Algorithm-Repo/SourceCode/MachineLearningUtils/VINNOFramework/YOLO/ultralytics/utils/ops.py

# Ultralytics YOLO 🚀, AGPL-3.0 license

import contextlib
import math
import re
import time

import cv2
import numpy as np
import torch
import torch.nn.functional as F

from ultralytics.utils import LOGGER
from ultralytics.utils.metrics import batch_probiou


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()


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


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)


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


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]

def bbox_iou_for_nms(box1, box2, xywh=False, GIoU=False, DIoU=False, CIoU=False, EIoU=False, SIoU=False, ShapeIoU=False, eps=1e-7, scale=0.0):
    """
    Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4).

    Args:
        box1 (torch.Tensor): A tensor representing a single bounding box with shape (1, 4).
        box2 (torch.Tensor): A tensor representing n bounding boxes with shape (n, 4).
        xywh (bool, optional): If True, input boxes are in (x, y, w, h) format. If False, input boxes are in
                               (x1, y1, x2, y2) format. Defaults to True.
        GIoU (bool, optional): If True, calculate Generalized IoU. Defaults to False.
        DIoU (bool, optional): If True, calculate Distance IoU. Defaults to False.
        CIoU (bool, optional): If True, calculate Complete IoU. Defaults to False.
        EIoU (bool, optional): If True, calculate Efficient IoU. Defaults to False.
        SIoU (bool, optional): If True, calculate Scylla IoU. Defaults to False.
        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

    Returns:
        (torch.Tensor): IoU, GIoU, DIoU, or CIoU values depending on the specified flags.
    """

    # Get the coordinates of bounding boxes
    if xywh:  # transform from xywh to xyxy
        (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1)
        w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2
        b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_
        b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_
    else:  # x1, y1, x2, y2 = box1
        b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, -1)
        b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, -1)
        w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
        w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps

    # Intersection area
    inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp_(0) * \
            (b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1)).clamp_(0)

    # Union Area
    union = w1 * h1 + w2 * h2 - inter + eps

    # IoU
    iou = inter / union
    if CIoU or DIoU or GIoU or EIoU or SIoU or ShapeIoU:
        cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1)  # convex (smallest enclosing box) width
        ch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1)  # convex height
        if CIoU or DIoU or EIoU or SIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
            rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center dist ** 2
            if CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
                v = (4 / math.pi ** 2) * (torch.atan(w2 / h2) - torch.atan(w1 / h1)).pow(2)
                with torch.no_grad():
                    alpha = v / (v - iou + (1 + eps))
                return iou - (rho2 / c2 + v * alpha)  # CIoU
            elif EIoU:
                rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2
                rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2
                cw2 = cw ** 2 + eps
                ch2 = ch ** 2 + eps
                return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2) # EIoU
            elif SIoU:
                # SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
                s_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + eps
                s_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5 + eps
                sigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)
                sin_alpha_1 = torch.abs(s_cw) / sigma
                sin_alpha_2 = torch.abs(s_ch) / sigma
                threshold = pow(2, 0.5) / 2
                sin_alpha = torch.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)
                angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - math.pi / 2)
                rho_x = (s_cw / cw) ** 2
                rho_y = (s_ch / ch) ** 2
                gamma = angle_cost - 2
                distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)
                omiga_w = torch.abs(w1 - w2) / torch.max(w1, w2)
                omiga_h = torch.abs(h1 - h2) / torch.max(h1, h2)
                shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)
                return iou - 0.5 * (distance_cost + shape_cost) + eps # SIoU
            elif ShapeIoU:
                #Shape-Distance    #Shape-Distance    #Shape-Distance    #Shape-Distance    #Shape-Distance    #Shape-Distance    #Shape-Distance  
                ww = 2 * torch.pow(w2, scale) / (torch.pow(w2, scale) + torch.pow(h2, scale))
                hh = 2 * torch.pow(h2, scale) / (torch.pow(w2, scale) + torch.pow(h2, scale))
                cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex width
                ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1)  # convex height
                c2 = cw ** 2 + ch ** 2 + eps                            # convex diagonal squared
                center_distance_x = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2) / 4
                center_distance_y = ((b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4
                center_distance = hh * center_distance_x + ww * center_distance_y
                distance = center_distance / c2

                #Shape-Shape    #Shape-Shape    #Shape-Shape    #Shape-Shape    #Shape-Shape    #Shape-Shape    #Shape-Shape    #Shape-Shape    
                omiga_w = hh * torch.abs(w1 - w2) / torch.max(w1, w2)
                omiga_h = ww * torch.abs(h1 - h2) / torch.max(h1, h2)
                shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)
                return iou - distance - 0.5 * shape_cost
            return iou - rho2 / c2  # DIoU
        c_area = cw * ch + eps  # convex area
        return iou - (c_area - union) / c_area  # GIoU https://arxiv.org/pdf/1902.09630.pdf
    return iou  # IoU

def soft_nms(bboxes, scores, iou_thresh=0.5, sigma=0.5,score_threshold=0.25):
    
    order = torch.arange(0, scores.size(0)).to(bboxes.device)
    keep = []
    
    while order.numel() > 1:
        if order.numel() == 1:
            keep.append(order[0])
            break
        else:
            i = order[0]
            keep.append(i)
        
        iou = bbox_iou_for_nms(bboxes[i:i+1], bboxes[order[1:]], GIoU=False, DIoU=False, CIoU=False, EIoU=False, SIoU=False, ShapeIoU=False, scale=0.0).squeeze()
        
        idx = (iou > iou_thresh).nonzero().squeeze()
        if idx.numel() > 0: 
            iou = iou[idx] 
            newScores = torch.exp(-torch.pow(iou,2)/sigma)
            scores[order[idx+1]] *= newScores
        
        newOrder = (scores[order[1:]] > score_threshold).nonzero().squeeze() 
        if newOrder.numel() == 0: 
            break
        else:
            maxScoreIndex = torch.argmax(scores[order[newOrder+1]]) 
            if maxScoreIndex != 0: 
                newOrder[[0,maxScoreIndex],] = newOrder[[maxScoreIndex,0],]
            order = order[newOrder+1]
    
    return torch.LongTensor(keep)

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.
        rotated (bool): If Oriented Bounding Boxes (OBB) are being passed for NMS.

    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, ...).
    """
    import torchvision  # scope for faster 'import ultralytics'

    # 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
    if classes is not None:
        classes = torch.tensor(classes, device=prediction.device)

    if prediction.shape[-1] == 6:  # end-to-end model (BNC, i.e. 1,300,6)
        output = [pred[pred[:, 4] > conf_thres] for pred in prediction]
        if classes is not None:
            output = [pred[(pred[:, 5:6] == classes).any(1)] for pred in output]
        return output

    bs = prediction.shape[0]  # batch size (BCN, i.e. 1,84,6300)
    nc = nc or (prediction.shape[1] - 4)  # number of classes
    nm = prediction.shape[1] - nc - 4  # number of masks
    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] == classes).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 = soft_nms(boxes, scores, iou_thres) $ Soft-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


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


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


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


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


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. Note: ops per 2 channels faster than per channel.

    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
    xy = x[..., :2]  # centers
    wh = x[..., 2:] / 2  # half width-height
    y[..., :2] = xy - wh  # top left xy
    y[..., 2:] = xy + wh  # bottom right xy
    return y


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


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


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


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


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


def xyxyxyxy2xywhr(x):
    """
    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:
        x (numpy.ndarray | torch.Tensor): Input box corners [xy1, xy2, xy3, xy4] 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(x, torch.Tensor)
    points = x.cpu().numpy() if is_torch else x
    points = points.reshape(len(x), -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.
        (cx, cy), (w, h), angle = cv2.minAreaRect(pts)
        rboxes.append([cx, cy, w, h, angle / 180 * np.pi])
    return torch.tensor(rboxes, device=x.device, dtype=x.dtype) if is_torch else np.asarray(rboxes)


def xywhr2xyxyxyxy(x):
    """
    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:
        x (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).
    """
    cos, sin, cat, stack = (
        (torch.cos, torch.sin, torch.cat, torch.stack)
        if isinstance(x, torch.Tensor)
        else (np.cos, np.sin, np.concatenate, np.stack)
    )

    ctr = x[..., :2]
    w, h, angle = (x[..., 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 = cat(vec1, -1)
    vec2 = cat(vec2, -1)
    pt1 = ctr + vec1 + vec2
    pt2 = ctr + vec1 - vec2
    pt3 = ctr - vec1 - vec2
    pt4 = ctr - vec1 + vec2
    return stack([pt1, pt2, pt3, pt4], -2)


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


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


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


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.
    """
    _, 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))


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)).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_(0.0)


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)).view(-1, mh, mw)  # CHW
    width_ratio = mw / iw
    height_ratio = mh / ih

    downsampled_bboxes = bboxes.clone()
    downsampled_bboxes[:, 0] *= width_ratio
    downsampled_bboxes[:, 2] *= width_ratio
    downsampled_bboxes[:, 3] *= height_ratio
    downsampled_bboxes[:, 1] *= height_ratio

    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_(0.0)


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)).view(-1, mh, mw)
    masks = scale_masks(masks[None], shape)[0]  # CHW
    masks = crop_mask(masks, bboxes)  # CHW
    return masks.gt_(0.0)


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


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


def regularize_rboxes(rboxes):
    """
    Regularize rotated boxes in range [0, pi/2].

    Args:
        rboxes (torch.Tensor): Input boxes of shape(N, 5) in xywhr format.

    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


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


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()


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)