, width, height, normalized) 格式、 宽度和高度归一化为图像尺寸。

参数

名称 类型 说明 默认值
x ndarray | Tensor

输入的边界框坐标,格式为 (x1, y1, x2, y2)。

所需
w int

图像的宽度。默认为 640

640
h int

图像的高度。默认为 640

640
clip bool

如果为 True,方框将被剪切到图像边界。默认为假

False
eps float

方框宽度和高度的最小值。默认为 0.0

0.0

返回:

名称 类型 说明
y ndarray | Tensor

以(x、y、宽、高、归一化)格式表示的边界框坐标

源代码 ultralytics/utils/ops.py
def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0):
    """
    Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height, normalized) format. x, y,
    width and height are normalized to image dimensions.

    Args:
        x (np.ndarray | torch.Tensor): The input bounding box coordinates in (x1, y1, x2, y2) format.
        w (int): The width of the image. Defaults to 640
        h (int): The height of the image. Defaults to 640
        clip (bool): If True, the boxes will be clipped to the image boundaries. Defaults to False
        eps (float): The minimum value of the box's width and height. Defaults to 0.0

    Returns:
        y (np.ndarray | torch.Tensor): The bounding box coordinates in (x, y, width, height, normalized) format
    """
    if clip:
        x = clip_boxes(x, (h - eps, w - eps))
    assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}"
    y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x)  # faster than clone/copy
    y[..., 0] = ((x[..., 0] + x[..., 2]) / 2) / w  # x center
    y[..., 1] = ((x[..., 1] + x[..., 3]) / 2) / h  # y center
    y[..., 2] = (x[..., 2] - x[..., 0]) / w  # width
    y[..., 3] = (x[..., 3] - x[..., 1]) / h  # height
    return y



ultralytics.utils.ops.xywh2ltwh(x)

将边界框格式从 [x, y, w, h] 转换为 [x1, y1, w, h],其中 x1, y1 为左上角坐标。

参数

名称 类型 说明 默认值
x ndarray | Tensor

输入tensor 和 xywh 格式的边界框坐标

所需

返回:

名称 类型 说明
y ndarray | Tensor

xyltwh 格式的边界框坐标

源代码 ultralytics/utils/ops.py
def xywh2ltwh(x):
    """
    Convert the bounding box format from [x, y, w, h] to [x1, y1, w, h], where x1, y1 are the top-left coordinates.

    Args:
        x (np.ndarray | torch.Tensor): The input tensor with the bounding box coordinates in the xywh format

    Returns:
        y (np.ndarray | torch.Tensor): The bounding box coordinates in the xyltwh format
    """
    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
    y[..., 0] = x[..., 0] - x[..., 2] / 2  # top left x
    y[..., 1] = x[..., 1] - x[..., 3] / 2  # top left y
    return y



ultralytics.utils.ops.xyxy2ltwh(x)

将 nx4 边界框从 [x1, y1, x2, y2] 转换为 [x1, y1, w, h],其中 xy1= 左上角,xy2= 右下角。

参数

名称 类型 说明 默认值
x ndarray | Tensor

输入tensor ,其中包含 xyxy 格式的边界框坐标

所需

返回:

名称 类型 说明
y ndarray | Tensor

xyltwh 格式的边界框坐标。

源代码 ultralytics/utils/ops.py
def xyxy2ltwh(x):
    """
    Convert nx4 bounding boxes from [x1, y1, x2, y2] to [x1, y1, w, h], where xy1=top-left, xy2=bottom-right.

    Args:
        x (np.ndarray | torch.Tensor): The input tensor with the bounding boxes coordinates in the xyxy format

    Returns:
        y (np.ndarray | torch.Tensor): The bounding box coordinates in the xyltwh format.
    """
    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
    y[..., 2] = x[..., 2] - x[..., 0]  # width
    y[..., 3] = x[..., 3] - x[..., 1]  # height
    return y



ultralytics.utils.ops.ltwh2xywh(x)

将 nx4 个方框从 [x1, y1, w, h] 转换为 [x, y, w, h],其中 xy1=左上角,xy=中间。

参数

名称 类型 说明 默认值
x Tensor

输入tensor

所需

返回:

名称 类型 说明
y ndarray | Tensor

xywh 格式的边界框坐标。

源代码 ultralytics/utils/ops.py
def ltwh2xywh(x):
    """
    Convert nx4 boxes from [x1, y1, w, h] to [x, y, w, h] where xy1=top-left, xy=center.

    Args:
        x (torch.Tensor): the input tensor

    Returns:
        y (np.ndarray | torch.Tensor): The bounding box coordinates in the xywh format.
    """
    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
    y[..., 0] = x[..., 0] + x[..., 2] / 2  # center x
    y[..., 1] = x[..., 1] + x[..., 3] / 2  # center y
    return y



ultralytics.utils.ops.xyxyxyxy2xywhr(corners)

将[xy1, xy2, xy3, xy4]批量定向边框 (OBB) 转换为[xywh, rotation]。旋转值 以 0 至 90 度为单位。

参数

名称 类型 说明 默认值
corners ndarray | Tensor

输入形状为 (n, 8) 的角。

所需

返回:

类型 说明
ndarray | Tensor

以 [cx、cy、w、h、旋转] 格式转换形状为 (n,5) 的数据。

源代码 ultralytics/utils/ops.py
def xyxyxyxy2xywhr(corners):
    """
    Convert batched Oriented Bounding Boxes (OBB) from [xy1, xy2, xy3, xy4] to [xywh, rotation]. Rotation values are
    expected in degrees from 0 to 90.

    Args:
        corners (numpy.ndarray | torch.Tensor): Input corners of shape (n, 8).

    Returns:
        (numpy.ndarray | torch.Tensor): Converted data in [cx, cy, w, h, rotation] format of shape (n, 5).
    """
    is_torch = isinstance(corners, torch.Tensor)
    points = corners.cpu().numpy() if is_torch else corners
    points = points.reshape(len(corners), -1, 2)
    rboxes = []
    for pts in points:
        # NOTE: Use cv2.minAreaRect to get accurate xywhr,
        # especially some objects are cut off by augmentations in dataloader.
        (x, y), (w, h), angle = cv2.minAreaRect(pts)
        rboxes.append([x, y, w, h, angle / 180 * np.pi])
    return (
        torch.tensor(rboxes, device=corners.device, dtype=corners.dtype)
        if is_torch
        else np.asarray(rboxes, dtype=points.dtype)
    )  # rboxes



ultralytics.utils.ops.xywhr2xyxyxyxy(rboxes)

将 [xywh, rotation] 的批次定向边框 (OBB) 转换为 [xy1, xy2, xy3, xy4]。旋转值应 以 0 至 90 度为单位。

参数

名称 类型 说明 默认值
rboxes ndarray | Tensor

形状为 (n, 5) 或 (b, n, 5) 的 [cx, cy, w, h, rotation] 格式方框。

所需

返回:

类型 说明
ndarray | Tensor

转换形状为 (n, 4, 2) 或 (b, n, 4, 2) 的角点。

源代码 ultralytics/utils/ops.py
def xywhr2xyxyxyxy(rboxes):
    """
    Convert batched Oriented Bounding Boxes (OBB) from [xywh, rotation] to [xy1, xy2, xy3, xy4]. Rotation values should
    be in degrees from 0 to 90.

    Args:
        rboxes (numpy.ndarray | torch.Tensor): Boxes in [cx, cy, w, h, rotation] format of shape (n, 5) or (b, n, 5).

    Returns:
        (numpy.ndarray | torch.Tensor): Converted corner points of shape (n, 4, 2) or (b, n, 4, 2).
    """
    is_numpy = isinstance(rboxes, np.ndarray)
    cos, sin = (np.cos, np.sin) if is_numpy else (torch.cos, torch.sin)

    ctr = rboxes[..., :2]
    w, h, angle = (rboxes[..., i : i + 1] for i in range(2, 5))
    cos_value, sin_value = cos(angle), sin(angle)
    vec1 = [w / 2 * cos_value, w / 2 * sin_value]
    vec2 = [-h / 2 * sin_value, h / 2 * cos_value]
    vec1 = np.concatenate(vec1, axis=-1) if is_numpy else torch.cat(vec1, dim=-1)
    vec2 = np.concatenate(vec2, axis=-1) if is_numpy else torch.cat(vec2, dim=-1)
    pt1 = ctr + vec1 + vec2
    pt2 = ctr + vec1 - vec2
    pt3 = ctr - vec1 - vec2
    pt4 = ctr - vec1 + vec2
    return np.stack([pt1, pt2, pt3, pt4], axis=-2) if is_numpy else torch.stack([pt1, pt2, pt3, pt4], dim=-2)



ultralytics.utils.ops.ltwh2xyxy(x)

它将边界框从 [x1, y1, w, h] 转换为 [x1, y1, x2, y2],其中 xy1= 左上角,xy2= 右下角。

参数

名称 类型 说明 默认值
x ndarray | Tensor

输入图像

所需

返回:

名称 类型 说明
y ndarray | Tensor

边界框的 xyxy 坐标。

源代码 ultralytics/utils/ops.py
def ltwh2xyxy(x):
    """
    It converts the bounding box from [x1, y1, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right.

    Args:
        x (np.ndarray | torch.Tensor): the input image

    Returns:
        y (np.ndarray | torch.Tensor): the xyxy coordinates of the bounding boxes.
    """
    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
    y[..., 2] = x[..., 2] + x[..., 0]  # width
    y[..., 3] = x[..., 3] + x[..., 1]  # height
    return y



ultralytics.utils.ops.segments2boxes(segments)

它将段落标签转换为方框标签,即 (cls, xy1, xy2, ...)转换为 (cls, xywh)

参数

名称 类型 说明 默认值
segments list

段列表,每个段是点列表,每个点是 x、y 坐标列表

所需

返回:

类型 说明
ndarray

边界框的 xywh 坐标。

源代码 ultralytics/utils/ops.py
def segments2boxes(segments):
    """
    It converts segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)

    Args:
        segments (list): list of segments, each segment is a list of points, each point is a list of x, y coordinates

    Returns:
        (np.ndarray): the xywh coordinates of the bounding boxes.
    """
    boxes = []
    for s in segments:
        x, y = s.T  # segment xy
        boxes.append([x.min(), y.min(), x.max(), y.max()])  # cls, xyxy
    return xyxy2xywh(np.array(boxes))  # cls, xywh



ultralytics.utils.ops.resample_segments(segments, n=1000)

输入一个线段列表(n,2),并返回一个向上采样到 n 个点的线段列表(n,2)。

参数

名称 类型 说明 默认值
segments list

(n,2) 数组的列表,其中 n 是线段中的点数。

所需
n int

对片段重新采样的点数。默认为 1000

1000

返回:

名称 类型 说明
segments list

重新采样的片段。

源代码 ultralytics/utils/ops.py
def resample_segments(segments, n=1000):
    """
    Inputs a list of segments (n,2) and returns a list of segments (n,2) up-sampled to n points each.

    Args:
        segments (list): a list of (n,2) arrays, where n is the number of points in the segment.
        n (int): number of points to resample the segment to. Defaults to 1000

    Returns:
        segments (list): the resampled segments.
    """
    for i, s in enumerate(segments):
        s = np.concatenate((s, s[0:1, :]), axis=0)
        x = np.linspace(0, len(s) - 1, n)
        xp = np.arange(len(s))
        segments[i] = (
            np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)], dtype=np.float32).reshape(2, -1).T
        )  # segment xy
    return segments



ultralytics.utils.ops.crop_mask(masks, boxes)

它接收一个遮罩和一个边界框,然后返回一个按边界框裁剪的遮罩。

参数

名称 类型 说明 默认值
masks Tensor

[n, h, w]tensor 掩码

所需
boxes Tensor

[n, 4]tensor 相对点形式的 bbox 坐标

所需

返回:

类型 说明
Tensor

遮罩被裁剪为边界框。

源代码 ultralytics/utils/ops.py
def crop_mask(masks, boxes):
    """
    It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box.

    Args:
        masks (torch.Tensor): [n, h, w] tensor of masks
        boxes (torch.Tensor): [n, 4] tensor of bbox coordinates in relative point form

    Returns:
        (torch.Tensor): The masks are being cropped to the bounding box.
    """
    n, h, w = masks.shape
    x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1)  # x1 shape(n,1,1)
    r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :]  # rows shape(1,1,w)
    c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None]  # cols shape(1,h,1)

    return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2))



ultralytics.utils.ops.process_mask_upsample(protos, masks_in, bboxes, shape)

获取遮罩头的输出,并将遮罩应用于边界框。这样生成的蒙版质量更高 但速度较慢。

参数

名称 类型 说明 默认值
protos Tensor

[掩码尺寸、掩码高度、掩码宽度] (mask_dim, mask_h, mask_w)

所需
masks_in Tensor

[n,mask_dim],n 为 nms 后的屏蔽数

所需
bboxes Tensor

[n,4],n 是 nms 之后的屏蔽数

所需
shape tuple

输入图像的大小 (h,w)

所需

返回:

类型 说明
Tensor

上采样掩码

源代码 ultralytics/utils/ops.py
def process_mask_upsample(protos, masks_in, bboxes, shape):
    """
    Takes the output of the mask head, and applies the mask to the bounding boxes. This produces masks of higher quality
    but is slower.

    Args:
        protos (torch.Tensor): [mask_dim, mask_h, mask_w]
        masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms
        bboxes (torch.Tensor): [n, 4], n is number of masks after nms
        shape (tuple): the size of the input image (h,w)

    Returns:
        (torch.Tensor): The upsampled masks.
    """
    c, mh, mw = protos.shape  # CHW
    masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
    masks = F.interpolate(masks[None], shape, mode="bilinear", align_corners=False)[0]  # CHW
    masks = crop_mask(masks, bboxes)  # CHW
    return masks.gt_(0.5)



ultralytics.utils.ops.process_mask(protos, masks_in, bboxes, shape, upsample=False)

使用遮罩头的输出将遮罩应用于边界框。

参数

名称 类型 说明 默认值
protos Tensor

形状为 [mask_dim, mask_h, mask_w] 的tensor 。

所需
masks_in Tensor

形状为 [n, mask_dim]的tensor ,其中 n 是 NMS 后的掩码数。

所需
bboxes Tensor

形状为 [n, 4] 的tensor ,其中 n 是 NMS 后的掩码数。

所需
shape tuple

表示输入图像大小的整数元组,格式为 (h,w)。

所需
upsample bool

指示是否将掩码上采样到原始图像大小的标志。默认为假。

False

返回:

类型 说明
Tensor

二进制掩码tensor 的形状为 [n,h,w],其中 n 是 NMS 后的掩码数,h 和 w 是输入图像的高度和宽度。 是输入图像的高度和宽度。掩码应用于边界框。

源代码 ultralytics/utils/ops.py
def process_mask(protos, masks_in, bboxes, shape, upsample=False):
    """
    Apply masks to bounding boxes using the output of the mask head.

    Args:
        protos (torch.Tensor): A tensor of shape [mask_dim, mask_h, mask_w].
        masks_in (torch.Tensor): A tensor of shape [n, mask_dim], where n is the number of masks after NMS.
        bboxes (torch.Tensor): A tensor of shape [n, 4], where n is the number of masks after NMS.
        shape (tuple): A tuple of integers representing the size of the input image in the format (h, w).
        upsample (bool): A flag to indicate whether to upsample the mask to the original image size. Default is False.

    Returns:
        (torch.Tensor): A binary mask tensor of shape [n, h, w], where n is the number of masks after NMS, and h and w
            are the height and width of the input image. The mask is applied to the bounding boxes.
    """

    c, mh, mw = protos.shape  # CHW
    ih, iw = shape
    masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)  # CHW

    downsampled_bboxes = bboxes.clone()
    downsampled_bboxes[:, 0] *= mw / iw
    downsampled_bboxes[:, 2] *= mw / iw
    downsampled_bboxes[:, 3] *= mh / ih
    downsampled_bboxes[:, 1] *= mh / ih

    masks = crop_mask(masks, downsampled_bboxes)  # CHW
    if upsample:
        masks = F.interpolate(masks[None], shape, mode="bilinear", align_corners=False)[0]  # CHW
    return masks.gt_(0.5)



ultralytics.utils.ops.process_mask_native(protos, masks_in, bboxes, shape)

它采用遮罩头的输出,在上采样到边界框后对其进行裁剪。

参数

名称 类型 说明 默认值
protos Tensor

[掩码尺寸、掩码高度、掩码宽度] (mask_dim, mask_h, mask_w)

所需
masks_in Tensor

[n,mask_dim],n 为 nms 后的屏蔽数

所需
bboxes Tensor

[n,4],n 是 nms 之后的屏蔽数

所需
shape tuple

输入图像的大小 (h,w)

所需

返回:

名称 类型 说明
masks Tensor

返回的掩码尺寸为 [h、w、n]

源代码 ultralytics/utils/ops.py
def process_mask_native(protos, masks_in, bboxes, shape):
    """
    It takes the output of the mask head, and crops it after upsampling to the bounding boxes.

    Args:
        protos (torch.Tensor): [mask_dim, mask_h, mask_w]
        masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms
        bboxes (torch.Tensor): [n, 4], n is number of masks after nms
        shape (tuple): the size of the input image (h,w)

    Returns:
        masks (torch.Tensor): The returned masks with dimensions [h, w, n]
    """
    c, mh, mw = protos.shape  # CHW
    masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
    masks = scale_masks(masks[None], shape)[0]  # CHW
    masks = crop_mask(masks, bboxes)  # CHW
    return masks.gt_(0.5)



ultralytics.utils.ops.scale_masks(masks, shape, padding=True)

根据形状调整段屏蔽的比例。

参数

名称 类型 说明 默认值
masks Tensor

(N、C、H、W)。

所需
shape tuple

高度和宽度

所需
padding bool

如果为 True,则假定方框是基于yolo 样式增强的图像。如果为 False,则进行常规 重新缩放。

True
源代码 ultralytics/utils/ops.py
def scale_masks(masks, shape, padding=True):
    """
    Rescale segment masks to shape.

    Args:
        masks (torch.Tensor): (N, C, H, W).
        shape (tuple): Height and width.
        padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
            rescaling.
    """
    mh, mw = masks.shape[2:]
    gain = min(mh / shape[0], mw / shape[1])  # gain  = old / new
    pad = [mw - shape[1] * gain, mh - shape[0] * gain]  # wh padding
    if padding:
        pad[0] /= 2
        pad[1] /= 2
    top, left = (int(pad[1]), int(pad[0])) if padding else (0, 0)  # y, x
    bottom, right = (int(mh - pad[1]), int(mw - pad[0]))
    masks = masks[..., top:bottom, left:right]

    masks = F.interpolate(masks, shape, mode="bilinear", align_corners=False)  # NCHW
    return masks



ultralytics.utils.ops.scale_coords(img1_shape, coords, img0_shape, ratio_pad=None, normalize=False, padding=True)

将 img1_shape 的线段坐标(xy)调整为 img0_shape。

参数

名称 类型 说明 默认值
img1_shape tuple

坐标的图像形状。

所需
coords Tensor

形状 n,2 要缩放的坐标。

所需
img0_shape tuple

进行分割的图像的形状。

所需
ratio_pad tuple

图像大小与填充图像大小的比率。

None
normalize bool

如果为 True,坐标将归一化为 [0, 1] 范围。默认为 "假"。

False
padding bool

如果为 True,则假定方框是基于yolo 样式增强的图像。如果为 False,则进行常规 重新缩放。

True

返回:

名称 类型 说明
coords Tensor

缩放坐标。

源代码 ultralytics/utils/ops.py
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None, normalize=False, padding=True):
    """
    Rescale segment coordinates (xy) from img1_shape to img0_shape.

    Args:
        img1_shape (tuple): The shape of the image that the coords are from.
        coords (torch.Tensor): the coords to be scaled of shape n,2.
        img0_shape (tuple): the shape of the image that the segmentation is being applied to.
        ratio_pad (tuple): the ratio of the image size to the padded image size.
        normalize (bool): If True, the coordinates will be normalized to the range [0, 1]. Defaults to False.
        padding (bool): If True, assuming the boxes is based on image augmented by yolo style. If False then do regular
            rescaling.

    Returns:
        coords (torch.Tensor): The scaled coordinates.
    """
    if ratio_pad is None:  # calculate from img0_shape
        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
    else:
        gain = ratio_pad[0][0]
        pad = ratio_pad[1]

    if padding:
        coords[..., 0] -= pad[0]  # x padding
        coords[..., 1] -= pad[1]  # y padding
    coords[..., 0] /= gain
    coords[..., 1] /= gain
    coords = clip_coords(coords, img0_shape)
    if normalize:
        coords[..., 0] /= img0_shape[1]  # width
        coords[..., 1] /= img0_shape[0]  # height
    return coords



ultralytics.utils.ops.regularize_rboxes(rboxes)

在 [0, pi/2] 范围内规范化旋转方框。

参数

名称 类型 说明 默认值
rboxes Tensor

(N, 5), xywhr.

所需

返回:

类型 说明
Tensor

规范化方框。

源代码 ultralytics/utils/ops.py
def regularize_rboxes(rboxes):
    """
    Regularize rotated boxes in range [0, pi/2].

    Args:
        rboxes (torch.Tensor): (N, 5), xywhr.

    Returns:
        (torch.Tensor): The regularized boxes.
    """
    x, y, w, h, t = rboxes.unbind(dim=-1)
    # Swap edge and angle if h >= w
    w_ = torch.where(w > h, w, h)
    h_ = torch.where(w > h, h, w)
    t = torch.where(w > h, t, t + math.pi / 2) % math.pi
    return torch.stack([x, y, w_, h_, t], dim=-1)  # regularized boxes



ultralytics.utils.ops.masks2segments(masks, strategy='largest')

它接收掩码(n,h,w)列表,并返回段(n,xy)列表

参数

名称 类型 说明 默认值
masks Tensor

模型的输出,即tensor 的形状 (batch_size, 160, 160)

所需
strategy str

连接 "或 "最大"。默认为最大

'largest'

返回:

名称 类型 说明
segments List

段掩码列表

源代码 ultralytics/utils/ops.py
def masks2segments(masks, strategy="largest"):
    """
    It takes a list of masks(n,h,w) and returns a list of segments(n,xy)

    Args:
        masks (torch.Tensor): the output of the model, which is a tensor of shape (batch_size, 160, 160)
        strategy (str): 'concat' or 'largest'. Defaults to largest

    Returns:
        segments (List): list of segment masks
    """
    segments = []
    for x in masks.int().cpu().numpy().astype("uint8"):
        c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]
        if c:
            if strategy == "concat":  # concatenate all segments
                c = np.concatenate([x.reshape(-1, 2) for x in c])
            elif strategy == "largest":  # select largest segment
                c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2)
        else:
            c = np.zeros((0, 2))  # no segments found
        segments.append(c.astype("float32"))
    return segments



ultralytics.utils.ops.convert_torch2numpy_batch(batch)

将一批 FP32torch 张量(0.0-1.0)转换为 NumPy uint8 数组(0-255),从 BCHW 布局转换为 BHWC 布局。

参数

名称 类型 说明 默认值
batch Tensor

输入tensor 形状批次(批次、通道、高度、宽度)和 dtypetorch.float32。

所需

返回:

类型 说明
ndarray

输出 NumPy 数组批次的形状(批次、高度、宽度、通道)和 dtype uint8。

源代码 ultralytics/utils/ops.py
def convert_torch2numpy_batch(batch: torch.Tensor) -> np.ndarray:
    """
    Convert a batch of FP32 torch tensors (0.0-1.0) to a NumPy uint8 array (0-255), changing from BCHW to BHWC layout.

    Args:
        batch (torch.Tensor): Input tensor batch of shape (Batch, Channels, Height, Width) and dtype torch.float32.

    Returns:
        (np.ndarray): Output NumPy array batch of shape (Batch, Height, Width, Channels) and dtype uint8.
    """
    return (batch.permute(0, 2, 3, 1).contiguous() * 255).clamp(0, 255).to(torch.uint8).cpu().numpy()



ultralytics.utils.ops.clean_str(s)

用下划线 _ 替换特殊字符,清理字符串

参数

名称 类型 说明 默认值
s str

需要替换特殊字符的字符串

所需

返回:

类型 说明
str

用下划线 _ 代替特殊字符的字符串

源代码 ultralytics/utils/ops.py
def clean_str(s):
    """
    Cleans a string by replacing special characters with underscore _

    Args:
        s (str): a string needing special characters replaced

    Returns:
        (str): a string with special characters replaced by an underscore _
    """
    return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)





创建于 2023-11-12,更新于 2024-01-23
作者:Laughing-q(1),glenn-jocher(4)