bplusplus 1.1.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

bplusplus/yolov5detect/utils/augmentations.py

@@ -1,448 +0,0 @@
-# Ultralytics YOLOv5 🚀, AGPL-3.0 license
-"""Image augmentation functions."""
-
-import math
-import random
-
-import cv2
-import numpy as np
-import torch
-import torchvision.transforms as T
-import torchvision.transforms.functional as TF
-
-from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box, xywhn2xyxy
-from utils.metrics import bbox_ioa
-
-IMAGENET_MEAN = 0.485, 0.456, 0.406  # RGB mean
-IMAGENET_STD = 0.229, 0.224, 0.225  # RGB standard deviation
-
-
-class Albumentations:
-    """Provides optional data augmentation for YOLOv5 using Albumentations library if installed."""
-
-    def __init__(self, size=640):
-        """Initializes Albumentations class for optional data augmentation in YOLOv5 with specified input size."""
-        self.transform = None
-        prefix = colorstr("albumentations: ")
-        try:
-            import albumentations as A
-
-            check_version(A.__version__, "1.0.3", hard=True)  # version requirement
-
-            T = [
-                A.RandomResizedCrop(height=size, width=size, scale=(0.8, 1.0), ratio=(0.9, 1.11), p=0.0),
-                A.Blur(p=0.01),
-                A.MedianBlur(p=0.01),
-                A.ToGray(p=0.01),
-                A.CLAHE(p=0.01),
-                A.RandomBrightnessContrast(p=0.0),
-                A.RandomGamma(p=0.0),
-                A.ImageCompression(quality_lower=75, p=0.0),
-            ]  # transforms
-            self.transform = A.Compose(T, bbox_params=A.BboxParams(format="yolo", label_fields=["class_labels"]))
-
-            LOGGER.info(prefix + ", ".join(f"{x}".replace("always_apply=False, ", "") for x in T if x.p))
-        except ImportError:  # package not installed, skip
-            pass
-        except Exception as e:
-            LOGGER.info(f"{prefix}{e}")
-
-    def __call__(self, im, labels, p=1.0):
-        """Applies transformations to an image and labels with probability `p`, returning updated image and labels."""
-        if self.transform and random.random() < p:
-            new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0])  # transformed
-            im, labels = new["image"], np.array([[c, *b] for c, b in zip(new["class_labels"], new["bboxes"])])
-        return im, labels
-
-
-def normalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD, inplace=False):
-    """
-    Applies ImageNet normalization to RGB images in BCHW format, modifying them in-place if specified.
-
-    Example: y = (x - mean) / std
-    """
-    return TF.normalize(x, mean, std, inplace=inplace)
-
-
-def denormalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD):
-    """Reverses ImageNet normalization for BCHW format RGB images by applying `x = x * std + mean`."""
-    for i in range(3):
-        x[:, i] = x[:, i] * std[i] + mean[i]
-    return x
-
-
-def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
-    """Applies HSV color-space augmentation to an image with random gains for hue, saturation, and value."""
-    if hgain or sgain or vgain:
-        r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1  # random gains
-        hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
-        dtype = im.dtype  # uint8
-
-        x = np.arange(0, 256, dtype=r.dtype)
-        lut_hue = ((x * r[0]) % 180).astype(dtype)
-        lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
-        lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
-
-        im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
-        cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im)  # no return needed
-
-
-def hist_equalize(im, clahe=True, bgr=False):
-    """Equalizes image histogram, with optional CLAHE, for BGR or RGB image with shape (n,m,3) and range 0-255."""
-    yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
-    if clahe:
-        c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
-        yuv[:, :, 0] = c.apply(yuv[:, :, 0])
-    else:
-        yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0])  # equalize Y channel histogram
-    return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB)  # convert YUV image to RGB
-
-
-def replicate(im, labels):
-    """
-    Replicates half of the smallest object labels in an image for data augmentation.
-
-    Returns augmented image and labels.
-    """
-    h, w = im.shape[:2]
-    boxes = labels[:, 1:].astype(int)
-    x1, y1, x2, y2 = boxes.T
-    s = ((x2 - x1) + (y2 - y1)) / 2  # side length (pixels)
-    for i in s.argsort()[: round(s.size * 0.5)]:  # smallest indices
-        x1b, y1b, x2b, y2b = boxes[i]
-        bh, bw = y2b - y1b, x2b - x1b
-        yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw))  # offset x, y
-        x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
-        im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b]  # im4[ymin:ymax, xmin:xmax]
-        labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
-
-    return im, labels
-
-
-def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
-    """Resizes and pads image to new_shape with stride-multiple constraints, returns resized image, ratio, padding."""
-    shape = im.shape[:2]  # current shape [height, width]
-    if isinstance(new_shape, int):
-        new_shape = (new_shape, new_shape)
-
-    # Scale ratio (new / old)
-    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
-    if not scaleup:  # only scale down, do not scale up (for better val mAP)
-        r = min(r, 1.0)
-
-    # Compute padding
-    ratio = r, r  # width, height ratios
-    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
-    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
-    if auto:  # minimum rectangle
-        dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
-    elif scaleFill:  # stretch
-        dw, dh = 0.0, 0.0
-        new_unpad = (new_shape[1], new_shape[0])
-        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios
-
-    dw /= 2  # divide padding into 2 sides
-    dh /= 2
-
-    if shape[::-1] != new_unpad:  # resize
-        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
-    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
-    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
-    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
-    return im, ratio, (dw, dh)
-
-
-def random_perspective(
-    im, targets=(), segments=(), degrees=10, translate=0.1, scale=0.1, shear=10, perspective=0.0, border=(0, 0)
-):
-    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
-    # targets = [cls, xyxy]
-    """Applies random perspective transformation to an image, modifying the image and corresponding labels."""
-    height = im.shape[0] + border[0] * 2  # shape(h,w,c)
-    width = im.shape[1] + border[1] * 2
-
-    # Center
-    C = np.eye(3)
-    C[0, 2] = -im.shape[1] / 2  # x translation (pixels)
-    C[1, 2] = -im.shape[0] / 2  # y translation (pixels)
-
-    # Perspective
-    P = np.eye(3)
-    P[2, 0] = random.uniform(-perspective, perspective)  # x perspective (about y)
-    P[2, 1] = random.uniform(-perspective, perspective)  # y perspective (about x)
-
-    # Rotation and Scale
-    R = np.eye(3)
-    a = random.uniform(-degrees, degrees)
-    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
-    s = random.uniform(1 - scale, 1 + scale)
-    # s = 2 ** random.uniform(-scale, scale)
-    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
-
-    # Shear
-    S = np.eye(3)
-    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
-    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)
-
-    # Translation
-    T = np.eye(3)
-    T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width  # x translation (pixels)
-    T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height  # y translation (pixels)
-
-    # Combined rotation matrix
-    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
-    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
-        if perspective:
-            im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
-        else:  # affine
-            im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
-
-    # Visualize
-    # import matplotlib.pyplot as plt
-    # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
-    # ax[0].imshow(im[:, :, ::-1])  # base
-    # ax[1].imshow(im2[:, :, ::-1])  # warped
-
-    # Transform label coordinates
-    n = len(targets)
-    if n:
-        use_segments = any(x.any() for x in segments) and len(segments) == n
-        new = np.zeros((n, 4))
-        if use_segments:  # warp segments
-            segments = resample_segments(segments)  # upsample
-            for i, segment in enumerate(segments):
-                xy = np.ones((len(segment), 3))
-                xy[:, :2] = segment
-                xy = xy @ M.T  # transform
-                xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]  # perspective rescale or affine
-
-                # clip
-                new[i] = segment2box(xy, width, height)
-
-        else:  # warp boxes
-            xy = np.ones((n * 4, 3))
-            xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
-            xy = xy @ M.T  # transform
-            xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8)  # perspective rescale or affine
-
-            # create new boxes
-            x = xy[:, [0, 2, 4, 6]]
-            y = xy[:, [1, 3, 5, 7]]
-            new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
-
-            # clip
-            new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
-            new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
-
-        # filter candidates
-        i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
-        targets = targets[i]
-        targets[:, 1:5] = new[i]
-
-    return im, targets
-
-
-def copy_paste(im, labels, segments, p=0.5):
-    """
-    Applies Copy-Paste augmentation by flipping and merging segments and labels on an image.
-
-    Details at https://arxiv.org/abs/2012.07177.
-    """
-    n = len(segments)
-    if p and n:
-        h, w, c = im.shape  # height, width, channels
-        im_new = np.zeros(im.shape, np.uint8)
-        for j in random.sample(range(n), k=round(p * n)):
-            l, s = labels[j], segments[j]
-            box = w - l[3], l[2], w - l[1], l[4]
-            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
-            if (ioa < 0.30).all():  # allow 30% obscuration of existing labels
-                labels = np.concatenate((labels, [[l[0], *box]]), 0)
-                segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
-                cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (1, 1, 1), cv2.FILLED)
-
-        result = cv2.flip(im, 1)  # augment segments (flip left-right)
-        i = cv2.flip(im_new, 1).astype(bool)
-        im[i] = result[i]  # cv2.imwrite('debug.jpg', im)  # debug
-
-    return im, labels, segments
-
-
-def cutout(im, labels, p=0.5):
-    """
-    Applies cutout augmentation to an image with optional label adjustment, using random masks of varying sizes.
-
-    Details at https://arxiv.org/abs/1708.04552.
-    """
-    if random.random() < p:
-        h, w = im.shape[:2]
-        scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16  # image size fraction
-        for s in scales:
-            mask_h = random.randint(1, int(h * s))  # create random masks
-            mask_w = random.randint(1, int(w * s))
-
-            # box
-            xmin = max(0, random.randint(0, w) - mask_w // 2)
-            ymin = max(0, random.randint(0, h) - mask_h // 2)
-            xmax = min(w, xmin + mask_w)
-            ymax = min(h, ymin + mask_h)
-
-            # apply random color mask
-            im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
-
-            # return unobscured labels
-            if len(labels) and s > 0.03:
-                box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
-                ioa = bbox_ioa(box, xywhn2xyxy(labels[:, 1:5], w, h))  # intersection over area
-                labels = labels[ioa < 0.60]  # remove >60% obscured labels
-
-    return labels
-
-
-def mixup(im, labels, im2, labels2):
-    """
-    Applies MixUp augmentation by blending images and labels.
-
-    See https://arxiv.org/pdf/1710.09412.pdf for details.
-    """
-    r = np.random.beta(32.0, 32.0)  # mixup ratio, alpha=beta=32.0
-    im = (im * r + im2 * (1 - r)).astype(np.uint8)
-    labels = np.concatenate((labels, labels2), 0)
-    return im, labels
-
-
-def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16):
-    """
-    Filters bounding box candidates by minimum width-height threshold `wh_thr` (pixels), aspect ratio threshold
-    `ar_thr`, and area ratio threshold `area_thr`.
-
-    box1(4,n) is before augmentation, box2(4,n) is after augmentation.
-    """
-    w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
-    w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
-    ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps))  # aspect ratio
-    return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr)  # candidates
-
-
-def classify_albumentations(
-    augment=True,
-    size=224,
-    scale=(0.08, 1.0),
-    ratio=(0.75, 1.0 / 0.75),  # 0.75, 1.33
-    hflip=0.5,
-    vflip=0.0,
-    jitter=0.4,
-    mean=IMAGENET_MEAN,
-    std=IMAGENET_STD,
-    auto_aug=False,
-):
-    # YOLOv5 classification Albumentations (optional, only used if package is installed)
-    """Sets up and returns Albumentations transforms for YOLOv5 classification tasks depending on augmentation
-    settings.
-    """
-    prefix = colorstr("albumentations: ")
-    try:
-        import albumentations as A
-        from albumentations.pytorch import ToTensorV2
-
-        check_version(A.__version__, "1.0.3", hard=True)  # version requirement
-        if augment:  # Resize and crop
-            T = [A.RandomResizedCrop(height=size, width=size, scale=scale, ratio=ratio)]
-            if auto_aug:
-                # TODO: implement AugMix, AutoAug & RandAug in albumentation
-                LOGGER.info(f"{prefix}auto augmentations are currently not supported")
-            else:
-                if hflip > 0:
-                    T += [A.HorizontalFlip(p=hflip)]
-                if vflip > 0:
-                    T += [A.VerticalFlip(p=vflip)]
-                if jitter > 0:
-                    color_jitter = (float(jitter),) * 3  # repeat value for brightness, contrast, saturation, 0 hue
-                    T += [A.ColorJitter(*color_jitter, 0)]
-        else:  # Use fixed crop for eval set (reproducibility)
-            T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]
-        T += [A.Normalize(mean=mean, std=std), ToTensorV2()]  # Normalize and convert to Tensor
-        LOGGER.info(prefix + ", ".join(f"{x}".replace("always_apply=False, ", "") for x in T if x.p))
-        return A.Compose(T)
-
-    except ImportError:  # package not installed, skip
-        LOGGER.warning(f"{prefix}⚠️ not found, install with `pip install albumentations` (recommended)")
-    except Exception as e:
-        LOGGER.info(f"{prefix}{e}")
-
-
-def classify_transforms(size=224):
-    """Applies a series of transformations including center crop, ToTensor, and normalization for classification."""
-    assert isinstance(size, int), f"ERROR: classify_transforms size {size} must be integer, not (list, tuple)"
-    # T.Compose([T.ToTensor(), T.Resize(size), T.CenterCrop(size), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)])
-    return T.Compose([CenterCrop(size), ToTensor(), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)])
-
-
-class LetterBox:
-    """Resizes and pads images to specified dimensions while maintaining aspect ratio for YOLOv5 preprocessing."""
-
-    def __init__(self, size=(640, 640), auto=False, stride=32):
-        """Initializes a LetterBox object for YOLOv5 image preprocessing with optional auto sizing and stride
-        adjustment.
-        """
-        super().__init__()
-        self.h, self.w = (size, size) if isinstance(size, int) else size
-        self.auto = auto  # pass max size integer, automatically solve for short side using stride
-        self.stride = stride  # used with auto
-
-    def __call__(self, im):
-        """
-        Resizes and pads input image `im` (HWC format) to specified dimensions, maintaining aspect ratio.
-
-        im = np.array HWC
-        """
-        imh, imw = im.shape[:2]
-        r = min(self.h / imh, self.w / imw)  # ratio of new/old
-        h, w = round(imh * r), round(imw * r)  # resized image
-        hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else self.h, self.w
-        top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1)
-        im_out = np.full((self.h, self.w, 3), 114, dtype=im.dtype)
-        im_out[top : top + h, left : left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
-        return im_out
-
-
-class CenterCrop:
-    """Applies center crop to an image, resizing it to the specified size while maintaining aspect ratio."""
-
-    def __init__(self, size=640):
-        """Initializes CenterCrop for image preprocessing, accepting single int or tuple for size, defaults to 640."""
-        super().__init__()
-        self.h, self.w = (size, size) if isinstance(size, int) else size
-
-    def __call__(self, im):
-        """
-        Applies center crop to the input image and resizes it to a specified size, maintaining aspect ratio.
-
-        im = np.array HWC
-        """
-        imh, imw = im.shape[:2]
-        m = min(imh, imw)  # min dimension
-        top, left = (imh - m) // 2, (imw - m) // 2
-        return cv2.resize(im[top : top + m, left : left + m], (self.w, self.h), interpolation=cv2.INTER_LINEAR)
-
-
-class ToTensor:
-    """Converts BGR np.array image from HWC to RGB CHW format, normalizes to [0, 1], and supports FP16 if half=True."""
-
-    def __init__(self, half=False):
-        """Initializes ToTensor for YOLOv5 image preprocessing, with optional half precision (half=True for FP16)."""
-        super().__init__()
-        self.half = half
-
-    def __call__(self, im):
-        """
-        Converts BGR np.array image from HWC to RGB CHW format, and normalizes to [0, 1], with support for FP16 if
-        `half=True`.
-
-        im = np.array HWC in BGR order
-        """
-        im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1])  # HWC to CHW -> BGR to RGB -> contiguous
-        im = torch.from_numpy(im)  # to torch
-        im = im.half() if self.half else im.float()  # uint8 to fp16/32
-        im /= 255.0  # 0-255 to 0.0-1.0
-        return im

bplusplus/yolov5detect/utils/autoanchor.py

@@ -1,175 +0,0 @@
-# Ultralytics YOLOv5 🚀, AGPL-3.0 license
-"""AutoAnchor utils."""
-
-import random
-
-import numpy as np
-import torch
-import yaml
-from tqdm import tqdm
-
-from utils import TryExcept
-from utils.general import LOGGER, TQDM_BAR_FORMAT, colorstr
-
-PREFIX = colorstr("AutoAnchor: ")
-
-
-def check_anchor_order(m):
-    """Checks and corrects anchor order against stride in YOLOv5 Detect() module if necessary."""
-    a = m.anchors.prod(-1).mean(-1).view(-1)  # mean anchor area per output layer
-    da = a[-1] - a[0]  # delta a
-    ds = m.stride[-1] - m.stride[0]  # delta s
-    if da and (da.sign() != ds.sign()):  # same order
-        LOGGER.info(f"{PREFIX}Reversing anchor order")
-        m.anchors[:] = m.anchors.flip(0)
-
-
-@TryExcept(f"{PREFIX}ERROR")
-def check_anchors(dataset, model, thr=4.0, imgsz=640):
-    """Evaluates anchor fit to dataset and adjusts if necessary, supporting customizable threshold and image size."""
-    m = model.module.model[-1] if hasattr(model, "module") else model.model[-1]  # Detect()
-    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
-    scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1))  # augment scale
-    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float()  # wh
-
-    def metric(k):  # compute metric
-        """Computes ratio metric, anchors above threshold, and best possible recall for YOLOv5 anchor evaluation."""
-        r = wh[:, None] / k[None]
-        x = torch.min(r, 1 / r).min(2)[0]  # ratio metric
-        best = x.max(1)[0]  # best_x
-        aat = (x > 1 / thr).float().sum(1).mean()  # anchors above threshold
-        bpr = (best > 1 / thr).float().mean()  # best possible recall
-        return bpr, aat
-
-    stride = m.stride.to(m.anchors.device).view(-1, 1, 1)  # model strides
-    anchors = m.anchors.clone() * stride  # current anchors
-    bpr, aat = metric(anchors.cpu().view(-1, 2))
-    s = f"\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). "
-    if bpr > 0.98:  # threshold to recompute
-        LOGGER.info(f"{s}Current anchors are a good fit to dataset ✅")
-    else:
-        LOGGER.info(f"{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...")
-        na = m.anchors.numel() // 2  # number of anchors
-        anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
-        new_bpr = metric(anchors)[0]
-        if new_bpr > bpr:  # replace anchors
-            anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
-            m.anchors[:] = anchors.clone().view_as(m.anchors)
-            check_anchor_order(m)  # must be in pixel-space (not grid-space)
-            m.anchors /= stride
-            s = f"{PREFIX}Done ✅ (optional: update model *.yaml to use these anchors in the future)"
-        else:
-            s = f"{PREFIX}Done ⚠️ (original anchors better than new anchors, proceeding with original anchors)"
-        LOGGER.info(s)
-
-
-def kmean_anchors(dataset="./data/coco128.yaml", n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
-    """
-    Creates kmeans-evolved anchors from training dataset.
-
-    Arguments:
-        dataset: path to data.yaml, or a loaded dataset
-        n: number of anchors
-        img_size: image size used for training
-        thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
-        gen: generations to evolve anchors using genetic algorithm
-        verbose: print all results
-
-    Return:
-        k: kmeans evolved anchors
-
-    Usage:
-        from utils.autoanchor import *; _ = kmean_anchors()
-    """
-    from scipy.cluster.vq import kmeans
-
-    npr = np.random
-    thr = 1 / thr
-
-    def metric(k, wh):  # compute metrics
-        """Computes ratio metric, anchors above threshold, and best possible recall for YOLOv5 anchor evaluation."""
-        r = wh[:, None] / k[None]
-        x = torch.min(r, 1 / r).min(2)[0]  # ratio metric
-        # x = wh_iou(wh, torch.tensor(k))  # iou metric
-        return x, x.max(1)[0]  # x, best_x
-
-    def anchor_fitness(k):  # mutation fitness
-        """Evaluates fitness of YOLOv5 anchors by computing recall and ratio metrics for an anchor evolution process."""
-        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
-        return (best * (best > thr).float()).mean()  # fitness
-
-    def print_results(k, verbose=True):
-        """Sorts and logs kmeans-evolved anchor metrics and best possible recall values for YOLOv5 anchor evaluation."""
-        k = k[np.argsort(k.prod(1))]  # sort small to large
-        x, best = metric(k, wh0)
-        bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n  # best possible recall, anch > thr
-        s = (
-            f"{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n"
-            f"{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, "
-            f"past_thr={x[x > thr].mean():.3f}-mean: "
-        )
-        for x in k:
-            s += "%i,%i, " % (round(x[0]), round(x[1]))
-        if verbose:
-            LOGGER.info(s[:-2])
-        return k
-
-    if isinstance(dataset, str):  # *.yaml file
-        with open(dataset, errors="ignore") as f:
-            data_dict = yaml.safe_load(f)  # model dict
-        from utils.dataloaders import LoadImagesAndLabels
-
-        dataset = LoadImagesAndLabels(data_dict["train"], augment=True, rect=True)
-
-    # Get label wh
-    shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
-    wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])  # wh
-
-    # Filter
-    i = (wh0 < 3.0).any(1).sum()
-    if i:
-        LOGGER.info(f"{PREFIX}WARNING ⚠️ Extremely small objects found: {i} of {len(wh0)} labels are <3 pixels in size")
-    wh = wh0[(wh0 >= 2.0).any(1)].astype(np.float32)  # filter > 2 pixels
-    # wh = wh * (npr.rand(wh.shape[0], 1) * 0.9 + 0.1)  # multiply by random scale 0-1
-
-    # Kmeans init
-    try:
-        LOGGER.info(f"{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...")
-        assert n <= len(wh)  # apply overdetermined constraint
-        s = wh.std(0)  # sigmas for whitening
-        k = kmeans(wh / s, n, iter=30)[0] * s  # points
-        assert n == len(k)  # kmeans may return fewer points than requested if wh is insufficient or too similar
-    except Exception:
-        LOGGER.warning(f"{PREFIX}WARNING ⚠️ switching strategies from kmeans to random init")
-        k = np.sort(npr.rand(n * 2)).reshape(n, 2) * img_size  # random init
-    wh, wh0 = (torch.tensor(x, dtype=torch.float32) for x in (wh, wh0))
-    k = print_results(k, verbose=False)
-
-    # Plot
-    # k, d = [None] * 20, [None] * 20
-    # for i in tqdm(range(1, 21)):
-    #     k[i-1], d[i-1] = kmeans(wh / s, i)  # points, mean distance
-    # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
-    # ax = ax.ravel()
-    # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
-    # fig, ax = plt.subplots(1, 2, figsize=(14, 7))  # plot wh
-    # ax[0].hist(wh[wh[:, 0]<100, 0],400)
-    # ax[1].hist(wh[wh[:, 1]<100, 1],400)
-    # fig.savefig('wh.png', dpi=200)
-
-    # Evolve
-    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
-    pbar = tqdm(range(gen), bar_format=TQDM_BAR_FORMAT)  # progress bar
-    for _ in pbar:
-        v = np.ones(sh)
-        while (v == 1).all():  # mutate until a change occurs (prevent duplicates)
-            v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
-        kg = (k.copy() * v).clip(min=2.0)
-        fg = anchor_fitness(kg)
-        if fg > f:
-            f, k = fg, kg.copy()
-            pbar.desc = f"{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}"
-            if verbose:
-                print_results(k, verbose)
-
-    return print_results(k).astype(np.float32)