Guess from YAML dictionary.

Checks a classification dataset such as Imagenet. This function accepts a `dataset` name and attempts to retrieve the corresponding dataset

Find font locally or download to user's configuration directory if it does not already exist. Args: font (str): Path or name of font

Sets mosaic, copy_paste and mixup options to 0.0 and builds transformations.

Crops bounding boxes to the size of the input image.

Transform distance(ltrb) to box(xywh or xyxy).

Downloads and unzips files concurrently if threads > 1, else sequentially.

Visualize feature maps of a given model module during inference. Args: x (torch.Tensor): Features to be visualized. module_t

Flips the coordinates of bounding boxes, segments, and keypoints vertically.

Function generates the YOLOv5 network's final layer.

Args: pred_bboxes (torch.Tensor): [l, b, query, 4] pred_scores (torch.Tensor): [l, b, query, num_classes]

Positionally encode points that are not normalized to [0,1].

Make HTTP requests with retries and timeouts, with optional progress tracking.

Fuse PyTorch Conv2d and BatchNorm2d layers.

Fuse parallel convolutions.

Compute gating distance between state distribution and measurements. A suitable distance threshold can be obtained from `chi2inv95`. If

TensorFlow GraphDef model output node names.

Get the authentication header for making API requests. Returns: (dict): The authentication header if id_token or API key

Return a string with system CPU information, i.e. 'Apple M2'.

Returns dataloader derived from torch.data.Dataloader.

Returns the positional encoding used to encode point prompts, applied to a dense set of points the shape of the image encoding.

Calculates the distance between tracks and detections using IOU and fuses scores.

Return a YOLO model's FLOPs.

Determines whether the current file is part of a git repository and if so, returns the repository root directory. If the current file is not

Returns a single hash value of a list of paths (files or dirs).

Get and return label information from the dataset.

Get model and raise NotImplementedError for loading cfg files.

Return the total number of parameters in a YOLO model.

Get relative positional embeddings according to the relative positions of query and key sizes. Args: q_size (int): size of qu

Handle Ultralytics HUB command-line interface (CLI) commands. This function processes Ultralytics HUB CLI commands such as login and logout.

Define label paths as a function of image paths.

Initialize object tracking with detections and scores using STrack algorithm.

Compute cost based on IoU :type atlbrs: list[tlbr] | np.ndarray :type atlbrs: list[tlbr] | np.ndarray :rtype ious np.ndarray

Determine if the script is running inside a Docker container. Returns: (bool): True if the script is running inside a Docker contain

Check if the current script is running inside a Jupyter Notebook. Verified on Colab, Jupyterlab, Kaggle, Paperspace. Returns: (b

Returns True if model is of type DP or DDP.

Plot keypoints on the image. Args: kpts (tensor): Predicted keypoints with shape [17, 3]. Each keypoint has (x, y, confidence).

Loads settings from the YAML file.

Compute loss Args: batch (dict): Batch to compute loss on preds (torch.Tensor | List[torch.Tensor]): Predict

Returns nearest x divisible by divisor.

Mark the track as removed.

Calculate masks IoU. Args: mask1 (torch.Tensor): A tensor of shape (N, n) where N is the number of ground truth objects and n is the

Update state tracks positions and covariances using a homography matrix.

Increment and return the global track ID counter.

Normalize bounding boxes, segments, and keypoints to image dimensions.

Parse one 'key=value' pair and return key and value.

Parse a YOLO model.yaml dictionary into a PyTorch model.

Plots the detection results on an input RGB image. Accepts a numpy array (cv2) or a PIL Image. Args: conf (bool): Whethe

Args: imgsz (tuple): The image size. polygons (list[np.ndarray]): [N, M], N is the number of polygons, M is the number of points(

Converts YOLO predictions to COCO JSON format.

Project state distribution to measurement space. Parameters ---------- mean : ndarray The state's mean vector (8

Project state distribution to measurement space. Parameters ---------- mean : ndarray The state's mean vector (8

Predict masks for the given input prompts, using the currently set image. Args: im (torch.Tensor): The preprocessed imag

Reactivates a previously lost track with a new detection.

Remove small disconnected regions or holes in a mask, returning the mask and a modification indicator.

Reset iterator. This is useful when we want to modify settings of dataset while training.

Return annotated image as array.

Execute all callbacks for a given event.

Save YOLO detections to a txt file in normalized coordinates in a specific format.

Box filter of fraction f.

Context manager to handle paths with spaces in their names. If a path contains spaces, it replaces them with underscores, copies the file/dir

Strip optimizer from 'f' to finalize training, optionally save as 's'. Args: f (str): file path to model to strip the optimizer from

DEPRECATED CODE in https://github.com/ultralytics/ultralytics/pull/1890/ stracks = {t.track_id: t for t in tlista} for t in tlistb:

Converts tlwh bounding box format to tlbr format.

This function attempts to load a PyTorch model with the torch.load() function. If a ModuleNotFoundError is raised, it catches the error, logs

Trains the model on a given dataset. Args: trainer (BaseTrainer, optional): Customized trainer. **kwargs (An

Returns transform of the loaded model.

Uncrop bounding boxes by adding the crop box offset.

Unzips a *.zip file to the specified path, excluding files containing strings in the exclude list. If the zipfile does not contain a single

Updates a setting value in the current settings.

Read stream `i` frames in daemon thread.

Update the YOLOv8 instance with new track and frame ID.

Upload a model checkpoint to Ultralytics HUB. Args: epoch (int): The current training epoch. weights (str):

Convert images to a size suitable for YOLOv8 training.

Warm up the model by running one forward pass with a dummy input. Args: imgsz (tuple): The shape of the dummy input tens

Add position embeddings if given.

Pretty prints a yaml file or a yaml-formatted dictionary. Args: yaml_file: The file path of the yaml file or a yaml-formatted dictio

Initialize TryExcept class with optional message and verbosity settings.