Get a copy of the default config. Returns: a detectron2 CfgNode instance.

Normalize, pad and batch the input images.

Args: input_ch(int) : the number of input channel out_features (list[str]): name of the layers whose outputs should

1x1 convolution

3x3 convolution with padding

3x3 convolution with padding

Args: bottom_up (Backbone): module representing the bottom up subnetwork. Must be a subclass of :class:`Backbone`

Greed decoder to obtain length from logit

Transform data back to its original space. In other words, return an input X_original whose transform would be X. Parameters

Performs non-maximum suppression on a boxlist, with scores specified in a boxlist field via score_field. Args: boxlist (dete

Args: crop_instance (bool): if False, extend cropping boxes to avoid cropping instances

Map each box in `box_lists` to a feature map level index and return the assignment vector. Args: box_lists (list[detectron2.stru

Create a ResNet instance from config. Returns: ResNet: a :class:`ResNet` instance.

Create a VoVNet instance from config. Returns: VoVNet: a :class:`VoVNet` instance.

Returns a Unicode object on success, or None on failure

In addition to the post processing of detectron2, we add scalign for bezier control points.

Apply dimensionality reduction to X. X is projected on the first principal components previously extracted from a training set.

Args: batched_inputs: a list, batched outputs of :class:`DatasetMapper` . Each item in the list contains the inpu

Generate a CropTransform so that the cropping region contains the center of the given instance. Args: crop_size (tuple): h, w in

Returns the labels of the corresponding text.

Validate the format of the line. If the line is not valid an exception will be raised. If maxWidth and maxHeight are specified, all points mu

Validate the format of the line. If the line is not valid an exception will be raised. If maxWidth and maxHeight are specified, all points mu

Resize image to a given size. Args: img (ndarray): The input image. size (tuple[int]): Target size (w, h). return_scale (b

Apply the inverse sigmoid operation. y = -ln(1-x/x)

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

Args: label: shape (n1, n2, ..., ) depth: a scalar Returns: onehot: (n1, n2, ..., depth)

Returns a Polygon object to use with the Polygon2 class from a list of 8 points: x1,y1,x2,y2,x3,y3,x4,y4

Visualizes predictions on frames of the input video. Args: video (cv2.VideoCapture): a :class:`VideoCapture` object, who

Validates that the points that the 4 points that dlimite a polygon are in clockwise order.

Args: cfg (CfgNode): num_gpus (int): if 0, will run on CPU