![]() _new: Initializes a new model based on a configuration file. Methods: _call_: Alias for the predict method, enabling the model instance to be callable. task (str): The type of task the model is intended for. session (HUBTrainingSession): The Ultralytics HUB session, if applicable. metrics (dict): The latest training/validation metrics. ![]() overrides (dict): A dictionary of overrides for model configuration. ckpt_path (str): The path to the checkpoint file. cfg (str): The configuration of the model if loaded from a *.yaml file. ckpt (dict): The checkpoint data if the model is loaded from a *.pt file. trainer (BaseTrainer): The trainer object used for training the model. model (nn.Module): The underlying PyTorch model. predictor (BasePredictor): The predictor object used for making predictions. Attributes: callbacks (dict): A dictionary of callback functions for various events during model operations. verbose (bool, optional): If True, enables verbose output during the model's operations. This can be used to specify the model's application domain, such as object detection, segmentation, etc. task (Any, optional): The task type associated with the YOLO model. This can be a local file path, a model name from Ultralytics HUB, or a Triton Server model. Args: model (Union, optional): Path or name of the model to load or create. The class is designed to be flexible and extendable for different tasks and model configurations. It handles different types of models, including those loaded from local files, Ultralytics HUB, or Triton Server. This class provides a common interface for various operations related to YOLO models, such as training, validation, prediction, exporting, and benchmarking. Module ): """ A base class for implementing YOLO models, unifying APIs across different model types.
0 Comments
Leave a Reply. |