r"""Return a sorted list of scenes

Guess the task of a PyTorch model from its architecture or configuration. Args: model (nn.Module | dict): PyTorch model or model con

Guess the task of a PyTorch model from its architecture or configuration. Args: model (nn.Module | dict): PyTorch model or model con

Define label paths as a function of image paths.

Define label paths as a function of image paths.

Check if a directory is writeable. Args: dir_path (str | Path): The path to the directory. Returns: (bool): True if the

Check if a directory is writeable. Args: dir_path (str | Path): The path to the directory. Returns: (bool): True if the

Check if the current script is running inside a Kaggle kernel. Returns: (bool): True if running inside a Kaggle kernel, False otherw

Check if the current script is running inside a Kaggle kernel. Returns: (bool): True if running inside a Kaggle kernel, False otherw

Generate anchors from features.

Generate anchors from features.

Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv').

Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv').

Perform prediction using the YOLO model. Args: source (str | int | PIL | np.ndarray): The source of the image to make pr

Perform prediction using the YOLO model. Args: source (str | int | PIL | np.ndarray): The source of the image to make pr

Runs all callbacks associated with a specified event.

Runs all callbacks associated with a specified event.

Set up YOLO model with specified thresholds and device.

Return gridworld index of realworld coordinates assuming top-left corner is the origin. The real world coordinates of lower left corner are (c

Return gridworld index of realworld coordinates assuming top-left corner is the origin. The real world coordinates of lower left corner are (c

Adds text to an image using PIL or cv2.

Adds text to an image using PIL or cv2.

angle: 0 ~ 360 degree

Read stream `i` frames in daemon thread.

Update a matched track :type new_track: STrack :type frame_id: int :return:

Read stream `i` frames in daemon thread.

Update a matched track :type new_track: STrack :type frame_id: int :return:

Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt.

Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt.

Run validation given dataset.

Run validation given dataset.

Convert normalized bounding box coordinates to pixel coordinates. Args: x (np.ndarray | torch.Tensor): The bounding box coordinates.

Convert normalized bounding box coordinates to pixel coordinates. Args: x (np.ndarray | torch.Tensor): The bounding box coordinates.

Initialize the Boxes class.

Args: equ_h: (int) the height of the generated equirect equ_w: (int) the width of the generated equirect

Initialize the Boxes class.

Args: equ_h: (int) the height of the generated equirect equ_w: (int) the width of the generated equirect

Builds the selected SAM model architecture.

Builds the selected SAM model architecture.

Returns metadata for YOLO training including epoch and asset saving status.

Returns metadata for YOLO training including epoch and asset saving status.

Log scalars to the NeptuneAI experiment logger.

Log scalars to the NeptuneAI experiment logger.

r"""Helper method to get the scene name from an episode. Assumes the scene_id is formated /path/to/<scene_name>.<ext>

r"""Helper method to get the scene name from an episode. Assumes the scene_id is formated /path/to/<scene_name>.<ext>

Separate the input tensor into the specified number of attention heads.

Separate the input tensor into the specified number of attention heads.

r"""Appends text underneath an image of size (height, width, channels). The returned image has white text on a black background. Uses textwrap to

Expects a numpy array of length 2 in the final dimension. Requires the original image size in (H, W) format.

Expects a numpy array of length 2 in the final dimension. Requires the original image size in (H, W) format.

Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.

Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.

Attempt to authenticate with the server using either id_token or API key. Returns: bool: True if authentication is succe

Attempt to authenticate with the server using either id_token or API key. Returns: bool: True if authentication is succe

Decode predicted object bounding box coordinates from anchor points and distribution.

Decode predicted object bounding box coordinates from anchor points and distribution.

Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format. Args: box1 (np.array): A numpy array of

Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format. Args: box1 (np.array): A numpy array of

Add one xyxy box to image with label.

Add one xyxy box to image with label.

Check class names. Map imagenet class codes to human-readable names if required. Convert lists to dicts.

Check class names. Map imagenet class codes to human-readable names if required. Convert lists to dicts.

Download, check and/or unzip dataset if not found locally.

Download, check and/or unzip dataset if not found locally.

Check file(s) for acceptable suffix.

Check file(s) for acceptable suffix.

It takes a list of bounding boxes and a shape (height, width) and clips the bounding boxes to the shape Args: boxes (torch.Tensor)

It takes a list of bounding boxes and a shape (height, width) and clips the bounding boxes to the shape Args: boxes (torch.Tensor)

Return the class values of the boxes.

Convert a bounding box's top-left-width-height format to its x-y-angle-height equivalent.

Convert a bounding box's top-left-width-height format to its x-y-angle-height equivalent.

YOLOv8 ONNX export.

YOLOv8 ONNX export.

Flips the coordinates of bounding boxes, segments, and keypoints vertically.

Flips the coordinates of bounding boxes, segments, and keypoints vertically.

Make HTTP requests with retries and timeouts, with optional progress tracking.

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

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

Generates masks for the given image. Arguments: image (np.ndarray): The image to generate masks for, in HWC uint8 format.