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

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`

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

Normalize, pad and batch the input images.

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.

Args: pred: Nx4 predicted bounding boxes target: Nx4 target bounding boxes Both are in the form of FCOS prediction (l, t,

Returns a Unicode object on success, or None on failure

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

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

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

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

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)

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

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

:param inputs: a list of inputs :param weights: [w0, w1, ...] :param bias: [b0, b1, ...] :return:

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

Rescale the output instances to the target size.

Rescale a size by a ratio. Args: size (tuple[int]): (w, h). scale (float): Scaling factor. Returns: tuple[int]: scaled

This function is used to transpose image first training targets to level first ones :return: level first training targets

This function is used to transpose image first training targets to level first ones :return: level first training targets

This function is used to transpose image first training targets to level first ones :return: level first training targets