Initializes the YOLO model. Args: model (Union[str, Path], optional): Path or name of the model to load or create. D

`_apply()` is a function that applies a function to all the tensors in the model that are not parameters or registered buffers

Initializes a new model and infers the task type from the model head. Args: weights (str): model checkpoint to be lo

Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a.

Forward pass of the model on a single scale. Wrapper for `_forward_once` method. Args: x (torch.Tensor): Th

Concatenates and returns predicted bounding boxes and class probabilities.

Arguments: x: Tensor, shape ``[seq_len, batch_size, embedding_dim]``

Fuse PyTorch Conv2d and BatchNorm2d layers.

Activation Function Factory Fetching activation fns by name with this function allows export or torch script friendly functions to be returne

Transfers parameters with matching names and shapes from 'weights' to model.

Loads an inference source for object detection and applies necessary transformations. Args: source (str, Path, Tensor, PIL.Image

Implement mosaic augmentation image_file_list: list of 4 images (only name of image, not path), [img_1.jpg, img_2.jpg, img_3.png, i

Prepares input image before inference. Args: im (torch.Tensor | List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list.

Resets the model modules parameters to randomly initialized values, losing all training information.