Initialize the BboxLoss module with regularization maximum and DFL settings.

Initialize an ensemble of models.

Return performance metrics and optionally cropped/save images or results.

Return performance metrics and optionally cropped/save images or results.

Computes the average precision per class for object detection evaluation. Args: tp (np.ndarray): Binary array indicating whether the

Computes the average precision per class for object detection evaluation. Args: tp (np.ndarray): Binary array indicating whether the

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

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

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

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

Search/download YAML file (if necessary) and return path, checking suffix.

Search/download YAML file (if necessary) and return path, checking suffix.

Denormalizes boxes, segments, and keypoints from normalized coordinates.

Denormalizes boxes, segments, and keypoints from normalized coordinates.

Issue a deprecation warning when a deprecated argument is used, suggesting an updated argument.

Issue a deprecation warning when a deprecated argument is used, suggesting an updated argument.

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

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

YOLOv8 export formats.

YOLOv8 export formats.

Model fitness as a weighted combination of metrics.

Model fitness as a weighted combination of metrics.

Determines if the file at the given filepath is part of a pip package. Args: filepath (str): The filepath to check. Returns:

Determines if the file at the given filepath is part of a pip package. Args: filepath (str): The filepath to check. Returns:

Resize and pad image while meeting stride-multiple constraints.

Resize and pad image while meeting stride-multiple constraints.

Model information. imgsz may be int or list, i.e. imgsz=640 or imgsz=[640, 320].

Args: scale (tuple | list | int): the scale for four coords.

Args: scale (tuple | list | int): the scale for four coords.

Method used for CLI prediction. It uses always generator as outputs as not required by CLI mode.

Method used for CLI prediction. It uses always generator as outputs as not required by CLI mode.

Prune a linear layer (a model parameters) to keep only entries in index. Return the pruned layer as a new layer with requires_grad=True.

Prune a linear layer (a model parameters) to keep only entries in index. Return the pruned layer as a new layer with requires_grad=True.

Prune a linear layer (a model parameters) to keep only entries in index. Return the pruned layer as a new layer with requires_grad=True.

Runs all registered callbacks for a specific event.

Runs all registered callbacks for a specific event.

PyTorch-accurate time.

PyTorch-accurate time.

Decorator to make all processes in distributed training wait for each local_master to do something.

Decorator to make all processes in distributed training wait for each local_master to do something.

Returns transform of the loaded model.

Returns transform of the loaded model.

wrap action, get obs if video_option

Load a YOLOv8 model from a YAML file.

Load a YOLOv8 model from a YAML file.

Initialize YOLO network with default parameters and Convolutional Layers.

Initialize YOLO network with default parameters and Convolutional Layers.

Return an activation function given a string

Return an activation function given a string

Return an activation function given a string

Logs images to the experiment with optional annotations.

Logs images to the experiment with optional annotations.

Perform a forward pass through the network. Args: x (torch.Tensor): The input tensor to the model. profile (

Perform a forward pass through the network. Args: x (torch.Tensor): The input tensor to the model. profile (

Return an InfiniteDataLoader or DataLoader for training or validation set.

Return an InfiniteDataLoader or DataLoader for training or validation set.

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

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

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

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).

Reverses the order of the bounding boxes and segments horizontally.

Reverses the order of the bounding boxes and segments horizontally.

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

Compute the output size given input size and target long side length.

Compute the output size given input size and target long side length.