Loads a single model weights.

Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4). Args: box1 (torch.Tensor): A tensor representing a single bound

Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4). Args: box1 (torch.Tensor): A tensor representing a single bound

Download, verify, and/or unzip a dataset if not found locally. This function checks the availability of a specified dataset, and if not foun

Download, verify, and/or unzip a dataset if not found locally. This function checks the availability of a specified dataset, and if not foun

This function checks for any mismatched keys between a custom configuration list and a base configuration list. If any mismatched keys are fo

This function checks for any mismatched keys between a custom configuration list and a base configuration list. If any mismatched keys are fo

Verify image size is a multiple of the given stride in each dimension. If the image size is not a multiple of the stride, update it to the ne

Verify image size is a multiple of the given stride in each dimension. If the image size is not a multiple of the stride, update it to the ne

Denormalizes boxes, segments, and keypoints from normalized coordinates.

YOLOv8 export formats.

YOLOv8 export formats.

Model fitness as a weighted combination of metrics.

Model fitness as a weighted combination of metrics.

Load the weights into the model. Args: weights (dict | torch.nn.Module): The pre-trained weights to be loaded.

Load the weights into the model. Args: weights (dict | torch.nn.Module): The pre-trained weights to be loaded.

Generate anchors from features.

Logs the benchmarking results of a model, checks metrics against floor and returns the results.

Logs the benchmarking results of a model, checks metrics against floor and returns the results.

Runs all registered callbacks for a specific event.

Runs all registered callbacks for a specific event.

PyTorch-accurate time.

PyTorch-accurate time.

Initializes MixUp object with dataset, pre_transform, and probability of applying MixUp.

Initialize YOLO network with default parameters and Convolutional Layers.

Initializes MixUp object with dataset, pre_transform, and probability of applying MixUp.

Initialize YOLO network with default parameters and Convolutional Layers.

Builds the selected SAM model architecture.

Builds the selected SAM model architecture.

Logs images to the experiment with optional annotations.

Logs images to the experiment with optional annotations.

Load model/trainer/validator/predictor.

Load model/trainer/validator/predictor.

Compute the areas for a set of 2D boxes

Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.

Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.

Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Based on https://gith

Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Based on https://gith

Return an InfiniteDataLoader or DataLoader for training or validation set.

Return an InfiniteDataLoader or DataLoader for training or validation set.

Search/download file (if necessary) and return path.

Search/download file (if necessary) and return path.

1x1 convolution

1x1 convolution

Converts bounding box format from one type to another.

Converts bounding box format from one type to another.

:param source_dir: Path of the directory that be copied from :type source_dir: str :param target_dir: Path of the directory that be copie

It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box. Args: masks (torch.Tensor): [n, h, w] te

It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box. Args: masks (torch.Tensor): [n, h, w] te

Return a copy of the Results object with all tensors on GPU memory.

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

Export model. Args: **kwargs : Any other args accepted by the Exporter. To see all args check 'configuration' section in

Export model. Args: **kwargs : Any other args accepted by the Exporter. To see all args check 'configuration' section in

Returns a list of HUB-supported export formats.

Returns a list of HUB-supported export formats.

Return file/dir size (MB).

Return file/dir size (MB).

Function generates the YOLO network's final layer.

Function generates the YOLO network's final layer.

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

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

Guess the task of a PyTorch model from its architecture or configuration. Args: model (nn.Module | dict): PyTorch model or model con

Guess the task of a PyTorch model from its architecture or configuration. Args: model (nn.Module | dict): PyTorch model or model con

Check if a directory is writeable. Args: dir_path (str | Path): The path to the directory. Returns: (bool): True if the

Check if a directory is writeable. Args: dir_path (str | Path): The path to the directory. Returns: (bool): True if the

Return a new Results object with the same image, path, and names.

Return a new Results object with the same image, path, and names.

Plot training results from a results CSV file. The function supports various types of data including segmentation, pose estimation, and class

Plot training results from a results CSV file. The function supports various types of data including segmentation, pose estimation, and class

Compute AP given precision-recall pr is a Nx2 array with first row being precision and second row being recall

Perform prediction using the YOLO model. Args: source (str | int | PIL | np.ndarray): The source of the image to make pr

Perform prediction using the YOLO model. Args: source (str | int | PIL | np.ndarray): The source of the image to make pr

* :ref:`API in English <Monitor.reset-en>` .. _Monitor.reset-cn: 清空之前的记录数据 * :ref:`中文API <Monitor.reset-cn>`

Runs all callbacks associated with a specified event.

Runs all callbacks associated with a specified event.

This might be similar with denormalize func but without normalized sign.

:param x_seq: shape=[T, batch_size, ...] :type x_seq: Tensor :param stateless_module: a stateless module, e.g., 'torch.nn.Conv2d' or a li