Efficient version of torch.cat that avoids a copy if there is only a single element in a list

Returns a resized copy of this bounding box :param size: The requested size in pixels, as a 2-tuple: (width, height).

Recursively copy this CfgNode.

Helper function to synchronize between multiple processes when using distributed training

Compute the intersection over union of two set of boxes. The box order must be (xmin, ymin, xmax, ymax). Arguments: box1: (BoxList) bou

From a set of original boxes and encoded relative box offsets, get the decoded boxes. Arguments: rel_codes (Tens

Returns the state of the scheduler as a :class:`dict`. It contains an entry for every variable in self.__dict__ which is not the opti

Concatenates a list of BoxList (having the same image size) into a single BoxList Arguments: bboxes (list[BoxList])

Encode a set of proposals with respect to some reference boxes Arguments: reference_boxes (Tensor): reference bo

Make this CfgNode and all of its children immutable.

Loads the schedulers state. Arguments: state_dict (dict): scheduler state. Should be an object returned from a ca

Load a yaml config file and merge it this CfgNode.

Merge config (keys, values) in a list (e.g., from command line) into this CfgNode. For example, `cfg_list = ['FOO.BAR', 0.5]`.

tensors can be an ImageList, a torch.Tensor or an iterable of Tensors. It can't be a numpy array. When tensors is an iterable of Tensors,

Transpose bounding box (flip or rotate in 90 degree steps) :param method: One of :py:attr:`PIL.Image.FLIP_LEFT_RIGHT`, :py:

Arguments: cfg : config in_channels (int): number of channels of the input feature num_ancho

Efficient version of torch.cat that avoids a copy if there is only a single element in a list

Checks that `replacement`, which is intended to replace `original` is of the right type. The type is correct if it matches exactly or is one of a

Decodes a raw config value (e.g., from a yaml config files or command line argument) into a Python object.

Set immutability to is_immutable and recursively apply the setting to all nested CfgNodes.

Load a config from a YAML string encoding.

Given a vector of widths (ws) and heights (hs) around a center (x_ctr, y_ctr), output a set of anchors (windows).

Return width, height, x center, and y center for an anchor (window).

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

Simple function that adds fixed colors depending on the class

evaluate dataset using different methods based on dataset type. Args: dataset: Dataset object predictions(list[BoxList]): each ite

Generates a matrix of anchor boxes in (x1, y1, x2, y2) format. Anchors are centered on stride / 2, have (approximate) sqrt areas of the specified

Test if a key is deprecated.

Test if a key is renamed.

very similar to the smooth_l1_loss from pytorch, but with the extra beta parameter

Generate anchor (reference) windows by enumerating aspect ratios X scales wrt a reference (0, 0, base_size - 1, base_size - 1) window.

Load a config from a YAML file or a Python source file.