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

YOLO (You Only Look Once) object detection model. Args: model (str, Path): Path to the model file to load or create. task (A

YOLOv8 Profile class. Usage: as a decorator with @Profile() or as a context manager with 'with Profile():'

Standard bottleneck.

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

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

Now only numpy is supported.

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

Depth-wise convolution.

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

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

YOLOv8 detections class for inference results

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

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

A class for storing and manipulating detection masks. Attributes: xy (list): A list of segments in pixel coordinates. xyn (l

ProfileModels class for profiling different models on ONNX and TensorRT. This class profiles the performance of different models, provided t

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

YOLOv5 Classification Dataset. Arguments root: Dataset path transform: torchvision transforms, used by default albu

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

x0 --> RGB feature map, x1 --> IR feature map

x0 --> RGB feature map, x1 --> IR feature map

Integral module of Distribution Focal Loss (DFL). Proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391

This class is a utility class for computing detection metrics such as precision, recall, and mean average precision (mAP) of an object detect

YOLOv8 detection model.

Early stopping class that stops training when a specified number of epochs have passed without improvement.

A custom logging filter class for removing emojis in log messages. This filter is particularly useful for ensuring compatibility with Window

Ensemble of models.

A class for collecting anonymous event analytics. Event analytics are enabled when sync=True in settings and disabled when sync=False. Run 'y

A class for exporting a model. Attributes: args (SimpleNamespace): Configuration for the exporter. save_dir (Path): Director

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

Class for generating HUB dataset JSON and `-hub` dataset directory Arguments path: Path to data.yaml or data.zip (with dat

HUB training session for Ultralytics HUB YOLO models. Handles model initialization, heartbeats, and checkpointing. Args: url (str):

Dataloader that reuses workers. Uses same syntax as vanilla DataLoader.

Dataloader that reuses workers Uses same syntax as vanilla DataLoader

A class for storing and manipulating detection keypoints. Attributes: xy (torch.Tensor): A collection of keypoints containing x, y c

YOLOv5 train_loader/val_loader, loads images and labels for training and validation.

Original Multi-Scale Deformable Attention Module. https://github.com/fundamentalvision/Deformable-DETR/blob/main/models/ops/modules/ms_deform

Updated Exponential Moving Average (EMA) from https://github.com/rwightman/pytorch-image-models Keeps a moving average of everything in the model

Mosaic augmentation. This class performs mosaic augmentation by combining multiple (4 or 9) images into a single mosaic image. The augme

A class for storing and manipulating classification predictions. Attributes: top1 (int): Index of the top 1 class. top5 (lis

RepConv is a basic rep-style block, including training and deploy status This code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvg

A task-aligned assigner for object detection. This class assigns ground-truth (gt) objects to anchors based on the task-aligned metric,

Vision Transformer https://arxiv.org/abs/2010.11929.

Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance).

Sampler that repeats forever. Args: sampler (Dataset.sampler): The sampler to repeat.

Sampler that repeats forever Args: sampler (Dataset.sampler): The sampler to repeat.

Wrap an Ultralytics YOLO model for iOS export.

YOLOv8 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS.

Base dataset class for loading and processing image data. Args: img_path (str): Path to the folder containing images. imgsz

This implementation is from mmyolo.

The BaseModel class serves as a base class for all the models in the Ultralytics YOLO family.

BasePredictor A base class for creating predictors. Attributes: args (SimpleNamespace): Configuration for the predictor.

Base tensor class with additional methods for easy manipulation and device handling.

BaseTrainer A base class for creating trainers. Attributes: args (SimpleNamespace): Configuration for the trainer. chec

BaseValidator A base class for creating validators. Attributes: dataloader (DataLoader): Dataloader to use for validation.

CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks.

CSP Bottleneck with 1 convolution.

CSP Bottleneck with 2 convolutions.

CSP Bottleneck with 2 convolutions.

CSP Bottleneck with 3 convolutions.

C3 module with GhostBottleneck().

C3 module with TransformerBlock().

C3 module with cross-convolutions.