ultralytics 8.1.28__py3-none-any.whl → 8.3.62__py3-none-any.whl

ultralytics/utils/loss.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 import torch
 import torch.nn as nn
@@ -7,6 +7,8 @@ import torch.nn.functional as F
 from ultralytics.utils.metrics import OKS_SIGMA
 from ultralytics.utils.ops import crop_mask, xywh2xyxy, xyxy2xywh
 from ultralytics.utils.tal import RotatedTaskAlignedAssigner, TaskAlignedAssigner, dist2bbox, dist2rbox, make_anchors
+from ultralytics.utils.torch_utils import autocast
+
 from .metrics import bbox_iou, probiou
 from .tal import bbox2dist
 
@@ -26,7 +28,7 @@ class VarifocalLoss(nn.Module):
     def forward(pred_score, gt_score, label, alpha=0.75, gamma=2.0):
         """Computes varfocal loss."""
         weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label
-        with torch.cuda.amp.autocast(enabled=False):
+        with autocast(enabled=False):
             loss = (
                 (F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(), reduction="none") * weight)
                 .mean(1)
@@ -60,39 +62,22 @@ class FocalLoss(nn.Module):
         return loss.mean(1).sum()
 
 
-class BboxLoss(nn.Module):
-    """Criterion class for computing training losses during training."""
+class DFLoss(nn.Module):
+    """Criterion class for computing DFL losses during training."""
 
-    def __init__(self, reg_max, use_dfl=False):
-        """Initialize the BboxLoss module with regularization maximum and DFL settings."""
+    def __init__(self, reg_max=16) -> None:
+        """Initialize the DFL module."""
         super().__init__()
         self.reg_max = reg_max
-        self.use_dfl = use_dfl
-
-    def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
-        """IoU loss."""
-        weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
-        iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True)
-        loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
 
-        # DFL loss
-        if self.use_dfl:
-            target_ltrb = bbox2dist(anchor_points, target_bboxes, self.reg_max)
-            loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
-            loss_dfl = loss_dfl.sum() / target_scores_sum
-        else:
-            loss_dfl = torch.tensor(0.0).to(pred_dist.device)
-
-        return loss_iou, loss_dfl
-
-    @staticmethod
-    def _df_loss(pred_dist, target):
+    def __call__(self, pred_dist, target):
         """
         Return sum of left and right DFL losses.
 
         Distribution Focal Loss (DFL) proposed in Generalized Focal Loss
         https://ieeexplore.ieee.org/document/9792391
         """
+        target = target.clamp_(0, self.reg_max - 1 - 0.01)
         tl = target.long()  # target left
         tr = tl + 1  # target right
         wl = tr - target  # weight left
@@ -103,12 +88,37 @@ class BboxLoss(nn.Module):
         ).mean(-1, keepdim=True)
 
 
+class BboxLoss(nn.Module):
+    """Criterion class for computing training losses during training."""
+
+    def __init__(self, reg_max=16):
+        """Initialize the BboxLoss module with regularization maximum and DFL settings."""
+        super().__init__()
+        self.dfl_loss = DFLoss(reg_max) if reg_max > 1 else None
+
+    def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
+        """IoU loss."""
+        weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
+        iou = bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, CIoU=True)
+        loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
+
+        # DFL loss
+        if self.dfl_loss:
+            target_ltrb = bbox2dist(anchor_points, target_bboxes, self.dfl_loss.reg_max - 1)
+            loss_dfl = self.dfl_loss(pred_dist[fg_mask].view(-1, self.dfl_loss.reg_max), target_ltrb[fg_mask]) * weight
+            loss_dfl = loss_dfl.sum() / target_scores_sum
+        else:
+            loss_dfl = torch.tensor(0.0).to(pred_dist.device)
+
+        return loss_iou, loss_dfl
+
+
 class RotatedBboxLoss(BboxLoss):
     """Criterion class for computing training losses during training."""
 
-    def __init__(self, reg_max, use_dfl=False):
+    def __init__(self, reg_max):
         """Initialize the BboxLoss module with regularization maximum and DFL settings."""
-        super().__init__(reg_max, use_dfl)
+        super().__init__(reg_max)
 
     def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
         """IoU loss."""
@@ -117,9 +127,9 @@ class RotatedBboxLoss(BboxLoss):
         loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
 
         # DFL loss
-        if self.use_dfl:
-            target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.reg_max)
-            loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
+        if self.dfl_loss:
+            target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.dfl_loss.reg_max - 1)
+            loss_dfl = self.dfl_loss(pred_dist[fg_mask].view(-1, self.dfl_loss.reg_max), target_ltrb[fg_mask]) * weight
             loss_dfl = loss_dfl.sum() / target_scores_sum
         else:
             loss_dfl = torch.tensor(0.0).to(pred_dist.device)
@@ -140,14 +150,14 @@ class KeypointLoss(nn.Module):
         d = (pred_kpts[..., 0] - gt_kpts[..., 0]).pow(2) + (pred_kpts[..., 1] - gt_kpts[..., 1]).pow(2)
         kpt_loss_factor = kpt_mask.shape[1] / (torch.sum(kpt_mask != 0, dim=1) + 1e-9)
         # e = d / (2 * (area * self.sigmas) ** 2 + 1e-9)  # from formula
-        e = d / (2 * self.sigmas).pow(2) / (area + 1e-9) / 2  # from cocoeval
+        e = d / ((2 * self.sigmas).pow(2) * (area + 1e-9) * 2)  # from cocoeval
         return (kpt_loss_factor.view(-1, 1) * ((1 - torch.exp(-e)) * kpt_mask)).mean()
 
 
 class v8DetectionLoss:
     """Criterion class for computing training losses."""
 
-    def __init__(self, model):  # model must be de-paralleled
+    def __init__(self, model, tal_topk=10):  # model must be de-paralleled
         """Initializes v8DetectionLoss with the model, defining model-related properties and BCE loss function."""
         device = next(model.parameters()).device  # get model device
         h = model.args  # hyperparameters
@@ -157,29 +167,29 @@ class v8DetectionLoss:
         self.hyp = h
         self.stride = m.stride  # model strides
         self.nc = m.nc  # number of classes
-        self.no = m.no
+        self.no = m.nc + m.reg_max * 4
         self.reg_max = m.reg_max
         self.device = device
 
         self.use_dfl = m.reg_max > 1
 
-        self.assigner = TaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
-        self.bbox_loss = BboxLoss(m.reg_max - 1, use_dfl=self.use_dfl).to(device)
+        self.assigner = TaskAlignedAssigner(topk=tal_topk, num_classes=self.nc, alpha=0.5, beta=6.0)
+        self.bbox_loss = BboxLoss(m.reg_max).to(device)
         self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device)
 
     def preprocess(self, targets, batch_size, scale_tensor):
         """Preprocesses the target counts and matches with the input batch size to output a tensor."""
-        if targets.shape[0] == 0:
-            out = torch.zeros(batch_size, 0, 5, device=self.device)
+        nl, ne = targets.shape
+        if nl == 0:
+            out = torch.zeros(batch_size, 0, ne - 1, device=self.device)
         else:
             i = targets[:, 0]  # image index
             _, counts = i.unique(return_counts=True)
             counts = counts.to(dtype=torch.int32)
-            out = torch.zeros(batch_size, counts.max(), 5, device=self.device)
+            out = torch.zeros(batch_size, counts.max(), ne - 1, device=self.device)
             for j in range(batch_size):
                 matches = i == j
-                n = matches.sum()
-                if n:
+                if n := matches.sum():
                     out[j, :n] = targets[matches, 1:]
             out[..., 1:5] = xywh2xyxy(out[..., 1:5].mul_(scale_tensor))
         return out
@@ -213,12 +223,15 @@ class v8DetectionLoss:
         targets = torch.cat((batch["batch_idx"].view(-1, 1), batch["cls"].view(-1, 1), batch["bboxes"]), 1)
         targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
         gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
-        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
+        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
 
         # Pboxes
         pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)
+        # dfl_conf = pred_distri.view(batch_size, -1, 4, self.reg_max).detach().softmax(-1)
+        # dfl_conf = (dfl_conf.amax(-1).mean(-1) + dfl_conf.amax(-1).amin(-1)) / 2
 
         _, target_bboxes, target_scores, fg_mask, _ = self.assigner(
+            # pred_scores.detach().sigmoid() * 0.8 + dfl_conf.unsqueeze(-1) * 0.2,
             pred_scores.detach().sigmoid(),
             (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
             anchor_points * stride_tensor,
@@ -279,7 +292,7 @@ class v8SegmentationLoss(v8DetectionLoss):
             targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
             targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
             gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
-            mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
+            mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
         except RuntimeError as e:
             raise TypeError(
                 "ERROR ❌ segment dataset incorrectly formatted or not a segment dataset.\n"
@@ -466,7 +479,7 @@ class v8PoseLoss(v8DetectionLoss):
         targets = torch.cat((batch_idx, batch["cls"].view(-1, 1), batch["bboxes"]), 1)
         targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
         gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
-        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
+        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
 
         # Pboxes
         pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)
@@ -538,9 +551,8 @@ class v8PoseLoss(v8DetectionLoss):
             pred_kpts (torch.Tensor): Predicted keypoints, shape (BS, N_anchors, N_kpts_per_object, kpts_dim).
 
         Returns:
-            (tuple): Returns a tuple containing:
-                - kpts_loss (torch.Tensor): The keypoints loss.
-                - kpts_obj_loss (torch.Tensor): The keypoints object loss.
+            kpts_loss (torch.Tensor): The keypoints loss.
+            kpts_obj_loss (torch.Tensor): The keypoints object loss.
         """
         batch_idx = batch_idx.flatten()
         batch_size = len(masks)
@@ -591,21 +603,20 @@ class v8ClassificationLoss:
 
     def __call__(self, preds, batch):
         """Compute the classification loss between predictions and true labels."""
-        loss = torch.nn.functional.cross_entropy(preds, batch["cls"], reduction="mean")
+        preds = preds[1] if isinstance(preds, (list, tuple)) else preds
+        loss = F.cross_entropy(preds, batch["cls"], reduction="mean")
         loss_items = loss.detach()
         return loss, loss_items
 
 
 class v8OBBLoss(v8DetectionLoss):
-    def __init__(self, model):
-        """
-        Initializes v8OBBLoss with model, assigner, and rotated bbox loss.
+    """Calculates losses for object detection, classification, and box distribution in rotated YOLO models."""
 
-        Note model must be de-paralleled.
-        """
+    def __init__(self, model):
+        """Initializes v8OBBLoss with model, assigner, and rotated bbox loss; note model must be de-paralleled."""
         super().__init__(model)
         self.assigner = RotatedTaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
-        self.bbox_loss = RotatedBboxLoss(self.reg_max - 1, use_dfl=self.use_dfl).to(self.device)
+        self.bbox_loss = RotatedBboxLoss(self.reg_max).to(self.device)
 
     def preprocess(self, targets, batch_size, scale_tensor):
         """Preprocesses the target counts and matches with the input batch size to output a tensor."""
@@ -618,8 +629,7 @@ class v8OBBLoss(v8DetectionLoss):
             out = torch.zeros(batch_size, counts.max(), 6, device=self.device)
             for j in range(batch_size):
                 matches = i == j
-                n = matches.sum()
-                if n:
+                if n := matches.sum():
                     bboxes = targets[matches, 2:]
                     bboxes[..., :4].mul_(scale_tensor)
                     out[j, :n] = torch.cat([targets[matches, 1:2], bboxes], dim=-1)
@@ -651,7 +661,7 @@ class v8OBBLoss(v8DetectionLoss):
             targets = targets[(rw >= 2) & (rh >= 2)]  # filter rboxes of tiny size to stabilize training
             targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
             gt_labels, gt_bboxes = targets.split((1, 5), 2)  # cls, xywhr
-            mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
+            mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0.0)
         except RuntimeError as e:
             raise TypeError(
                 "ERROR ❌ OBB dataset incorrectly formatted or not a OBB dataset.\n"
@@ -713,3 +723,21 @@ class v8OBBLoss(v8DetectionLoss):
             b, a, c = pred_dist.shape  # batch, anchors, channels
             pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
         return torch.cat((dist2rbox(pred_dist, pred_angle, anchor_points), pred_angle), dim=-1)
+
+
+class E2EDetectLoss:
+    """Criterion class for computing training losses."""
+
+    def __init__(self, model):
+        """Initialize E2EDetectLoss with one-to-many and one-to-one detection losses using the provided model."""
+        self.one2many = v8DetectionLoss(model, tal_topk=10)
+        self.one2one = v8DetectionLoss(model, tal_topk=1)
+
+    def __call__(self, preds, batch):
+        """Calculate the sum of the loss for box, cls and dfl multiplied by batch size."""
+        preds = preds[1] if isinstance(preds, tuple) else preds
+        one2many = preds["one2many"]
+        loss_one2many = self.one2many(one2many, batch)
+        one2one = preds["one2one"]
+        loss_one2one = self.one2one(one2one, batch)
+        return loss_one2many[0] + loss_one2one[0], loss_one2many[1] + loss_one2one[1]

ultralytics/utils/metrics.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 """Model validation metrics."""
 
 import math
@@ -30,7 +30,6 @@ def bbox_ioa(box1, box2, iou=False, eps=1e-7):
     Returns:
         (np.ndarray): A numpy array of shape (n, m) representing the intersection over box2 area.
     """
-
     # Get the coordinates of bounding boxes
     b1_x1, b1_y1, b1_x2, b1_y2 = box1.T
     b2_x1, b2_y1, b2_x2, b2_y2 = box2.T
@@ -53,7 +52,7 @@ def bbox_ioa(box1, box2, iou=False, eps=1e-7):
 def box_iou(box1, box2, eps=1e-7):
     """
     Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
-    Based on https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
+    Based on https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py.
 
     Args:
         box1 (torch.Tensor): A tensor of shape (N, 4) representing N bounding boxes.
@@ -63,9 +62,9 @@ def box_iou(box1, box2, eps=1e-7):
     Returns:
         (torch.Tensor): An NxM tensor containing the pairwise IoU values for every element in box1 and box2.
     """
-
+    # NOTE: Need .float() to get accurate iou values
     # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
-    (a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2)
+    (a1, a2), (b1, b2) = box1.float().unsqueeze(1).chunk(2, 2), box2.float().unsqueeze(0).chunk(2, 2)
     inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp_(0).prod(2)
 
     # IoU = inter / (area1 + area2 - inter)
@@ -74,11 +73,16 @@ def box_iou(box1, box2, eps=1e-7):
 
 def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
     """
-    Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4).
+    Calculates the Intersection over Union (IoU) between bounding boxes.
+
+    This function supports various shapes for `box1` and `box2` as long as the last dimension is 4.
+    For instance, you may pass tensors shaped like (4,), (N, 4), (B, N, 4), or (B, N, 1, 4).
+    Internally, the code will split the last dimension into (x, y, w, h) if `xywh=True`,
+    or (x1, y1, x2, y2) if `xywh=False`.
 
     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).
+        box1 (torch.Tensor): A tensor representing one or more bounding boxes, with the last dimension being 4.
+        box2 (torch.Tensor): A tensor representing one or more bounding boxes, with the last dimension being 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.
@@ -89,7 +93,6 @@ def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=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)
@@ -167,7 +170,7 @@ def kpt_iou(kpt1, kpt2, area, sigma, eps=1e-7):
     d = (kpt1[:, None, :, 0] - kpt2[..., 0]).pow(2) + (kpt1[:, None, :, 1] - kpt2[..., 1]).pow(2)  # (N, M, 17)
     sigma = torch.tensor(sigma, device=kpt1.device, dtype=kpt1.dtype)  # (17, )
     kpt_mask = kpt1[..., 2] != 0  # (N, 17)
-    e = d / (2 * sigma).pow(2) / (area[:, None, None] + eps) / 2  # from cocoeval
+    e = d / ((2 * sigma).pow(2) * (area[:, None, None] + eps) * 2)  # from cocoeval
     # e = d / ((area[None, :, None] + eps) * sigma) ** 2 / 2  # from formula
     return ((-e).exp() * kpt_mask[:, None]).sum(-1) / (kpt_mask.sum(-1)[:, None] + eps)
 
@@ -180,7 +183,7 @@ def _get_covariance_matrix(boxes):
         boxes (torch.Tensor): A tensor of shape (N, 5) representing rotated bounding boxes, with xywhr format.
 
     Returns:
-        (torch.Tensor): Covariance metrixs corresponding to original rotated bounding boxes.
+        (torch.Tensor): Covariance matrices corresponding to original rotated bounding boxes.
     """
     # Gaussian bounding boxes, ignore the center points (the first two columns) because they are not needed here.
     gbbs = torch.cat((boxes[:, 2:4].pow(2) / 12, boxes[:, 4:]), dim=-1)
@@ -194,15 +197,22 @@ def _get_covariance_matrix(boxes):
 
 def probiou(obb1, obb2, CIoU=False, eps=1e-7):
     """
-    Calculate the prob IoU between oriented bounding boxes, https://arxiv.org/pdf/2106.06072v1.pdf.
+    Calculate probabilistic IoU between oriented bounding boxes.
+
+    Implements the algorithm from https://arxiv.org/pdf/2106.06072v1.pdf.
 
     Args:
-        obb1 (torch.Tensor): A tensor of shape (N, 5) representing ground truth obbs, with xywhr format.
-        obb2 (torch.Tensor): A tensor of shape (N, 5) representing predicted obbs, with xywhr format.
-        eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.
+        obb1 (torch.Tensor): Ground truth OBBs, shape (N, 5), format xywhr.
+        obb2 (torch.Tensor): Predicted OBBs, shape (N, 5), format xywhr.
+        CIoU (bool, optional): If True, calculate CIoU. Defaults to False.
+        eps (float, optional): Small value to avoid division by zero. Defaults to 1e-7.
 
     Returns:
-        (torch.Tensor): A tensor of shape (N, ) representing obb similarities.
+        (torch.Tensor): OBB similarities, shape (N,).
+
+    Note:
+        OBB format: [center_x, center_y, width, height, rotation_angle].
+        If CIoU is True, returns CIoU instead of IoU.
     """
     x1, y1 = obb1[..., :2].split(1, dim=-1)
     x2, y2 = obb2[..., :2].split(1, dim=-1)
@@ -265,7 +275,7 @@ def batch_probiou(obb1, obb2, eps=1e-7):
     return 1 - hd
 
 
-def smooth_BCE(eps=0.1):
+def smooth_bce(eps=0.1):
     """
     Computes smoothed positive and negative Binary Cross-Entropy targets.
 
@@ -298,7 +308,7 @@ class ConfusionMatrix:
         self.task = task
         self.matrix = np.zeros((nc + 1, nc + 1)) if self.task == "detect" else np.zeros((nc, nc))
         self.nc = nc  # number of classes
-        self.conf = 0.25 if conf in (None, 0.001) else conf  # apply 0.25 if default val conf is passed
+        self.conf = 0.25 if conf in {None, 0.001} else conf  # apply 0.25 if default val conf is passed
         self.iou_thres = iou_thres
 
     def process_cls_preds(self, preds, targets):
@@ -367,10 +377,9 @@ class ConfusionMatrix:
             else:
                 self.matrix[self.nc, gc] += 1  # true background
 
-        if n:
-            for i, dc in enumerate(detection_classes):
-                if not any(m1 == i):
-                    self.matrix[dc, self.nc] += 1  # predicted background
+        for i, dc in enumerate(detection_classes):
+            if not any(m1 == i):
+                self.matrix[dc, self.nc] += 1  # predicted background
 
     def matrix(self):
         """Returns the confusion matrix."""
@@ -395,19 +404,19 @@ class ConfusionMatrix:
             names (tuple): Names of classes, used as labels on the plot.
             on_plot (func): An optional callback to pass plots path and data when they are rendered.
         """
-        import seaborn as sn
+        import seaborn  # scope for faster 'import ultralytics'
 
         array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1e-9) if normalize else 1)  # normalize columns
         array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)
 
         fig, ax = plt.subplots(1, 1, figsize=(12, 9), tight_layout=True)
         nc, nn = self.nc, len(names)  # number of classes, names
-        sn.set(font_scale=1.0 if nc < 50 else 0.8)  # for label size
+        seaborn.set_theme(font_scale=1.0 if nc < 50 else 0.8)  # for label size
         labels = (0 < nn < 99) and (nn == nc)  # apply names to ticklabels
         ticklabels = (list(names) + ["background"]) if labels else "auto"
         with warnings.catch_warnings():
             warnings.simplefilter("ignore")  # suppress empty matrix RuntimeWarning: All-NaN slice encountered
-            sn.heatmap(
+            seaborn.heatmap(
                 array,
                 ax=ax,
                 annot=nc < 30,
@@ -423,7 +432,7 @@ class ConfusionMatrix:
         ax.set_xlabel("True")
         ax.set_ylabel("Predicted")
         ax.set_title(title)
-        plot_fname = Path(save_dir) / f'{title.lower().replace(" ", "_")}.png'
+        plot_fname = Path(save_dir) / f"{title.lower().replace(' ', '_')}.png"
         fig.savefig(plot_fname, dpi=250)
         plt.close(fig)
         if on_plot:
@@ -444,7 +453,7 @@ def smooth(y, f=0.05):
 
 
 @plt_settings()
-def plot_pr_curve(px, py, ap, save_dir=Path("pr_curve.png"), names=(), on_plot=None):
+def plot_pr_curve(px, py, ap, save_dir=Path("pr_curve.png"), names={}, on_plot=None):
     """Plots a precision-recall curve."""
     fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
     py = np.stack(py, axis=1)
@@ -455,7 +464,7 @@ def plot_pr_curve(px, py, ap, save_dir=Path("pr_curve.png"), names=(), on_plot=N
     else:
         ax.plot(px, py, linewidth=1, color="grey")  # plot(recall, precision)
 
-    ax.plot(px, py.mean(1), linewidth=3, color="blue", label="all classes %.3f mAP@0.5" % ap[:, 0].mean())
+    ax.plot(px, py.mean(1), linewidth=3, color="blue", label=f"all classes {ap[:, 0].mean():.3f} mAP@0.5")
     ax.set_xlabel("Recall")
     ax.set_ylabel("Precision")
     ax.set_xlim(0, 1)
@@ -469,7 +478,7 @@ def plot_pr_curve(px, py, ap, save_dir=Path("pr_curve.png"), names=(), on_plot=N
 
 
 @plt_settings()
-def plot_mc_curve(px, py, save_dir=Path("mc_curve.png"), names=(), xlabel="Confidence", ylabel="Metric", on_plot=None):
+def plot_mc_curve(px, py, save_dir=Path("mc_curve.png"), names={}, xlabel="Confidence", ylabel="Metric", on_plot=None):
     """Plots a metric-confidence curve."""
     fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
 
@@ -506,7 +515,6 @@ def compute_ap(recall, precision):
         (np.ndarray): Precision envelope curve.
         (np.ndarray): Modified recall curve with sentinel values added at the beginning and end.
     """
-
     # Append sentinel values to beginning and end
     mrec = np.concatenate(([0.0], recall, [1.0]))
     mpre = np.concatenate(([1.0], precision, [0.0]))
@@ -527,7 +535,7 @@ def compute_ap(recall, precision):
 
 
 def ap_per_class(
-    tp, conf, pred_cls, target_cls, plot=False, on_plot=None, save_dir=Path(), names=(), eps=1e-16, prefix=""
+    tp, conf, pred_cls, target_cls, plot=False, on_plot=None, save_dir=Path(), names={}, eps=1e-16, prefix=""
 ):
     """
     Computes the average precision per class for object detection evaluation.
@@ -540,26 +548,24 @@ def ap_per_class(
         plot (bool, optional): Whether to plot PR curves or not. Defaults to False.
         on_plot (func, optional): A callback to pass plots path and data when they are rendered. Defaults to None.
         save_dir (Path, optional): Directory to save the PR curves. Defaults to an empty path.
-        names (tuple, optional): Tuple of class names to plot PR curves. Defaults to an empty tuple.
+        names (dict, optional): Dict of class names to plot PR curves. Defaults to an empty tuple.
         eps (float, optional): A small value to avoid division by zero. Defaults to 1e-16.
         prefix (str, optional): A prefix string for saving the plot files. Defaults to an empty string.
 
     Returns:
-        (tuple): A tuple of six arrays and one array of unique classes, where:
-            tp (np.ndarray): True positive counts at threshold given by max F1 metric for each class.Shape: (nc,).
-            fp (np.ndarray): False positive counts at threshold given by max F1 metric for each class. Shape: (nc,).
-            p (np.ndarray): Precision values at threshold given by max F1 metric for each class. Shape: (nc,).
-            r (np.ndarray): Recall values at threshold given by max F1 metric for each class. Shape: (nc,).
-            f1 (np.ndarray): F1-score values at threshold given by max F1 metric for each class. Shape: (nc,).
-            ap (np.ndarray): Average precision for each class at different IoU thresholds. Shape: (nc, 10).
-            unique_classes (np.ndarray): An array of unique classes that have data. Shape: (nc,).
-            p_curve (np.ndarray): Precision curves for each class. Shape: (nc, 1000).
-            r_curve (np.ndarray): Recall curves for each class. Shape: (nc, 1000).
-            f1_curve (np.ndarray): F1-score curves for each class. Shape: (nc, 1000).
-            x (np.ndarray): X-axis values for the curves. Shape: (1000,).
-            prec_values: Precision values at mAP@0.5 for each class. Shape: (nc, 1000).
+        tp (np.ndarray): True positive counts at threshold given by max F1 metric for each class.Shape: (nc,).
+        fp (np.ndarray): False positive counts at threshold given by max F1 metric for each class. Shape: (nc,).
+        p (np.ndarray): Precision values at threshold given by max F1 metric for each class. Shape: (nc,).
+        r (np.ndarray): Recall values at threshold given by max F1 metric for each class. Shape: (nc,).
+        f1 (np.ndarray): F1-score values at threshold given by max F1 metric for each class. Shape: (nc,).
+        ap (np.ndarray): Average precision for each class at different IoU thresholds. Shape: (nc, 10).
+        unique_classes (np.ndarray): An array of unique classes that have data. Shape: (nc,).
+        p_curve (np.ndarray): Precision curves for each class. Shape: (nc, 1000).
+        r_curve (np.ndarray): Recall curves for each class. Shape: (nc, 1000).
+        f1_curve (np.ndarray): F1-score curves for each class. Shape: (nc, 1000).
+        x (np.ndarray): X-axis values for the curves. Shape: (1000,).
+        prec_values (np.ndarray): Precision values at mAP@0.5 for each class. Shape: (nc, 1000).
     """
-
     # Sort by objectness
     i = np.argsort(-conf)
     tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
@@ -595,7 +601,7 @@ def ap_per_class(
         # AP from recall-precision curve
         for j in range(tp.shape[1]):
             ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
-            if plot and j == 0:
+            if j == 0:
                 prec_values.append(np.interp(x, mrec, mpre))  # precision at mAP@0.5
 
     prec_values = np.array(prec_values)  # (nc, 1000)
@@ -791,20 +797,20 @@ class Metric(SimpleClass):
 
 class DetMetrics(SimpleClass):
     """
-    This class is a utility class for computing detection metrics such as precision, recall, and mean average precision
-    (mAP) of an object detection model.
+    Utility class for computing detection metrics such as precision, recall, and mean average precision (mAP) of an
+    object detection model.
 
     Args:
         save_dir (Path): A path to the directory where the output plots will be saved. Defaults to current directory.
         plot (bool): A flag that indicates whether to plot precision-recall curves for each class. Defaults to False.
         on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None.
-        names (tuple of str): A tuple of strings that represents the names of the classes. Defaults to an empty tuple.
+        names (dict of str): A dict of strings that represents the names of the classes. Defaults to an empty tuple.
 
     Attributes:
         save_dir (Path): A path to the directory where the output plots will be saved.
         plot (bool): A flag that indicates whether to plot the precision-recall curves for each class.
         on_plot (func): An optional callback to pass plots path and data when they are rendered.
-        names (tuple of str): A tuple of strings that represents the names of the classes.
+        names (dict of str): A dict of strings that represents the names of the classes.
         box (Metric): An instance of the Metric class for storing the results of the detection metrics.
         speed (dict): A dictionary for storing the execution time of different parts of the detection process.
 
@@ -821,7 +827,7 @@ class DetMetrics(SimpleClass):
         curves_results: TODO
     """
 
-    def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None:
+    def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names={}) -> None:
         """Initialize a DetMetrics instance with a save directory, plot flag, callback function, and class names."""
         self.save_dir = save_dir
         self.plot = plot
@@ -941,7 +947,6 @@ class SegmentMetrics(SimpleClass):
             pred_cls (list): List of predicted classes.
             target_cls (list): List of target classes.
         """
-
         results_mask = ap_per_class(
             tp_m,
             conf,
@@ -1083,7 +1088,6 @@ class PoseMetrics(SegmentMetrics):
             pred_cls (list): List of predicted classes.
             target_cls (list): List of target classes.
         """
-
         results_pose = ap_per_class(
             tp_p,
             conf,
@@ -1171,8 +1175,6 @@ class ClassifyMetrics(SimpleClass):
         top1 (float): The top-1 accuracy.
         top5 (float): The top-5 accuracy.
         speed (Dict[str, float]): A dictionary containing the time taken for each step in the pipeline.
-
-    Properties:
         fitness (float): The fitness of the model, which is equal to top-5 accuracy.
         results_dict (Dict[str, Union[float, str]]): A dictionary containing the classification metrics and fitness.
         keys (List[str]): A list of keys for the results_dict.
@@ -1222,7 +1224,10 @@ class ClassifyMetrics(SimpleClass):
 
 
 class OBBMetrics(SimpleClass):
+    """Metrics for evaluating oriented bounding box (OBB) detection, see https://arxiv.org/pdf/2106.06072.pdf."""
+
     def __init__(self, save_dir=Path("."), plot=False, on_plot=None, names=()) -> None:
+        """Initialize an OBBMetrics instance with directory, plotting, callback, and class names."""
         self.save_dir = save_dir
         self.plot = plot
         self.on_plot = on_plot