Update labels

Update labels

apply affine to bboxes only. Args: bboxes(ndarray): list of bboxes, xyxy format, with shape (num_bboxes, 4). M(ndarra

apply affine to keypoints. Args: keypoints(ndarray): keypoints, [N, 17, 2]. M(ndarray): affine matrix. Return

apply affine to segments and generate new bboxes from segments. Args: segments(ndarray): list of segments, [num_samples, 500, 2].

Attempt to fetch authentication via cookies and set id_token. User must be logged in to HUB and running in a supported browser.

Transform bbox(xyxy) to dist(ltrb).

> Builds an optimizer with the specified parameters and parameter groups. Args: model (nn.Module): model to optimize

Users can custom augmentations here like: if self.augment: # training transforms return Compose([]

Check internet connectivity by attempting to connect to a known online host. Returns: bool: True if connection is successful, False

Check current python version against the required minimum version. Args: minimum (str): Required minimum version of python. Ret

> It takes a list of line segments (x1,y1,x2,y2) and clips them to the image shape (height, width) Args: segments: a list of segments,

Compute the average precision, given the recall and precision curves # Arguments recall: The recall curve (list) precision: Th

Finds a free port on localhost. It is useful in single-node training when we don't want to connect to a real main node but have to set the `M

Runs inference on the given model Args: im: the image tensor augment: whether to augment the image. Defaults to

> Get train, val path from data dict if it exists. Returns None if data format is not recognized.

Determines whether the current file is part of a git repository and if so, returns the repository root directory. If the current file is not

Read image files.

Users can custom their own format here. Make sure your output is a list with each element like below: dict( im_fil

Loads a global settings YAML file or creates one with default values if it does not exist. Args: file (Path): Path to the settings Y

Get the authentication state

Args: gt_labels: (b, max_num_obj, 1) gt_bboxes: (b, max_num_obj, 4) target_gt_idx: (b, h*w) f

Get the user config directory. Args: sub_dir (str): The name of the subdirectory to create. Returns: Path: The path to

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

Determine if the script is running inside a Docker container. Returns: bool: True if the script is running inside a Docker container

Check if the current script is running inside a Jupyter Notebook. Verified on Colab, Jupyterlab, Kaggle, Paperspace. Returns: bo

> Convert nx4 boxes from [x1, y1, w, h] to [x, y, w, h] where xy1=top-left, xy=center Args: x: the input tensor

> It converts the bounding box from [x1, y1, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right Args: x: the input ima

Mean AP@0.5:0.95 of all classes. Return: float.

mask1: [N, n] m1 means number of predicted objects mask2: [M, n] m2 means number of gt objects Note: n means image_w x image_h return

Plot masks at once. Args: masks (tensor): predicted masks on cuda, shape: [n, h, w] colors (List[List[Int]]): colors f