Sends the model to the given device. Args: device (str): device

Prints model information Args: verbose (bool): if True, prints out the model information. Defaults to False

Raises TypeError is model is not a PyTorch model

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

Implement random crop image image_name: for example img_0.jpg image_dir: original image directory label_dir: orri

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

Loads a single model weights.

Run forward pass on input image(s) with optional augmentation and profiling.

Fuse the `Conv2d()` and `BatchNorm2d()` layers of the model into a single layer, in order to improve the computation efficiency.

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

Resize and pad image while meeting stride-multiple constraints.

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

Load a YOLOv8 model from a YAML file.

Clip YOLOv5 augmented inference tails.

De-scale predictions following augmented inference (inverse operation).

Perform augmentations on input image x and return augmented inference and train outputs.

Initializes a new model and infers the task type from the model definitions. Args: cfg (str): model configuration fi

Profile the computation time and FLOPs of a single layer of the model on a given input. Appends the results to the provided list.

Initialize Detect() biases, WARNING: requires stride availability.

Guess from YAML dictionary.

Check source type and return corresponding flag values.

Clamps bounding box coordinates to be within image boundaries [0, dim).

Clamps keypoint coordinates to be within image boundaries [0, dim).

Takes a path to a YOLO model's YAML file as input and extracts the size character of the model's scale. The function uses regular expressio

Hard Mish Experimental, based on notes by Mish author Diganta Misra at https://github.com/digantamisra98/H-Mish/blob/0da20d4bc58e696b6803f2

Hard Mish Experimental, based on notes by Mish author Diganta Misra at https://github.com/digantamisra98/H-Mish/blob/0da20d4bc58e696b6803f2

Check if the model has less than a certain threshold of BatchNorm layers. Args: thresh (int, optional): The threshol

Mish: A Self Regularized Non-Monotonic Neural Activation Function - https://arxiv.org/abs/1908.08681 NOTE: I don't have a working inplace variant

Mish: A Self Regularized Non-Monotonic Neural Activation Function - https://arxiv.org/abs/1908.08681

Pre-tranform input image before inference. Args: im (List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list.

Swish - Described in: https://arxiv.org/abs/1710.05941

Swish - Described in: https://arxiv.org/abs/1710.05941

Calls the 'predict' function with given arguments to perform object detection.