ultralytics 8.1.29__py3-none-any.whl → 8.3.63__py3-none-any.whl

ultralytics/models/utils/__init__.py

@@ -1 +1 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

ultralytics/models/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
@@ -6,6 +6,7 @@ import torch.nn.functional as F
 
 from ultralytics.utils.loss import FocalLoss, VarifocalLoss
 from ultralytics.utils.metrics import bbox_iou
+
 from .ops import HungarianMatcher
 
 
@@ -33,15 +34,19 @@ class DETRLoss(nn.Module):
         self, nc=80, loss_gain=None, aux_loss=True, use_fl=True, use_vfl=False, use_uni_match=False, uni_match_ind=0
     ):
         """
-        DETR loss function.
+        Initialize DETR loss function with customizable components and gains.
+
+        Uses default loss_gain if not provided. Initializes HungarianMatcher with
+        preset cost gains. Supports auxiliary losses and various loss types.
 
         Args:
-            nc (int): The number of classes.
-            loss_gain (dict): The coefficient of loss.
-            aux_loss (bool): If 'aux_loss = True', loss at each decoder layer are to be used.
-            use_vfl (bool): Use VarifocalLoss or not.
-            use_uni_match (bool): Whether to use a fixed layer to assign labels for auxiliary branch.
-            uni_match_ind (int): The fixed indices of a layer.
+            nc (int): Number of classes.
+            loss_gain (dict): Coefficients for different loss components.
+            aux_loss (bool): Use auxiliary losses from each decoder layer.
+            use_fl (bool): Use FocalLoss.
+            use_vfl (bool): Use VarifocalLoss.
+            use_uni_match (bool): Use fixed layer for auxiliary branch label assignment.
+            uni_match_ind (int): Index of fixed layer for uni_match.
         """
         super().__init__()
 
@@ -81,9 +86,7 @@ class DETRLoss(nn.Module):
         return {name_class: loss_cls.squeeze() * self.loss_gain["class"]}
 
     def _get_loss_bbox(self, pred_bboxes, gt_bboxes, postfix=""):
-        """Calculates and returns the bounding box loss and GIoU loss for the predicted and ground truth bounding
-        boxes.
-        """
+        """Computes bounding box and GIoU losses for predicted and ground truth bounding boxes."""
         # Boxes: [b, query, 4], gt_bbox: list[[n, 4]]
         name_bbox = f"loss_bbox{postfix}"
         name_giou = f"loss_giou{postfix}"
@@ -240,23 +243,32 @@ class DETRLoss(nn.Module):
         if len(gt_bboxes):
             gt_scores[idx] = bbox_iou(pred_bboxes.detach(), gt_bboxes, xywh=True).squeeze(-1)
 
-        loss = {}
-        loss.update(self._get_loss_class(pred_scores, targets, gt_scores, len(gt_bboxes), postfix))
-        loss.update(self._get_loss_bbox(pred_bboxes, gt_bboxes, postfix))
-        # if masks is not None and gt_mask is not None:
-        #     loss.update(self._get_loss_mask(masks, gt_mask, match_indices, postfix))
-        return loss
+        return {
+            **self._get_loss_class(pred_scores, targets, gt_scores, len(gt_bboxes), postfix),
+            **self._get_loss_bbox(pred_bboxes, gt_bboxes, postfix),
+            # **(self._get_loss_mask(masks, gt_mask, match_indices, postfix) if masks is not None and gt_mask is not None else {})
+        }
 
     def forward(self, pred_bboxes, pred_scores, batch, postfix="", **kwargs):
         """
+        Calculate loss for predicted bounding boxes and scores.
+
         Args:
-            pred_bboxes (torch.Tensor): [l, b, query, 4]
-            pred_scores (torch.Tensor): [l, b, query, num_classes]
-            batch (dict): A dict includes:
-                gt_cls (torch.Tensor) with shape [num_gts, ],
-                gt_bboxes (torch.Tensor): [num_gts, 4],
-                gt_groups (List(int)): a list of batch size length includes the number of gts of each image.
-            postfix (str): postfix of loss name.
+            pred_bboxes (torch.Tensor): Predicted bounding boxes, shape [l, b, query, 4].
+            pred_scores (torch.Tensor): Predicted class scores, shape [l, b, query, num_classes].
+            batch (dict): Batch information containing:
+                cls (torch.Tensor): Ground truth classes, shape [num_gts].
+                bboxes (torch.Tensor): Ground truth bounding boxes, shape [num_gts, 4].
+                gt_groups (List[int]): Number of ground truths for each image in the batch.
+            postfix (str): Postfix for loss names.
+            **kwargs (Any): Additional arguments, may include 'match_indices'.
+
+        Returns:
+            (dict): Computed losses, including main and auxiliary (if enabled).
+
+        Note:
+            Uses last elements of pred_bboxes and pred_scores for main loss, and the rest for auxiliary losses if
+            self.aux_loss is True.
         """
         self.device = pred_bboxes.device
         match_indices = kwargs.get("match_indices", None)

ultralytics/models/utils/ops.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
@@ -32,9 +32,7 @@ class HungarianMatcher(nn.Module):
     """
 
     def __init__(self, cost_gain=None, use_fl=True, with_mask=False, num_sample_points=12544, alpha=0.25, gamma=2.0):
-        """Initializes HungarianMatcher with cost coefficients, Focal Loss, mask prediction, sample points, and alpha
-        gamma factors.
-        """
+        """Initializes a HungarianMatcher module for optimal assignment of predicted and ground truth bounding boxes."""
         super().__init__()
         if cost_gain is None:
             cost_gain = {"class": 1, "bbox": 5, "giou": 2, "mask": 1, "dice": 1}
@@ -70,7 +68,6 @@ class HungarianMatcher(nn.Module):
                 For each batch element, it holds:
                     len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
         """
-
         bs, nq, nc = pred_scores.shape
 
         if sum(gt_groups) == 0:
@@ -133,7 +130,7 @@ class HungarianMatcher(nn.Module):
     #     sample_points = torch.cat([a.repeat(b, 1, 1, 1) for a, b in zip(sample_points, num_gts) if b > 0])
     #     tgt_mask = F.grid_sample(tgt_mask, sample_points, align_corners=False).squeeze([1, 2])
     #
-    #     with torch.cuda.amp.autocast(False):
+    #     with torch.amp.autocast("cuda", enabled=False):
     #         # binary cross entropy cost
     #         pos_cost_mask = F.binary_cross_entropy_with_logits(out_mask, torch.ones_like(out_mask), reduction='none')
     #         neg_cost_mask = F.binary_cross_entropy_with_logits(out_mask, torch.zeros_like(out_mask), reduction='none')
@@ -175,7 +172,6 @@ def get_cdn_group(
             bounding boxes, attention mask and meta information for denoising. If not in training mode or 'num_dn'
             is less than or equal to 0, the function returns None for all elements in the tuple.
     """
-
     if (not training) or num_dn <= 0:
         return None, None, None, None
     gt_groups = batch["gt_groups"]

ultralytics/models/yolo/__init__.py

@@ -1,7 +1,7 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-from ultralytics.models.yolo import classify, detect, obb, pose, segment
+from ultralytics.models.yolo import classify, detect, obb, pose, segment, world
 
 from .model import YOLO, YOLOWorld
 
-__all__ = "classify", "segment", "detect", "pose", "obb", "YOLO", "YOLOWorld"
+__all__ = "classify", "segment", "detect", "pose", "obb", "world", "YOLO", "YOLOWorld"

ultralytics/models/yolo/classify/__init__.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from ultralytics.models.yolo.classify.predict import ClassificationPredictor
 from ultralytics.models.yolo.classify.train import ClassificationTrainer

ultralytics/models/yolo/classify/predict.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 import cv2
 import torch
@@ -21,7 +21,7 @@ class ClassificationPredictor(BasePredictor):
         from ultralytics.utils import ASSETS
         from ultralytics.models.yolo.classify import ClassificationPredictor
 
-        args = dict(model='yolov8n-cls.pt', source=ASSETS)
+        args = dict(model="yolov8n-cls.pt", source=ASSETS)
         predictor = ClassificationPredictor(overrides=args)
         predictor.predict_cli()
         ```
@@ -53,9 +53,8 @@ class ClassificationPredictor(BasePredictor):
         if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
             orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
 
-        results = []
-        for i, pred in enumerate(preds):
-            orig_img = orig_imgs[i]
-            img_path = self.batch[0][i]
-            results.append(Results(orig_img, path=img_path, names=self.model.names, probs=pred))
-        return results
+        preds = preds[0] if isinstance(preds, (list, tuple)) else preds
+        return [
+            Results(orig_img, path=img_path, names=self.model.names, probs=pred)
+            for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0])
+        ]

ultralytics/models/yolo/classify/train.py

@@ -1,13 +1,14 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from copy import copy
 
 import torch
-import torchvision
 
 from ultralytics.data import ClassificationDataset, build_dataloader
 from ultralytics.engine.trainer import BaseTrainer
 from ultralytics.models import yolo
-from ultralytics.nn.tasks import ClassificationModel, attempt_load_one_weight
-from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK, colorstr
+from ultralytics.nn.tasks import ClassificationModel
+from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
 from ultralytics.utils.plotting import plot_images, plot_results
 from ultralytics.utils.torch_utils import is_parallel, strip_optimizer, torch_distributed_zero_first
 
@@ -23,7 +24,7 @@ class ClassificationTrainer(BaseTrainer):
         ```python
         from ultralytics.models.yolo.classify import ClassificationTrainer
 
-        args = dict(model='yolov8n-cls.pt', data='imagenet10', epochs=3)
+        args = dict(model="yolov8n-cls.pt", data="imagenet10", epochs=3)
         trainer = ClassificationTrainer(overrides=args)
         trainer.train()
         ```
@@ -59,23 +60,16 @@ class ClassificationTrainer(BaseTrainer):
 
     def setup_model(self):
         """Load, create or download model for any task."""
-        if isinstance(self.model, torch.nn.Module):  # if model is loaded beforehand. No setup needed
-            return
-
-        model, ckpt = str(self.model), None
-        # Load a YOLO model locally, from torchvision, or from Ultralytics assets
-        if model.endswith(".pt"):
-            self.model, ckpt = attempt_load_one_weight(model, device="cpu")
-            for p in self.model.parameters():
-                p.requires_grad = True  # for training
-        elif model.split(".")[-1] in ("yaml", "yml"):
-            self.model = self.get_model(cfg=model)
-        elif model in torchvision.models.__dict__:
-            self.model = torchvision.models.__dict__[model](weights="IMAGENET1K_V1" if self.args.pretrained else None)
+        import torchvision  # scope for faster 'import ultralytics'
+
+        if str(self.model) in torchvision.models.__dict__:
+            self.model = torchvision.models.__dict__[self.model](
+                weights="IMAGENET1K_V1" if self.args.pretrained else None
+            )
+            ckpt = None
         else:
-            FileNotFoundError(f"ERROR: model={model} not found locally or online. Please check model name.")
+            ckpt = super().setup_model()
         ClassificationModel.reshape_outputs(self.model, self.data["nc"])
-
         return ckpt
 
     def build_dataset(self, img_path, mode="train", batch=None):
@@ -115,7 +109,9 @@ class ClassificationTrainer(BaseTrainer):
     def get_validator(self):
         """Returns an instance of ClassificationValidator for validation."""
         self.loss_names = ["loss"]
-        return yolo.classify.ClassificationValidator(self.test_loader, self.save_dir, _callbacks=self.callbacks)
+        return yolo.classify.ClassificationValidator(
+            self.test_loader, self.save_dir, args=copy(self.args), _callbacks=self.callbacks
+        )
 
     def label_loss_items(self, loss_items=None, prefix="train"):
         """
@@ -145,7 +141,6 @@ class ClassificationTrainer(BaseTrainer):
                     self.metrics = self.validator(model=f)
                     self.metrics.pop("fitness", None)
                     self.run_callbacks("on_fit_epoch_end")
-        LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}")
 
     def plot_training_samples(self, batch, ni):
         """Plots training samples with their annotations."""

ultralytics/models/yolo/classify/val.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 import torch
 
@@ -20,7 +20,7 @@ class ClassificationValidator(BaseValidator):
         ```python
         from ultralytics.models.yolo.classify import ClassificationValidator
 
-        args = dict(model='yolov8n-cls.pt', data='imagenet10')
+        args = dict(model="yolov8n-cls.pt", data="imagenet10")
         validator = ClassificationValidator(args=args)
         validator()
         ```
@@ -56,8 +56,8 @@ class ClassificationValidator(BaseValidator):
     def update_metrics(self, preds, batch):
         """Updates running metrics with model predictions and batch targets."""
         n5 = min(len(self.names), 5)
-        self.pred.append(preds.argsort(1, descending=True)[:, :n5])
-        self.targets.append(batch["cls"])
+        self.pred.append(preds.argsort(1, descending=True)[:, :n5].type(torch.int32).cpu())
+        self.targets.append(batch["cls"].type(torch.int32).cpu())
 
     def finalize_metrics(self, *args, **kwargs):
         """Finalizes metrics of the model such as confusion_matrix and speed."""
@@ -71,6 +71,10 @@ class ClassificationValidator(BaseValidator):
         self.metrics.confusion_matrix = self.confusion_matrix
         self.metrics.save_dir = self.save_dir
 
+    def postprocess(self, preds):
+        """Preprocesses the classification predictions."""
+        return preds[0] if isinstance(preds, (list, tuple)) else preds
+
     def get_stats(self):
         """Returns a dictionary of metrics obtained by processing targets and predictions."""
         self.metrics.process(self.targets, self.pred)

ultralytics/models/yolo/detect/__init__.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from .predict import DetectionPredictor
 from .train import DetectionTrainer

ultralytics/models/yolo/detect/predict.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from ultralytics.engine.predictor import BasePredictor
 from ultralytics.engine.results import Results
@@ -14,7 +14,7 @@ class DetectionPredictor(BasePredictor):
         from ultralytics.utils import ASSETS
         from ultralytics.models.yolo.detect import DetectionPredictor
 
-        args = dict(model='yolov8n.pt', source=ASSETS)
+        args = dict(model="yolo11n.pt", source=ASSETS)
         predictor = DetectionPredictor(overrides=args)
         predictor.predict_cli()
         ```
@@ -35,9 +35,7 @@ class DetectionPredictor(BasePredictor):
             orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
 
         results = []
-        for i, pred in enumerate(preds):
-            orig_img = orig_imgs[i]
+        for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0]):
             pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
-            img_path = self.batch[0][i]
             results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred))
         return results

ultralytics/models/yolo/detect/train.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 import math
 import random
@@ -24,7 +24,7 @@ class DetectionTrainer(BaseTrainer):
         ```python
         from ultralytics.models.yolo.detect import DetectionTrainer
 
-        args = dict(model='yolov8n.pt', data='coco8.yaml', epochs=3)
+        args = dict(model="yolo11n.pt", data="coco8.yaml", epochs=3)
         trainer = DetectionTrainer(overrides=args)
         trainer.train()
         ```
@@ -44,7 +44,7 @@ class DetectionTrainer(BaseTrainer):
 
     def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"):
         """Construct and return dataloader."""
-        assert mode in ["train", "val"]
+        assert mode in {"train", "val"}, f"Mode must be 'train' or 'val', not {mode}."
         with torch_distributed_zero_first(rank):  # init dataset *.cache only once if DDP
             dataset = self.build_dataset(dataset_path, mode, batch_size)
         shuffle = mode == "train"
@@ -60,7 +60,7 @@ class DetectionTrainer(BaseTrainer):
         if self.args.multi_scale:
             imgs = batch["img"]
             sz = (
-                random.randrange(self.args.imgsz * 0.5, self.args.imgsz * 1.5 + self.stride)
+                random.randrange(int(self.args.imgsz * 0.5), int(self.args.imgsz * 1.5 + self.stride))
                 // self.stride
                 * self.stride
             )  # size
@@ -141,3 +141,10 @@ class DetectionTrainer(BaseTrainer):
         boxes = np.concatenate([lb["bboxes"] for lb in self.train_loader.dataset.labels], 0)
         cls = np.concatenate([lb["cls"] for lb in self.train_loader.dataset.labels], 0)
         plot_labels(boxes, cls.squeeze(), names=self.data["names"], save_dir=self.save_dir, on_plot=self.on_plot)
+
+    def auto_batch(self):
+        """Get batch size by calculating memory occupation of model."""
+        train_dataset = self.build_dataset(self.trainset, mode="train", batch=16)
+        # 4 for mosaic augmentation
+        max_num_obj = max(len(label["cls"]) for label in train_dataset.labels) * 4
+        return super().auto_batch(max_num_obj)

ultralytics/models/yolo/detect/val.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 import os
 from pathlib import Path
@@ -22,7 +22,7 @@ class DetectionValidator(BaseValidator):
         ```python
         from ultralytics.models.yolo.detect import DetectionValidator
 
-        args = dict(model='yolov8n.pt', data='coco8.yaml')
+        args = dict(model="yolo11n.pt", data="coco8.yaml")
         validator = DetectionValidator(args=args)
         validator()
         ```
@@ -32,13 +32,20 @@ class DetectionValidator(BaseValidator):
         """Initialize detection model with necessary variables and settings."""
         super().__init__(dataloader, save_dir, pbar, args, _callbacks)
         self.nt_per_class = None
+        self.nt_per_image = None
         self.is_coco = False
+        self.is_lvis = False
         self.class_map = None
         self.args.task = "detect"
         self.metrics = DetMetrics(save_dir=self.save_dir, on_plot=self.on_plot)
         self.iouv = torch.linspace(0.5, 0.95, 10)  # IoU vector for mAP@0.5:0.95
         self.niou = self.iouv.numel()
         self.lb = []  # for autolabelling
+        if self.args.save_hybrid:
+            LOGGER.warning(
+                "WARNING ⚠️ 'save_hybrid=True' will append ground truth to predictions for autolabelling.\n"
+                "WARNING ⚠️ 'save_hybrid=True' will cause incorrect mAP.\n"
+            )
 
     def preprocess(self, batch):
         """Preprocesses batch of images for YOLO training."""
@@ -51,23 +58,24 @@ class DetectionValidator(BaseValidator):
             height, width = batch["img"].shape[2:]
             nb = len(batch["img"])
             bboxes = batch["bboxes"] * torch.tensor((width, height, width, height), device=self.device)
-            self.lb = (
-                [
-                    torch.cat([batch["cls"][batch["batch_idx"] == i], bboxes[batch["batch_idx"] == i]], dim=-1)
-                    for i in range(nb)
-                ]
-                if self.args.save_hybrid
-                else []
-            )  # for autolabelling
+            self.lb = [
+                torch.cat([batch["cls"][batch["batch_idx"] == i], bboxes[batch["batch_idx"] == i]], dim=-1)
+                for i in range(nb)
+            ]
 
         return batch
 
     def init_metrics(self, model):
         """Initialize evaluation metrics for YOLO."""
         val = self.data.get(self.args.split, "")  # validation path
-        self.is_coco = isinstance(val, str) and "coco" in val and val.endswith(f"{os.sep}val2017.txt")  # is COCO
-        self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(1000))
-        self.args.save_json |= self.is_coco and not self.training  # run on final val if training COCO
+        self.is_coco = (
+            isinstance(val, str)
+            and "coco" in val
+            and (val.endswith(f"{os.sep}val2017.txt") or val.endswith(f"{os.sep}test-dev2017.txt"))
+        )  # is COCO
+        self.is_lvis = isinstance(val, str) and "lvis" in val and not self.is_coco  # is LVIS
+        self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(1, len(model.names) + 1))
+        self.args.save_json |= self.args.val and (self.is_coco or self.is_lvis) and not self.training  # run final val
         self.names = model.names
         self.nc = len(model.names)
         self.metrics.names = self.names
@@ -75,7 +83,7 @@ class DetectionValidator(BaseValidator):
         self.confusion_matrix = ConfusionMatrix(nc=self.nc, conf=self.args.conf)
         self.seen = 0
         self.jdict = []
-        self.stats = dict(tp=[], conf=[], pred_cls=[], target_cls=[])
+        self.stats = dict(tp=[], conf=[], pred_cls=[], target_cls=[], target_img=[])
 
     def get_desc(self):
         """Return a formatted string summarizing class metrics of YOLO model."""
@@ -89,7 +97,7 @@ class DetectionValidator(BaseValidator):
             self.args.iou,
             labels=self.lb,
             multi_label=True,
-            agnostic=self.args.single_cls,
+            agnostic=self.args.single_cls or self.args.agnostic_nms,
             max_det=self.args.max_det,
         )
 
@@ -104,7 +112,7 @@ class DetectionValidator(BaseValidator):
         if len(cls):
             bbox = ops.xywh2xyxy(bbox) * torch.tensor(imgsz, device=self.device)[[1, 0, 1, 0]]  # target boxes
             ops.scale_boxes(imgsz, bbox, ori_shape, ratio_pad=ratio_pad)  # native-space labels
-        return dict(cls=cls, bbox=bbox, ori_shape=ori_shape, imgsz=imgsz, ratio_pad=ratio_pad)
+        return {"cls": cls, "bbox": bbox, "ori_shape": ori_shape, "imgsz": imgsz, "ratio_pad": ratio_pad}
 
     def _prepare_pred(self, pred, pbatch):
         """Prepares a batch of images and annotations for validation."""
@@ -128,6 +136,7 @@ class DetectionValidator(BaseValidator):
             cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox")
             nl = len(cls)
             stat["target_cls"] = cls
+            stat["target_img"] = cls.unique()
             if npr == 0:
                 if nl:
                     for k in self.stats.keys():
@@ -146,8 +155,8 @@ class DetectionValidator(BaseValidator):
             # Evaluate
             if nl:
                 stat["tp"] = self._process_batch(predn, bbox, cls)
-                if self.args.plots:
-                    self.confusion_matrix.process_batch(predn, bbox, cls)
+            if self.args.plots:
+                self.confusion_matrix.process_batch(predn, bbox, cls)
             for k in self.stats.keys():
                 self.stats[k].append(stat[k])
 
@@ -155,8 +164,12 @@ class DetectionValidator(BaseValidator):
             if self.args.save_json:
                 self.pred_to_json(predn, batch["im_file"][si])
             if self.args.save_txt:
-                file = self.save_dir / "labels" / f'{Path(batch["im_file"][si]).stem}.txt'
-                self.save_one_txt(predn, self.args.save_conf, pbatch["ori_shape"], file)
+                self.save_one_txt(
+                    predn,
+                    self.args.save_conf,
+                    pbatch["ori_shape"],
+                    self.save_dir / "labels" / f"{Path(batch['im_file'][si]).stem}.txt",
+                )
 
     def finalize_metrics(self, *args, **kwargs):
         """Set final values for metrics speed and confusion matrix."""
@@ -166,11 +179,11 @@ class DetectionValidator(BaseValidator):
     def get_stats(self):
         """Returns metrics statistics and results dictionary."""
         stats = {k: torch.cat(v, 0).cpu().numpy() for k, v in self.stats.items()}  # to numpy
+        self.nt_per_class = np.bincount(stats["target_cls"].astype(int), minlength=self.nc)
+        self.nt_per_image = np.bincount(stats["target_img"].astype(int), minlength=self.nc)
+        stats.pop("target_img", None)
         if len(stats) and stats["tp"].any():
             self.metrics.process(**stats)
-        self.nt_per_class = np.bincount(
-            stats["target_cls"].astype(int), minlength=self.nc
-        )  # number of targets per class
         return self.metrics.results_dict
 
     def print_results(self):
@@ -183,7 +196,9 @@ class DetectionValidator(BaseValidator):
         # Print results per class
         if self.args.verbose and not self.training and self.nc > 1 and len(self.stats):
             for i, c in enumerate(self.metrics.ap_class_index):
-                LOGGER.info(pf % (self.names[c], self.seen, self.nt_per_class[c], *self.metrics.class_result(i)))
+                LOGGER.info(
+                    pf % (self.names[c], self.nt_per_image[c], self.nt_per_class[c], *self.metrics.class_result(i))
+                )
 
         if self.args.plots:
             for normalize in True, False:
@@ -196,13 +211,18 @@ class DetectionValidator(BaseValidator):
         Return correct prediction matrix.
 
         Args:
-            detections (torch.Tensor): Tensor of shape [N, 6] representing detections.
-                Each detection is of the format: x1, y1, x2, y2, conf, class.
-            labels (torch.Tensor): Tensor of shape [M, 5] representing labels.
-                Each label is of the format: class, x1, y1, x2, y2.
+            detections (torch.Tensor): Tensor of shape (N, 6) representing detections where each detection is
+                (x1, y1, x2, y2, conf, class).
+            gt_bboxes (torch.Tensor): Tensor of shape (M, 4) representing ground-truth bounding box coordinates. Each
+                bounding box is of the format: (x1, y1, x2, y2).
+            gt_cls (torch.Tensor): Tensor of shape (M,) representing target class indices.
 
         Returns:
-            (torch.Tensor): Correct prediction matrix of shape [N, 10] for 10 IoU levels.
+            (torch.Tensor): Correct prediction matrix of shape (N, 10) for 10 IoU levels.
+
+        Note:
+            The function does not return any value directly usable for metrics calculation. Instead, it provides an
+            intermediate representation used for evaluating predictions against ground truth.
         """
         iou = box_iou(gt_bboxes, detections[:, :4])
         return self.match_predictions(detections[:, 5], gt_cls, iou)
@@ -249,12 +269,14 @@ class DetectionValidator(BaseValidator):
 
     def save_one_txt(self, predn, save_conf, shape, file):
         """Save YOLO detections to a txt file in normalized coordinates in a specific format."""
-        gn = torch.tensor(shape)[[1, 0, 1, 0]]  # normalization gain whwh
-        for *xyxy, conf, cls in predn.tolist():
-            xywh = (ops.xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
-            line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
-            with open(file, "a") as f:
-                f.write(("%g " * len(line)).rstrip() % line + "\n")
+        from ultralytics.engine.results import Results
+
+        Results(
+            np.zeros((shape[0], shape[1]), dtype=np.uint8),
+            path=None,
+            names=self.names,
+            boxes=predn[:, :6],
+        ).save_txt(file, save_conf=save_conf)
 
     def pred_to_json(self, predn, filename):
         """Serialize YOLO predictions to COCO json format."""
@@ -274,26 +296,42 @@ class DetectionValidator(BaseValidator):
 
     def eval_json(self, stats):
         """Evaluates YOLO output in JSON format and returns performance statistics."""
-        if self.args.save_json and self.is_coco and len(self.jdict):
-            anno_json = self.data["path"] / "annotations/instances_val2017.json"  # annotations
+        if self.args.save_json and (self.is_coco or self.is_lvis) and len(self.jdict):
             pred_json = self.save_dir / "predictions.json"  # predictions
-            LOGGER.info(f"\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...")
+            anno_json = (
+                self.data["path"]
+                / "annotations"
+                / ("instances_val2017.json" if self.is_coco else f"lvis_v1_{self.args.split}.json")
+            )  # annotations
+            pkg = "pycocotools" if self.is_coco else "lvis"
+            LOGGER.info(f"\nEvaluating {pkg} mAP using {pred_json} and {anno_json}...")
             try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
-                check_requirements("pycocotools>=2.0.6")
-                from pycocotools.coco import COCO  # noqa
-                from pycocotools.cocoeval import COCOeval  # noqa
-
-                for x in anno_json, pred_json:
+                for x in pred_json, anno_json:
                     assert x.is_file(), f"{x} file not found"
-                anno = COCO(str(anno_json))  # init annotations api
-                pred = anno.loadRes(str(pred_json))  # init predictions api (must pass string, not Path)
-                eval = COCOeval(anno, pred, "bbox")
+                check_requirements("pycocotools>=2.0.6" if self.is_coco else "lvis>=0.5.3")
                 if self.is_coco:
-                    eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # images to eval
-                eval.evaluate()
-                eval.accumulate()
-                eval.summarize()
-                stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = eval.stats[:2]  # update mAP50-95 and mAP50
+                    from pycocotools.coco import COCO  # noqa
+                    from pycocotools.cocoeval import COCOeval  # noqa
+
+                    anno = COCO(str(anno_json))  # init annotations api
+                    pred = anno.loadRes(str(pred_json))  # init predictions api (must pass string, not Path)
+                    val = COCOeval(anno, pred, "bbox")
+                else:
+                    from lvis import LVIS, LVISEval
+
+                    anno = LVIS(str(anno_json))  # init annotations api
+                    pred = anno._load_json(str(pred_json))  # init predictions api (must pass string, not Path)
+                    val = LVISEval(anno, pred, "bbox")
+                val.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # images to eval
+                val.evaluate()
+                val.accumulate()
+                val.summarize()
+                if self.is_lvis:
+                    val.print_results()  # explicitly call print_results
+                # update mAP50-95 and mAP50
+                stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = (
+                    val.stats[:2] if self.is_coco else [val.results["AP50"], val.results["AP"]]
+                )
             except Exception as e:
-                LOGGER.warning(f"pycocotools unable to run: {e}")
+                LOGGER.warning(f"{pkg} unable to run: {e}")
         return stats