anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

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

    thr = 1. / thr
    prefix = colorstr('autoanchor: ')

    def metric(k, wh):  # compute metrics
        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
        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
        return (best * (best > thr).float()).mean()  # fitness

    def print_results(k):
        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
        print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
        print(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: ', end='')
        for i, x in enumerate(k):
            print('%i,%i' % (round(x[0]), round(x[1])), end=',  ' if i < len(k) - 1 else '\n')  # use in *.cfg
        return k

    if isinstance(dataset, str):  # *.yaml file
        with open(dataset, errors='ignore') as f:
            data_dict = yaml.safe_load(f)  # model dict
        from datasets 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:
        print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
    wh = wh0[(wh0 >= 2.0).any(1)]  # filter > 2 pixels
    # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1)  # multiply by random scale 0-1

    # Kmeans calculation
    print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
    s = wh.std(0)  # sigmas for whitening
    k, dist = kmeans(wh / s, n, iter=30)  # points, mean distance
    assert len(k) == n, f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}'
    k *= s
    wh = torch.tensor(wh, dtype=torch.float32)  # filtered
    wh0 = torch.tensor(wh0, dtype=torch.float32)  # unfiltered
    k = print_results(k)

    # 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
    npr = np.random
    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
    pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:')  # 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)

    return print_results(k)

Arguments:
          dataset: 數據的yaml路徑
          n: 類簇的個數
          img_size: 訓練過程中的圖片尺寸（32的倍數）
          thr: anchor的長寬比閾值，將長寬比限制在此閾值之內
          gen: k-means算法最大迭代次數（不理解的可以去看k-means算法）
          verbose: 打印參數

Usage:
          from utils.autoanchor import *; _ = kmean_anchors()