boxes.py

import torch
from torch.jit.annotations import Tuple
from torch import Tensor
import torchvision


def nms(boxes: Tensor, scores: Tensor, iou_threshold: float) -> Tensor:
    """
    Performs non-maximum suppression (NMS) on the boxes according
    to their intersection-over-union (IoU).

    NMS iteratively removes lower scoring boxes which have an
    IoU greater than iou_threshold with another (higher scoring)
    box.

    If multiple boxes have the exact same score and satisfy the IoU
    criterion with respect to a reference box, the selected box is
    not guaranteed to be the same between CPU and GPU. This is similar
    to the behavior of argsort in PyTorch when repeated values are present.

    Parameters
    ----------
    boxes : Tensor[N, 4])
        boxes to perform NMS on. They
        are expected to be in (x1, y1, x2, y2) format
    scores : Tensor[N]
        scores for each one of the boxes
    iou_threshold : float
        discards all overlapping
        boxes with IoU > iou_threshold

    Returns
    -------
    keep : Tensor
        int64 tensor with the indices
        of the elements that have been kept
        by NMS, sorted in decreasing order of scores
    """
    return torch.ops.torchvision.nms(boxes, scores, iou_threshold)


@torch.jit._script_if_tracing
def batched_nms(
    boxes: Tensor,
    scores: Tensor,
    idxs: Tensor,
    iou_threshold: float,
) -> Tensor:
    """
    Performs non-maximum suppression in a batched fashion.

    Each index value correspond to a category, and NMS
    will not be applied between elements of different categories.

    Parameters
    ----------
    boxes : Tensor[N, 4]
        boxes where NMS will be performed. They
        are expected to be in (x1, y1, x2, y2) format
    scores : Tensor[N]
        scores for each one of the boxes
    idxs : Tensor[N]
        indices of the categories for each one of the boxes.
    iou_threshold : float
        discards all overlapping boxes
        with IoU > iou_threshold

    Returns
    -------
    keep : Tensor
        int64 tensor with the indices of
        the elements that have been kept by NMS, sorted
        in decreasing order of scores
    """
    if boxes.numel() == 0:
        return torch.empty((0,), dtype=torch.int64, device=boxes.device)
    # strategy: in order to perform NMS independently per class.
    # we add an offset to all the boxes. The offset is dependent
    # only on the class idx, and is large enough so that boxes
    # from different classes do not overlap
    else:
        max_coordinate = boxes.max()
        offsets = idxs.to(boxes) * (max_coordinate + torch.tensor(1).to(boxes))
        boxes_for_nms = boxes + offsets[:, None]
        keep = nms(boxes_for_nms, scores, iou_threshold)
        return keep


def remove_small_boxes(boxes: Tensor, min_size: float) -> Tensor:
    """
    Remove boxes which contains at least one side smaller than min_size.

    Arguments:
        boxes (Tensor[N, 4]): boxes in (x1, y1, x2, y2) format
        min_size (float): minimum size

    Returns:
        keep (Tensor[K]): indices of the boxes that have both sides
            larger than min_size
    """
    ws, hs = boxes[:, 2] - boxes[:, 0], boxes[:, 3] - boxes[:, 1]
    keep = (ws >= min_size) & (hs >= min_size)
    keep = keep.nonzero().squeeze(1)
    return keep


def clip_boxes_to_image(boxes: Tensor, size: Tuple[int, int]) -> Tensor:
    """
    Clip boxes so that they lie inside an image of size `size`.

    Arguments:
        boxes (Tensor[N, 4]): boxes in (x1, y1, x2, y2) format
        size (Tuple[height, width]): size of the image

    Returns:
        clipped_boxes (Tensor[N, 4])
    """
    dim = boxes.dim()
    boxes_x = boxes[..., 0::2]
    boxes_y = boxes[..., 1::2]
    height, width = size

    if torchvision._is_tracing():
        boxes_x = torch.max(boxes_x, torch.tensor(0, dtype=boxes.dtype, device=boxes.device))
        boxes_x = torch.min(boxes_x, torch.tensor(width, dtype=boxes.dtype, device=boxes.device))
        boxes_y = torch.max(boxes_y, torch.tensor(0, dtype=boxes.dtype, device=boxes.device))
        boxes_y = torch.min(boxes_y, torch.tensor(height, dtype=boxes.dtype, device=boxes.device))
    else:
        boxes_x = boxes_x.clamp(min=0, max=width)
        boxes_y = boxes_y.clamp(min=0, max=height)

    clipped_boxes = torch.stack((boxes_x, boxes_y), dim=dim)
    return clipped_boxes.reshape(boxes.shape)


def box_area(boxes: Tensor) -> Tensor:
    """
    Computes the area of a set of bounding boxes, which are specified by its
    (x1, y1, x2, y2) coordinates.

    Arguments:
        boxes (Tensor[N, 4]): boxes for which the area will be computed. They
            are expected to be in (x1, y1, x2, y2) format

    Returns:
        area (Tensor[N]): area for each box
    """
    return (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])


# implementation from https://github.com/kuangliu/torchcv/blob/master/torchcv/utils/box.py
# with slight modifications
def box_iou(boxes1: Tensor, boxes2: Tensor) -> Tensor:
    """
    Return intersection-over-union (Jaccard index) of boxes.

    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.

    Arguments:
        boxes1 (Tensor[N, 4])
        boxes2 (Tensor[M, 4])

    Returns:
        iou (Tensor[N, M]): the NxM matrix containing the pairwise
            IoU values for every element in boxes1 and boxes2
    """
    area1 = box_area(boxes1)
    area2 = box_area(boxes2)

    lt = torch.max(boxes1[:, None, :2], boxes2[:, :2])  # [N,M,2]
    rb = torch.min(boxes1[:, None, 2:], boxes2[:, 2:])  # [N,M,2]

    wh = (rb - lt).clamp(min=0)  # [N,M,2]
    inter = wh[:, :, 0] * wh[:, :, 1]  # [N,M]

    iou = inter / (area1[:, None] + area2 - inter)
    return iou