Raises TypeError is model is not a PyTorch model.

Raises TypeError is model is not a PyTorch model.

Convert bounding box format.

Convert bounding box format.

De-parallelize a model: returns single-GPU model if model is of type DP or DDP.

De-parallelize a model: returns single-GPU model if model is of type DP or DDP.

* :ref:`API in English <SpikingRNNBase.states_num-en>` .. _SpikingRNNBase.states_num-cn: :return: 状态变量的数量。例如对于 :class:`~spi

Adds text to an image using PIL or cv2.

Load and merge configuration data from a file or dictionary. Args: cfg (str | Path | Dict | SimpleNamespace): Configuration data.

Load and merge configuration data from a file or dictionary. Args: cfg (str | Path | Dict | SimpleNamespace): Configuration data.

Logs model info. Args: detailed (bool): Show detailed information about model. verbose (bool): Controls verb

Logs model info. Args: detailed (bool): Show detailed information about model. verbose (bool): Controls verb

Compute the IoU between a set of boxes b1 and 1 box b2

Check if the current script is running inside a Google Colab notebook. Returns: (bool): True if running inside a Colab notebook, Fal

Check if the current script is running inside a Google Colab notebook. Returns: (bool): True if running inside a Colab notebook, Fal

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

Update confusion matrix for object detection task. Args: detections (Array[N, 6]): Detected bounding boxes and their ass

Update confusion matrix for object detection task. Args: detections (Array[N, 6]): Detected bounding boxes and their ass

Downloads files from a URL, with options for retrying, unzipping, and deleting the downloaded file. Args: url (str): The URL of the

Downloads files from a URL, with options for retrying, unzipping, and deleting the downloaded file. Args: url (str): The URL of the

Selects the appropriate PyTorch device based on the provided arguments. The function takes a string specifying the device or a torch.device

Selects the appropriate PyTorch device based on the provided arguments. The function takes a string specifying the device or a torch.device

Save YAML data to a file. Args: file (str, optional): File name. Default is 'data.yaml'. data (dict): Data to save in YAML f

Save YAML data to a file. Args: file (str, optional): File name. Default is 'data.yaml'. data (dict): Data to save in YAML f

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

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

Strip auth from URL, i.e. https://url.com/file.txt?auth -> https://url.com/file.txt.

Strip auth from URL, i.e. https://url.com/file.txt?auth -> https://url.com/file.txt.

Returns device if PyTorch model.

Return save_dir as created from train/val/predict arguments.

Return save_dir as created from train/val/predict arguments.

Mean of results, return mp, mr, map50, map.

Mean of results, return mp, mr, map50, map.

* :ref:`API in English <SpikingRNNCellBase.reset_parameters-en>` .. _SpikingRNNCellBase.reset_parameters-cn: 初始化所有可学习参数。

Saves the current settings to the YAML file.

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

* :ref:`API in English <SpikingRNNBase.base_cell-en>` .. _SpikingRNNBase.base_cell-cn: :return: 构成该RNN的基本RNN Cell。例如对于 :cla

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

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

Class-aware result, return p[i], r[i], ap50[i], ap[i].

Class-aware result, return p[i], r[i], ap50[i], ap[i].

Denormalizes boxes, segments, and keypoints from normalized coordinates.

Increments a file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. If the path exists and exist_ok is not set t

Increments a file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc. If the path exists and exist_ok is not set t

Determines whether the current file is part of a git repository. If the current file is not part of a git repository, returns None. Retu

Determines whether the current file is part of a git repository. If the current file is not part of a git repository, returns None. Retu

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:

Generate anchors from features.

Return model info dict with useful model information. Example: YOLOv8n info for loggers ```python results = {'model/

Return model info dict with useful model information. Example: YOLOv8n info for loggers ```python results = {'model/

Makes an HTTP request using the 'requests' library, with exponential backoff retries up to a specified timeout. Args: method (str):

Makes an HTTP request using the 'requests' library, with exponential backoff retries up to a specified timeout. Args: method (str):

Initialize the BboxLoss module with regularization maximum and DFL settings.

Initialize an ensemble of models.

Args: dim (int): Number of input channels. num_heads (int): Number of attention heads in each ViT block.

Initialize the BboxLoss module with regularization maximum and DFL settings.

Initialize an ensemble of models.

Args: dim (int): Number of input channels. num_heads (int): Number of attention heads in each ViT block.

* :ref:`API in English <LatencyEncoder.__init__-en>` .. _LatencyEncoder.__init__-cn: :param T: 最大（最晚）脉冲发放时刻 :type T

Applies a function to all non-empty attributes and returns a new Results object with modified attributes. This function is internally

Applies a function to all non-empty attributes and returns a new Results object with modified attributes. This function is internally

Logs plots from the input dictionary if they haven't been logged already at the specified step.

Logs plot images for training progress if they have not been previously processed.

Logs plots from the input dictionary if they haven't been logged already at the specified step.

Logs plot images for training progress if they have not been previously processed.

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

Loads a single model weights.