r"""Create VectorEnv object with specified config and env class type. To allow better performance, dataset are split into small ones for each

r"""Create VectorEnv object with specified config and env class type. To allow better performance, dataset are split into small ones for each

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.

Extracts instruction tokens from an instruction sensor if the tokens exist and are in a dict structure.

Extracts instruction tokens from an instruction sensor if the tokens exist and are in a dict structure.

Extracts instruction tokens from an instruction sensor if the tokens exist and are in a dict structure.

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

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

Returns a loss dict with labelled training loss items tensor

Returns a loss dict with labelled training loss items tensor

Return a new Results object with the same image, path, and names.

Update the boxes, masks, and probs attributes of the Results object.

Update the boxes, masks, and probs attributes of the Results object.

Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height) format. Args: x (np.ndarray | torch.Tensor):

Convert bounding box coordinates from (x1, y1, x2, y2) format to (x, y, width, height) format. Args: x (np.ndarray | torch.Tensor):

Verify image size is a multiple of the given stride in each dimension. If the image size is not a multiple of the stride, update it to the ne

Convert bounding box format.

Convert bounding box format.

Return a copy of the Results object with all tensors on GPU memory.

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

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

Return a new Results object with the same image, path, and names.

Selects PyTorch Device. Options are device = None or 'cpu' or 0 or '0' or '0,1,2,3'.

Selects PyTorch Device. Options are device = None or 'cpu' or 0 or '0' or '0,1,2,3'.

Function trains models but raises an error as NAS models do not support training.

Function trains models but raises an error as NAS models do not support training.

Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the top-left corner and (x2,

Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the top-left corner and (x2,

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

Raises TypeError is model is not a PyTorch model

Raises TypeError is model is not a PyTorch model

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

Loads a single model weights.

Loads a single model weights.

Verify image size is a multiple of the given stride in each dimension. If the image size is not a multiple of the stride, update it to the ne

r"""Create VectorEnv object with specified config and env class type. To allow better performance, dataset are split into small ones for each

Filter the MaskData object based on the given boolean tensor.

Plot the confusion matrix using seaborn and save it to a file. Args: normalize (bool): Whether to normalize the confusio

Plot the confusion matrix using seaborn and save it to a file. Args: normalize (bool): Whether to normalize the confusio

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

Add rectangle to image (PIL-only).

Add rectangle to image (PIL-only).

Conv1D layer as defined by Radford et al. for OpenAI GPT (and also used in GPT-2) Basically works like a Linear layer but the weights are

Conv1D layer as defined by Radford et al. for OpenAI GPT (and also used in GPT-2) Basically works like a Linear layer but the weights are

Conv1D layer as defined by Radford et al. for OpenAI GPT (and also used in GPT-2) Basically works like a Linear layer but the weights are

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.

Filter the MaskData object based on the given boolean tensor.

r"""Create a unified config with default values. Initialized from the habitat_baselines default config. Overwritten by values from `config_pat

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

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

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

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

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

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

Return the class values of the boxes.

Converts bounding box format from one type to another.

Converts bounding box format from one type to another.

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

Return model info dict with useful model information. Example for YOLOv8n: {'model/parameters': 3151904, 'model/GFLOPs': 8.

Return model info dict with useful model information. Example for YOLOv8n: {'model/parameters': 3151904, 'model/GFLOPs': 8.

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

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):

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.