Add https://youtu.be/SArFQs6CHwk to docs (#10014)

Co-authored-by: UltralyticsAssistant <web@ultralytics.com>

docs/en/models/rtdetr.md

@@ -10,6 +10,17 @@ keywords: RT-DETR, Baidu, Vision Transformers, object detection, real-time perfo
 
 Real-Time Detection Transformer (RT-DETR), developed by Baidu, is a cutting-edge end-to-end object detector that provides real-time performance while maintaining high accuracy. It leverages the power of Vision Transformers (ViT) to efficiently process multiscale features by decoupling intra-scale interaction and cross-scale fusion. RT-DETR is highly adaptable, supporting flexible adjustment of inference speed using different decoder layers without retraining. The model excels on accelerated backends like CUDA with TensorRT, outperforming many other real-time object detectors.
 
+<p align="center">
+  <br>
+  <iframe loading="lazy" width="720" height="405" src="https://www.youtube.com/embed/SArFQs6CHwk"
+    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> Real-Time Detection Transformer (RT-DETR)
+</p>
+
 ![Model example image](https://user-images.githubusercontent.com/26833433/238963168-90e8483f-90aa-4eb6-a5e1-0d408b23dd33.png) **Overview of Baidu's RT-DETR.** The RT-DETR model architecture diagram shows the last three stages of the backbone {S3, S4, S5} as the input to the encoder. The efficient hybrid encoder transforms multiscale features into a sequence of image features through intrascale feature interaction (AIFI) and cross-scale feature-fusion module (CCFM). The IoU-aware query selection is employed to select a fixed number of image features to serve as initial object queries for the decoder. Finally, the decoder with auxiliary prediction heads iteratively optimizes object queries to generate boxes and confidence scores ([source](https://arxiv.org/pdf/2304.08069.pdf)).
 
 ### Key Features

ultralytics/data/augment.py

@@ -16,6 +16,7 @@ from ultralytics.utils.instance import Instances
 from ultralytics.utils.metrics import bbox_ioa
 from ultralytics.utils.ops import segment2box, xyxyxyxy2xywhr
 from ultralytics.utils.torch_utils import TORCHVISION_0_10, TORCHVISION_0_11, TORCHVISION_0_13
+
 from .utils import polygons2masks, polygons2masks_overlap
 
 DEFAULT_MEAN = (0.0, 0.0, 0.0)

ultralytics/data/base.py

@@ -15,6 +15,7 @@ import psutil
 from torch.utils.data import Dataset
 
 from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM
+
 from .utils import FORMATS_HELP_MSG, HELP_URL, IMG_FORMATS
 
 

ultralytics/data/build.py

@@ -22,6 +22,7 @@ from ultralytics.data.loaders import (
 from ultralytics.data.utils import IMG_FORMATS, VID_FORMATS
 from ultralytics.utils import RANK, colorstr
 from ultralytics.utils.checks import check_file
+
 from .dataset import GroundingDataset, YOLODataset, YOLOMultiModalDataset
 from .utils import PIN_MEMORY
 

ultralytics/data/dataset.py

@@ -15,6 +15,7 @@ from torch.utils.data import ConcatDataset
 
 from ultralytics.utils import LOCAL_RANK, NUM_THREADS, TQDM, colorstr
 from ultralytics.utils.ops import resample_segments
+
 from .augment import (
     Compose,
     Format,

ultralytics/data/explorer/explorer.py

@@ -7,8 +7,8 @@ from typing import Any, List, Tuple, Union
 import cv2
 import numpy as np
 import torch
-from PIL import Image
 from matplotlib import pyplot as plt
+from PIL import Image
 from tqdm import tqdm
 
 from ultralytics.data.augment import Format
@@ -16,6 +16,7 @@ from ultralytics.data.dataset import YOLODataset
 from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.model import YOLO
 from ultralytics.utils import LOGGER, USER_CONFIG_DIR, IterableSimpleNamespace, checks
+
 from .utils import get_sim_index_schema, get_table_schema, plot_query_result, prompt_sql_query, sanitize_batch
 
 

ultralytics/models/fastsam/model.py

@@ -3,6 +3,7 @@
 from pathlib import Path
 
 from ultralytics.engine.model import Model
+
 from .predict import FastSAMPredictor
 from .val import FastSAMValidator
 

ultralytics/models/nas/model.py

@@ -17,6 +17,7 @@ import torch
 
 from ultralytics.engine.model import Model
 from ultralytics.utils.torch_utils import model_info, smart_inference_mode
+
 from .predict import NASPredictor
 from .val import NASValidator
 

ultralytics/models/rtdetr/train.py

@@ -7,6 +7,7 @@ import torch
 from ultralytics.models.yolo.detect import DetectionTrainer
 from ultralytics.nn.tasks import RTDETRDetectionModel
 from ultralytics.utils import RANK, colorstr
+
 from .val import RTDETRDataset, RTDETRValidator
 
 

ultralytics/models/sam/build.py

@@ -11,6 +11,7 @@ from functools import partial
 import torch
 
 from ultralytics.utils.downloads import attempt_download_asset
+
 from .modules.decoders import MaskDecoder
 from .modules.encoders import ImageEncoderViT, PromptEncoder
 from .modules.sam import Sam

ultralytics/models/sam/model.py

@@ -18,6 +18,7 @@ from pathlib import Path
 
 from ultralytics.engine.model import Model
 from ultralytics.utils.torch_utils import model_info
+
 from .build import build_sam
 from .predict import Predictor
 

ultralytics/models/sam/predict.py

@@ -17,6 +17,7 @@ from ultralytics.engine.predictor import BasePredictor
 from ultralytics.engine.results import Results
 from ultralytics.utils import DEFAULT_CFG, ops
 from ultralytics.utils.torch_utils import select_device
+
 from .amg import (
     batch_iterator,
     batched_mask_to_box,

ultralytics/models/utils/loss.py

@@ -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
 
 

ultralytics/nn/modules/head.py

@@ -8,6 +8,7 @@ import torch.nn as nn
 from torch.nn.init import constant_, xavier_uniform_
 
 from ultralytics.utils.tal import TORCH_1_10, dist2bbox, dist2rbox, make_anchors
+
 from .block import DFL, BNContrastiveHead, ContrastiveHead, Proto
 from .conv import Conv
 from .transformer import MLP, DeformableTransformerDecoder, DeformableTransformerDecoderLayer

ultralytics/trackers/byte_tracker.py

@@ -2,11 +2,11 @@
 
 import numpy as np
 
+from ..utils import LOGGER
+from ..utils.ops import xywh2ltwh
 from .basetrack import BaseTrack, TrackState
 from .utils import matching
 from .utils.kalman_filter import KalmanFilterXYAH
-from ..utils import LOGGER
-from ..utils.ops import xywh2ltwh
 
 
 class STrack(BaseTrack):

ultralytics/trackers/track.py

@@ -7,6 +7,7 @@ import torch
 
 from ultralytics.utils import IterableSimpleNamespace, yaml_load
 from ultralytics.utils.checks import check_yaml
+
 from .bot_sort import BOTSORT
 from .byte_tracker import BYTETracker
 

ultralytics/utils/callbacks/base.py

@@ -4,7 +4,6 @@
 from collections import defaultdict
 from copy import deepcopy
 
-
 # Trainer callbacks ----------------------------------------------------------------------------------------------------
 
 

ultralytics/utils/loss.py

@@ -7,6 +7,7 @@ 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 .metrics import bbox_iou, probiou
 from .tal import bbox2dist
 

ultralytics/utils/plotting.py

@@ -13,6 +13,7 @@ from PIL import Image, ImageDraw, ImageFont
 from PIL import __version__ as pil_version
 
 from ultralytics.utils import LOGGER, TryExcept, ops, plt_settings, threaded
+
 from .checks import check_font, check_version, is_ascii
 from .files import increment_path