Build a dataloader for object detection with some default features. This interface is experimental. Args: dataset (list or torch

A wrapper around :function:`torch.nn.functional.grid_sample` to support 3D point_coords tensors. Unlike :function:`torch.nn.functional.grid_s

Depending on the brightness_factor, gives a lighter or darker color i.e. a color with less or more saturation than the original color

Args: filepath (str): a string that contains the absolute path, including the file name, where the visualized ima

Return an activation function given a string

Args: binary_mask (ndarray): numpy array of shape (H, W), where H is the image height and W is the image width. E

Args: x_data (list[int]): a list containing x values of all the points being drawn. Length of list should match t

Compute the output size given input size and target long side length.

Load the key, value pairs from config_dict to opt, overriding existing values in opt if there is any.

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features t

Args: classes (list[int] or None): scores (list[float] or None): class_names (list[str] or None): is_crowd (list[

Randomly modifies given color to produce a slightly different color than the color given. Args: color (tuple[double]): a

Computes the stability score for a batch of masks. The stability score is the IoU between the binary masks obtained by thresholding the p

Args: text (str): class label position (tuple): a tuple of the x and y coordinates to place text on image.

:param features: multi-scale features from the backbone :param masks: image mask :return: enhanced multi-scale features and m

Load opt from the config files, settings in later files can override those in previous files. Args: conf_files: config file path

Args: boxes (Boxes, RotatedBoxes or ndarray): either a :class:`Boxes`, or an Nx4 numpy array of XYXY_ABS format f

Args: img: same as in __init__

Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002. Args: inputs: A float tensor of arbitrary shape.

Construct a layernorm module in the TF style (epsilon inside the square root).

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features c

Returns: bool: whether the arguments contain CfgNode and should be considered forwarded to from_config.

Create a grayscale version of the original image. The colors in masked area, if given, will be kept.

Find proper places to draw text given a binary mask.

Return an activation function given a string

Use `from_config` to obtain explicit arguments. Returns: dict: arguments to be used for cls.__init__

Calculates boxes in XYXY format around masks. Return [0,0,0,0] for an empty mask. For input shape C1xC2x...xHxW, the output shape is C1xC2x..

Similar to `build_detection_train_loader`, with default batch size = 1, and sampler = :class:`InferenceSampler`. This sampler coordinates all

Create evaluator(s) for a given dataset. This uses the special metadata "evaluator_type" associated with each builtin dataset. For your o

Returns: torch.nn.Module: It now calls :func:`detectron2.modeling.build_model`. Overwrite it if you'd like a dif

Args: segment: numpy array of shape Nx2, containing all the points in the polygon. color: color of the polygon. Refer

Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, where

Load and prepare dataset dicts for instance detection/segmentation and semantic segmentation. Args: dataset_names (str or list[str])

Returns: ndarray: the visualized image of shape (H, W, 3) (RGB) in uint8 type. The shape is scale

Sample points in [0, 1] x [0, 1] coordinate space based on their uncertainty. The unceratinties are calculated for each point using 'unce

Encodes masks to an uncompressed RLE, in the format expected by pycoco tools.

r""" Args: query, key, value: map a query and a set of key-value pairs to an output. See "Attention Is All You Need" for more

prepare targets for interactive segmentation, mainly includes: box: mask: labels: part / instance