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

Returns: output (VisImage): the image output containing the visualizations added to the image.

An initializer which allows initializing model parameters in "blocks". This is helpful in the case of recurrent models which use multiple

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

gt_ids are mapped from previous Hungarian matchinmg results. ~[0,99]

:param labels: [batch_size, 2] :return:

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to re

Creates a [size, num_classes] torch FloatTensor where one_hot[i, vec[i]] = fill :param vec: 1d torch tensor :param num_classes: int

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

Convert [x1 y1 w h] box format to [x1 y1 x2 y2] format.

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

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

encode proposed box information (x1, y1, x2, y2) to (cx/wid, cy/hei, w/wid, h/hei, x1/wid, y1/hei, x2/wid, y2/hei, wh/wid*hei)

**kwargs: contain the paramteters specifically for OD, e.g., proposal_nums. Overwritten evaluate API: For each metric in

once get, it is fixed all the time.

Given two arrays [m1, n], [m2,n], returns a [m1, m2] array where each entry is True if those rows match. :param x1: [m1, n] numpy array :

Parameters ---------- seg_mask : np.ndarray Boolean mask containing segmented object, (H, W) Returns ------- Tuple[i

Test without Augmentation; convert panoptic segments to bounding boxes.

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

Returns the indices that sort scores descending in a smart way. :param scores: Numpy array of arbitrary size :return: an array of size [numel

Test without augmentation. Used in SGG. Return: det_bboxes: (list[Tensor]): The boxes may have 5 columns (sgdet) or 4 columns (pr

Test without augmentation. Used in SGG. Return: det_bboxes: (list[Tensor]): The boxes may have 5 columns (sgdet)

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

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

input: [batch_size, (x1,y1,x2,y2)] size: [h, w] output: [batch_size, (x1,y1,x2,y2,cx,cy,w,h)]

for test forward. :param det_result: :return:

Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t

Calculate districution and predict/sample labels Add to lstm_IO.

We'll sort everything scorewise from Hi->low, BUT we need to keep images together and sort LSTM from l. :param im_inds: Which im we're on

Convert [x1 y1 x2 y2] box format to [xc yc w h] format.

Convert different format of boxes to an NxB array, where B = 4 or 5 is the box dimension.

Convert different format of masks or polygons to a tuple of masks and polygons. Returns: list[GenericMask]:

Transform outputs from the last decoder layer into bbox predictions for each image. Args: h_cls_score/o_cls_score/i_cls_s