Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation).

Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation).

Custom Ultralytics tqdm class with different default arguments. Args: *args (list): Positional arguments passed to original tqdm.

Custom Ultralytics tqdm class with different default arguments. Args: *args (list): Positional arguments passed to original tqdm.

YOLO (You Only Look Once) object detection model.

YOLO (You Only Look Once) object detection model.

A sequential container that performs 2D convolution followed by batch normalization.

A sequential container that performs 2D convolution followed by batch normalization.

A class for storing and manipulating inference results. Args: orig_img (numpy.ndarray): The original image as a numpy array.

A class for storing and manipulating inference results. Args: orig_img (numpy.ndarray): The original image as a numpy array.

A PyTorch implementation of Layer Normalization in 2D.

A PyTorch implementation of Layer Normalization in 2D.

Resize image and padding for detection, instance segmentation, pose.

Resize image and padding for detection, instance segmentation, pose.

Manages authentication processes including API key handling, cookie-based authentication, and header generation. The class supports differen

Manages authentication processes including API key handling, cookie-based authentication, and header generation. The class supports differen

Standard bottleneck.

Standard bottleneck.

Class for computing evaluation metrics for YOLOv8 model. Attributes: p (list): Precision for each class. Shape: (nc,). r (li

Class for computing evaluation metrics for YOLOv8 model. Attributes: p (list): Precision for each class. Shape: (nc,). r (li

YOLOv8 Profile class. Use as a decorator with @Profile() or as a context manager with 'with Profile():'. Example: ```python

YOLOv8 Profile class. Use as a decorator with @Profile() or as a context manager with 'with Profile():'. Example: ```python

Dataset class for loading object detection and/or segmentation labels in YOLO format. Args: data (dict, optional): A dataset YAML di

Dataset class for loading object detection and/or segmentation labels in YOLO format. Args: data (dict, optional): A dataset YAML di

An attention layer that allows for downscaling the size of the embedding after projection to queries, keys, and values.

An attention layer that allows for downscaling the size of the embedding after projection to queries, keys, and values.

A class for handling bounding boxes. The class supports various bounding box formats like 'xyxy', 'xywh', and 'ltwh'. Bounding box data

A class for handling bounding boxes. The class supports various bounding box formats like 'xyxy', 'xywh', and 'ltwh'. Bounding box data

Standard bottleneck.

Class for composing multiple image transformations.

Class for composing multiple image transformations.

Concatenate a list of tensors along dimension.

Ultralytics Annotator for train/val mosaics and JPGs and predictions annotations. Attributes: im (Image.Image or numpy array): The i

Ultralytics Annotator for train/val mosaics and JPGs and predictions annotations. Attributes: im (Image.Image or numpy array): The i

Depth-wise convolution.

Depth-wise convolution.

Container for bounding boxes, segments, and keypoints of detected objects in an image. Attributes: _bboxes (Bboxes): Internal object

Container for bounding boxes, segments, and keypoints of detected objects in an image. Attributes: _bboxes (Bboxes): Internal object

Ultralytics IterableSimpleNamespace is an extension class of SimpleNamespace that adds iterable functionality and enables usage with dict() and fo

Ultralytics IterableSimpleNamespace is an extension class of SimpleNamespace that adds iterable functionality and enables usage with dict() and fo

Implements a simple multi-layer perceptron (also called FFN).

Implements a simple multi-layer perceptron (also called FFN).

Handles dynamic backend selection for running inference using Ultralytics YOLO models. The AutoBackend class is designed to provide an abstr

Handles dynamic backend selection for running inference using Ultralytics YOLO models. The AutoBackend class is designed to provide an abstr

An extended version of the STrack class for YOLOv8, adding object tracking features. Attributes: shared_kalman (KalmanFilterXYWH): A

An extended version of the STrack class for YOLOv8, adding object tracking features. Attributes: shared_kalman (KalmanFilterXYWH): A

A class for storing and manipulating detection boxes. Args: boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing

A class for storing and manipulating detection boxes. Args: boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing

YOLO Classification Dataset. Args: root (str): Dataset path. Attributes: cache_ram (bool): True if images should be cac

YOLO Classification Dataset. Args: root (str): Dataset path. Attributes: cache_ram (bool): True if images should be cac

A class for calculating and updating a confusion matrix for object detection and classification tasks. Attributes: task (str): The t

A class for calculating and updating a confusion matrix for object detection and classification tasks. Attributes: task (str): The t

Formats image annotations for object detection, instance segmentation, and pose estimation tasks. The class standardizes the image and instan

Formats image annotations for object detection, instance segmentation, and pose estimation tasks. The class standardizes the image and instan

Ghost Convolution https://github.com/huawei-noah/ghostnet.

Ghost Convolution https://github.com/huawei-noah/ghostnet.

For bytetrack. A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space (x, y, a, h, vx, vy, va, vh)

For bytetrack. A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space (x, y, a, h, vx, vy, va, vh)

For BoT-SORT. A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space (x, y, w, h, vx, vy, vw, vh)

For BoT-SORT. A simple Kalman filter for tracking bounding boxes in image space. The 8-dimensional state space (x, y, w, h, vx, vy, vw, vh)

MLP (Multi-Layer Perceptron) model lightly adapted from https://github.com/facebookresearch/MaskFormer/blob/main/mask_former/modeling/transfo

MLP (Multi-Layer Perceptron) model lightly adapted from https://github.com/facebookresearch/MaskFormer/blob/main/mask_former/modeling/transfo

Implements a single block of a multi-layer perceptron.

Implements a single block of a multi-layer perceptron.