# anchors
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

parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')

def check_anchors(dataset, model, thr=4.0, imgsz=640):
  # Check anchor fit to data, recompute if necessary
  print('\nAnalyzing anchors... ', end='')
  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
      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

  bpr, aat = metric(m.anchor_grid.clone().cpu().view(-1, 2))
  print('anchors/target = %.2f, Best Possible Recall (BPR) = %.4f' % (aat, bpr), end='')
  if bpr < 0.98:  # threshold to recompute
      print('. Attempting to generate improved anchors, please wait...' % bpr)
      na = m.anchor_grid.numel() // 2  # number of anchors
      new_anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
      new_bpr = metric(new_anchors.reshape(-1, 2))[0]
      if new_bpr > bpr:  # replace anchors
          new_anchors = torch.tensor(new_anchors, device=m.anchors.device).type_as(m.anchors)
          m.anchor_grid[:] = new_anchors.clone().view_as(m.anchor_grid)  # for inference
          m.anchors[:] = new_anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1)  # loss
          check_anchor_order(m)
          print('New anchors saved to model. Update model *.yaml to use these anchors in the future.')
      else:
          print('Original anchors better than new anchors. Proceeding with original anchors.')
  print('')  # newline

def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
  """ Creates kmeans-evolved anchors from training dataset

      Arguments:
          path: path to dataset *.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

      Return:
          k: kmeans evolved anchors

      Usage:
          from utils.general import *; _ = kmean_anchors()
  """
  thr = 1. / thr

  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 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('thr=%.2f: %.4f best possible recall, %.2f anchors past thr' % (thr, bpr, aat))
      print('n=%g, img_size=%s, metric_all=%.3f/%.3f-mean/best, past_thr=%.3f-mean: ' %
            (n, img_size, x.mean(), best.mean(), x[x > thr].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(path, str):  # *.yaml file
      with open(path) as f:
          data_dict = yaml.load(f, Loader=yaml.FullLoader)  # model dict
      from utils.datasets import LoadImagesAndLabels
      dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
  else:
      dataset = path  # dataset

  # 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('WARNING: Extremely small objects found. '
            '%g of %g labels are < 3 pixels in width or height.' % (i, len(wh0)))
  wh = wh0[(wh0 >= 2.0).any(1)]  # filter > 2 pixels

  # Kmeans calculation
  print('Running kmeans for %g anchors on %g points...' % (n, len(wh)))
  s = wh.std(0)  # sigmas for whitening
  k, dist = kmeans(wh / s, n, iter=30)  # points, mean distance
  k *= s
  wh = torch.tensor(wh, dtype=torch.float32)  # filtered
  wh0 = torch.tensor(wh0, dtype=torch.float32)  # unflitered
  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))
  # 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.tight_layout()
  # fig.savefig('wh.png', dpi=200)

  # Evolve
  npr = np.random
  f, sh, mp, s = fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
  pbar = tqdm(range(gen), desc='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) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
      kg = (k.copy() * v).clip(min=2.0)
      fg = fitness(kg)
      if fg > f:
          f, k = fg, kg.copy()
          pbar.desc = 'Evolving anchors with Genetic Algorithm: fitness = %.4f' % f
          if verbose:
              print_results(k)

  return print_results(k)

python train_people.py