Load a config from a Python source file.

Merge config dictionary a into config dictionary b, clobbering the options in b whenever they are also specified in a.

Enumerate a set of anchors for each aspect ratio wrt an anchor.

Enumerate a set of anchors for each scale wrt an anchor.

Recursively convert all CfgNode objects to dict objects.

Arguments: proposals: list[BoxList] targets: list[BoxList]

Strategy: suppose that the models that we will create will have prefixes appended to each of its keys, for example due to an extra level of n

Arguments: dataset_list (list[str]): Contains the names of the datasets, i.e., coco_2014_trian, coco_2014_val, etc tr

Constructs a new box head. By default, uses ROIBoxHead, but if it turns out not to be enough, just register a new class and make it a par

This gives the gist of it. Not super important because it doesn't change as much

Creates a basic transformation that was used to train the models

r"""Loads the Torch serialized object at the given URL. If the object is already present in `model_dir`, it's deserialized and returned. The f

Calculate average precisions based on evaluation code of PASCAL VOC. This function calculates average precisions from given precisions and rec

Calculate precision and recall based on evaluation code of PASCAL VOC. This function calculates precision and recall of predicted bounding box

Arguments: original_image (np.ndarray): an image as returned by OpenCV Returns: prediction (BoxList): the de

Convert from cityscapes format to COCO instance seg format - polygons

Convert to png and save json with path. This currently only contains the segmentation labels for objects+stuff in cocostuff - if we need to co

Create a montage showing the probability heatmaps for each one one of the detected objects Arguments: image (np.

Cropss a rectangular region from this bounding box. The box is a 4-tuple defining the left, upper, right, and lower pixel coo

Make this CfgNode and all of its children mutable.

Dump to a string.

Evaluate on voc dataset. Args: pred_boxlists(list[BoxList]): pred boxlist, has labels and scores fields. gt_boxlists(list[BoxList]

Evaluate detection proposal recall metrics. This function is a much faster alternative to the official COCO API recall evaluation code. However,

Returns bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS).

Arguments: x (Tensor): the mask logits boxes (list[BoxList]): bounding boxes that are used as referen

Arguments: anchors: list[BoxList] objectness: tensor of size N, A, H, W box_regression: tensor of size N,

Return mutability.

Given a set of BoxList containing the `labels` field, return a set of BoxList for which `labels > 0`. Arguments: boxes (list of

Load a cfg. Supports loading from: - A file object backed by a YAML file - A file object backed by a Python source file that exports a

Merge `cfg_other` into this CfgNode.