Merge branch 'main' into quan

docs/en/datasets/classify/cifar10.md

@@ -153,6 +153,10 @@ Each subset comprises images categorized into 10 classes, with their annotations
 
 If you use the CIFAR-10 dataset in your research or development projects, make sure to cite the following paper:
 
+!!! Quote ""
+
+    === "BibTeX"
+
         ```bibtex
         @TECHREPORT{Krizhevsky09learningmultiple,
                     author={Alex Krizhevsky},

docs/en/datasets/classify/imagewoof.md

@@ -59,6 +59,10 @@ ImageWoof dataset comes in three different sizes to accommodate various research
 
 To use these variants in your training, simply replace 'imagewoof' in the dataset argument with 'imagewoof320' or 'imagewoof160'. For example:
 
+!!! Example "Example"
+
+    === "Python"
+
         ```python
         from ultralytics import YOLO
 
@@ -72,6 +76,13 @@ model.train(data="imagewoof320", epochs=100, imgsz=224)
         model.train(data="imagewoof160", epochs=100, imgsz=224)
         ```
 
+    === "CLI"
+
+        ```bash
+        # Load a pretrained model and train on the small-sized dataset
+        yolo classify train model=yolov8n-cls.pt data=imagewoof320 epochs=100 imgsz=224
+        ```
+
 It's important to note that using smaller images will likely yield lower performance in terms of classification accuracy. However, it's an excellent way to iterate quickly in the early stages of model development and prototyping.
 
 ## Sample Images and Annotations

docs/en/datasets/detect/roboflow-100.md

@@ -203,7 +203,7 @@ The **Roboflow 100** dataset is accessible on [GitHub](https://github.com/robofl
 
 When using the Roboflow 100 dataset in your research, ensure to properly cite it. Here is the recommended citation:
 
-!!! Quote
+!!! Quote ""
 
     === "BibTeX"
 

docs/en/datasets/detect/visdrone.md

@@ -159,7 +159,9 @@ The configuration file for the VisDrone dataset, `VisDrone.yaml`, can be found i
 
 If you use the VisDrone dataset in your research or development work, please cite the following paper:
 
-!!! Quote "BibTeX"
+!!! Quote ""
+
+    === "BibTeX"
 
         ```bibtex
         @ARTICLE{9573394,
@@ -170,5 +172,6 @@ If you use the VisDrone dataset in your research or development work, please cit
           volume={},
           number={},
           pages={1-1},
-      doi={10.1109/TPAMI.2021.3119563}}
+          doi={10.1109/TPAMI.2021.3119563}
+        }
         ```

docs/en/datasets/segment/crack-seg.md

@@ -135,6 +135,10 @@ Ultralytics YOLO offers advanced real-time object detection, segmentation, and c
 
 If you incorporate the Crack Segmentation Dataset into your research, please use the following BibTeX reference:
 
+!!! Quote ""
+
+    === "BibTeX"
+
         ```bibtex
         @misc{ crack-bphdr_dataset,
             title = { crack Dataset },

docs/en/datasets/segment/package-seg.md

@@ -99,7 +99,11 @@ The [Roboflow Package Segmentation Dataset](https://universe.roboflow.com/factor
 
 ### How do I train an Ultralytics YOLOv8 model on the Package Segmentation Dataset?
 
-You can train an Ultralytics YOLOv8n model using both Python and CLI methods. For Python, use the snippet below:
+You can train an Ultralytics YOLOv8n model using both Python and CLI methods. Use the snippets below:
+
+!!! Example "Train Example"
+
+    === "Python"
     
         ```python
         from ultralytics import YOLO
@@ -111,7 +115,7 @@ model = YOLO("yolov8n-seg.pt")  # load a pretrained model
         results = model.train(data="package-seg.yaml", epochs=100, imgsz=640)
         ```
 
-For CLI:
+    === "CLI"
         
         ```bash
         # Start training from a pretrained *.pt model

docs/en/guides/parking-management.md

@@ -10,6 +10,17 @@ keywords: parking management, YOLOv8, Ultralytics, vehicle detection, real-time
 
 Parking management with [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics/) ensures efficient and safe parking by organizing spaces and monitoring availability. YOLOv8 can improve parking lot management through real-time vehicle detection, and insights into parking occupancy.
 
+<p align="center">
+  <br>
+  <iframe loading="lazy" width="720" height="405" src="https://www.youtube.com/embed/WwXnljc7ZUM"
+    title="YouTube video player" frameborder="0"
+    allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
+    allowfullscreen>
+  </iframe>
+  <br>
+  <strong>Watch:</strong> How to Implement Parking Management Using Ultralytics YOLOv8 🚀
+</p>
+
 ## Advantages of Parking Management System?
 
 - **Efficiency**: Parking lot management optimizes the use of parking spaces and reduces congestion.

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.80"
+__version__ = "8.2.81"
 
 import os
 

ultralytics/engine/results.py

@@ -992,8 +992,8 @@ class Boxes(BaseTensor):
         Convert bounding boxes from [x1, y1, x2, y2] format to [x, y, width, height] format.
 
         Returns:
-            (torch.Tensor | numpy.ndarray): Boxes in [x, y, width, height] format, where x, y are the coordinates of
-                the top-left corner of the bounding box, width, height are the dimensions of the bounding box and the
+            (torch.Tensor | numpy.ndarray): Boxes in [x_center, y_center, width, height] format, where x_center, y_center are the coordinates of
+                the center point of the bounding box, width, height are the dimensions of the bounding box and the
                 shape of the returned tensor is (N, 4), where N is the number of boxes.
 
         Examples:

ultralytics/hub/session.py

@@ -1,5 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
+import shutil
 import threading
 import time
 from http import HTTPStatus
@@ -344,23 +345,34 @@ class HUBTrainingSession:
             map (float): Mean average precision of the model.
             final (bool): Indicates if the model is the final model after training.
         """
-        if Path(weights).is_file():
-            progress_total = Path(weights).stat().st_size if final else None  # Only show progress if final
+        weights = Path(weights)
+        if not weights.is_file():
+            last = weights.with_name("last" + weights.suffix)
+            if final and last.is_file():
+                LOGGER.warning(
+                    f"{PREFIX} ARNING ⚠️ Model 'best.pt' not found, copying 'last.pt' to 'best.pt' and uploading. "
+                    "This often happens when resuming training in transient environments like Google Colab. "
+                    "For more reliable training, consider using Ultralytics HUB Cloud. "
+                    "Learn more at https://docs.ultralytics.com/hub/cloud-training/."
+                )
+                shutil.copy(last, weights)  # copy last.pt to best.pt
+            else:
+                LOGGER.warning(f"{PREFIX} WARNING ⚠️ Model upload issue. Missing model {weights}.")
+                return
+
         self.request_queue(
             self.model.upload_model,
             epoch=epoch,
-                weights=weights,
+            weights=str(weights),
             is_best=is_best,
             map=map,
             final=final,
             retry=10,
             timeout=3600,
             thread=not final,
-                progress_total=progress_total,
+            progress_total=weights.stat().st_size if final else None,  # only show progress if final
             stream_response=True,
         )
-        else:
-            LOGGER.warning(f"{PREFIX}WARNING ⚠️ Model upload issue. Missing model {weights}.")
 
     @staticmethod
     def _show_upload_progress(content_length: int, response: requests.Response) -> None:

ultralytics/utils/__init__.py

@@ -219,14 +219,17 @@ def plt_settings(rcparams=None, backend="Agg"):
         def wrapper(*args, **kwargs):
             """Sets rc parameters and backend, calls the original function, and restores the settings."""
             original_backend = plt.get_backend()
-            if backend.lower() != original_backend.lower():
+            switch = backend.lower() != original_backend.lower()
+            if switch:
                 plt.close("all")  # auto-close()ing of figures upon backend switching is deprecated since 3.8
                 plt.switch_backend(backend)
 
+            # Plot with backend and always revert to original backend
+            try:
                 with plt.rc_context(rcparams):
                     result = func(*args, **kwargs)
-
-            if backend != original_backend:
+            finally:
+                if switch:
                     plt.close("all")
                     plt.switch_backend(original_backend)
             return result