Merge branch 'main' into quan

docs/en/datasets/classify/cifar10.md

@@ -153,14 +153,18 @@ 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:
 
-```bibtex
-@TECHREPORT{Krizhevsky09learningmultiple,
-            author={Alex Krizhevsky},
-            title={Learning multiple layers of features from tiny images},
-            institution={},
-            year={2009}
-}
-```
+!!! Quote ""
+
+    === "BibTeX"
+
+        ```bibtex
+        @TECHREPORT{Krizhevsky09learningmultiple,
+                    author={Alex Krizhevsky},
+                    title={Learning multiple layers of features from tiny images},
+                    institution={},
+                    year={2009}
+        }
+        ```
 
 Acknowledging the dataset's creators helps support continued research and development in the field. For more details, see the [citations and acknowledgments](#citations-and-acknowledgments) section.
 

docs/en/datasets/classify/imagewoof.md

@@ -59,18 +59,29 @@ 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:
 
-```python
-from ultralytics import YOLO
+!!! Example "Example"
 
-# Load a model
-model = YOLO("yolov8n-cls.pt")  # load a pretrained model (recommended for training)
+    === "Python"
+
+        ```python
+        from ultralytics import YOLO
+
+        # Load a model
+        model = YOLO("yolov8n-cls.pt")  # load a pretrained model (recommended for training)
 
-# For medium-sized dataset
-model.train(data="imagewoof320", epochs=100, imgsz=224)
+        # For medium-sized dataset
+        model.train(data="imagewoof320", epochs=100, imgsz=224)
 
-# For small-sized dataset
-model.train(data="imagewoof160", epochs=100, imgsz=224)
-```
+        # For small-sized dataset
+        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.
 

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

@@ -159,16 +159,19 @@ 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"
-
-    ```bibtex
-    @ARTICLE{9573394,
-      author={Zhu, Pengfei and Wen, Longyin and Du, Dawei and Bian, Xiao and Fan, Heng and Hu, Qinghua and Ling, Haibin},
-      journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
-      title={Detection and Tracking Meet Drones Challenge},
-      year={2021},
-      volume={},
-      number={},
-      pages={1-1},
-      doi={10.1109/TPAMI.2021.3119563}}
-    ```
+!!! Quote ""
+
+    === "BibTeX"
+
+        ```bibtex
+        @ARTICLE{9573394,
+          author={Zhu, Pengfei and Wen, Longyin and Du, Dawei and Bian, Xiao and Fan, Heng and Hu, Qinghua and Ling, Haibin},
+          journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+          title={Detection and Tracking Meet Drones Challenge},
+          year={2021},
+          volume={},
+          number={},
+          pages={1-1},
+          doi={10.1109/TPAMI.2021.3119563}
+        }
+        ```

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

@@ -135,19 +135,23 @@ 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:
 
-```bibtex
-@misc{ crack-bphdr_dataset,
-    title = { crack Dataset },
-    type = { Open Source Dataset },
-    author = { University },
-    howpublished = { \url{ https://universe.roboflow.com/university-bswxt/crack-bphdr } },
-    url = { https://universe.roboflow.com/university-bswxt/crack-bphdr },
-    journal = { Roboflow Universe },
-    publisher = { Roboflow },
-    year = { 2022 },
-    month = { dec },
-    note = { visited on 2024-01-23 },
-}
-```
+!!! Quote ""
+
+    === "BibTeX"
+
+        ```bibtex
+        @misc{ crack-bphdr_dataset,
+            title = { crack Dataset },
+            type = { Open Source Dataset },
+            author = { University },
+            howpublished = { \url{ https://universe.roboflow.com/university-bswxt/crack-bphdr } },
+            url = { https://universe.roboflow.com/university-bswxt/crack-bphdr },
+            journal = { Roboflow Universe },
+            publisher = { Roboflow },
+            year = { 2022 },
+            month = { dec },
+            note = { visited on 2024-01-23 },
+        }
+        ```
 
 This citation format ensures proper accreditation to the creators of the dataset and acknowledges its use in your research.

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

@@ -99,24 +99,28 @@ 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:
 
-```python
-from ultralytics import YOLO
+!!! Example "Train Example"
 
-# Load a model
-model = YOLO("yolov8n-seg.pt")  # load a pretrained model
+    === "Python"
+    
+        ```python
+        from ultralytics import YOLO
 
-# Train the model
-results = model.train(data="package-seg.yaml", epochs=100, imgsz=640)
-```
+        # Load a model
+        model = YOLO("yolov8n-seg.pt")  # load a pretrained model
 
-For CLI:
+        # Train the model
+        results = model.train(data="package-seg.yaml", epochs=100, imgsz=640)
+        ```
 
-```bash
-# Start training from a pretrained *.pt model
-yolo segment train data=package-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640
-```
+    === "CLI"
+        
+        ```bash
+        # Start training from a pretrained *.pt model
+        yolo segment train data=package-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640
+        ```
 
 Refer to the model [Training](../../modes/train.md) page for more details.
 

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
-            self.request_queue(
-                self.model.upload_model,
-                epoch=epoch,
-                weights=weights,
-                is_best=is_best,
-                map=map,
-                final=final,
-                retry=10,
-                timeout=3600,
-                thread=not final,
-                progress_total=progress_total,
-                stream_response=True,
-            )
-        else:
-            LOGGER.warning(f"{PREFIX}WARNING ⚠️ Model upload issue. Missing model {weights}.")
+        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=str(weights),
+            is_best=is_best,
+            map=map,
+            final=final,
+            retry=10,
+            timeout=3600,
+            thread=not final,
+            progress_total=weights.stat().st_size if final else None,  # only show progress if final
+            stream_response=True,
+        )
 
     @staticmethod
     def _show_upload_progress(content_length: int, response: requests.Response) -> None:

ultralytics/utils/__init__.py

@@ -219,16 +219,19 @@ 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)
 
-            with plt.rc_context(rcparams):
-                result = func(*args, **kwargs)
-
-            if backend != original_backend:
-                plt.close("all")
-                plt.switch_backend(original_backend)
+            # Plot with backend and always revert to original backend
+            try:
+                with plt.rc_context(rcparams):
+                    result = func(*args, **kwargs)
+            finally:
+                if switch:
+                    plt.close("all")
+                    plt.switch_backend(original_backend)
             return result
 
         return wrapper