:param features :param weights: [w0, w1, ...] :param bias: [b0, b1, ...] :return:

Convert a mask tensor to one or more bounding boxes. Note: This function is a bit new, make sure it does what it says. /Andreas :param mask:

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod

pre-allocate gpu memory for training to avoid memory Fragmentation.

Read image using opencv's imread function and returns it in rgb format

args for training.

args for training.

args for training.

Parse a PASCAL VOC xml file

Call function to perform photometric distortion on images. Args: results (dict): Result dict from loading pipeline. Return

add padding and swap dimension

add padding and swap dimension

Print the results for the given trackers in a formatted table args: trackers - List of trackers to evaluate dataset - List of seq

idx is invalid

idx is invalid

idx is invalid

Returns the original image and target at an index for mixup Note: not using self.__getitem__(), as any transformations passed in coul

serialize picklable python object to tensor

Random select some elements from the gallery. It seems that Pytorch's implementation is slower than numpy so we use numpy to randperm

Call function to randomly crop images, bounding boxes, masks, semantic segmentation maps. Args: results (dict): Result dic