import torch
from torch.jit.annotations import Tuple
from torch import Tensor
from ._box_convert import _box_cxcywh_to_xyxy, _box_xyxy_to_cxcywh, _box_xywh_to_xyxy, _box_xyxy_to_xywh
import torchvision
from torchvision.extension import _assert_has_ops
[docs]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
"""
_assert_has_ops()
return torch.ops.torchvision.nms(boxes, scores, iou_threshold)
[docs]@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
[docs]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 = torch.where(keep)[0]
return keep
[docs]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)
[docs]def box_convert(boxes: Tensor, in_fmt: str, out_fmt: str) -> Tensor:
"""
Converts boxes from given in_fmt to out_fmt.
Supported in_fmt and out_fmt are:
'xyxy': boxes are represented via corners, x1, y1 being top left and x2, y2 being bottom right.
'xywh' : boxes are represented via corner, width and height, x1, y2 being top left, w, h being width and height.
'cxcywh' : boxes are represented via centre, width and height, cx, cy being center of box, w, h
being width and height.
Arguments:
boxes (Tensor[N, 4]): boxes which will be converted.
in_fmt (str): Input format of given boxes. Supported formats are ['xyxy', 'xywh', 'cxcywh'].
out_fmt (str): Output format of given boxes. Supported formats are ['xyxy', 'xywh', 'cxcywh']
Returns:
boxes (Tensor[N, 4]): Boxes into converted format.
"""
allowed_fmts = ("xyxy", "xywh", "cxcywh")
if in_fmt not in allowed_fmts or out_fmt not in allowed_fmts:
raise ValueError("Unsupported Bounding Box Conversions for given in_fmt and out_fmt")
if in_fmt == out_fmt:
return boxes.clone()
if in_fmt != 'xyxy' and out_fmt != 'xyxy':
# convert to xyxy and change in_fmt xyxy
if in_fmt == "xywh":
boxes = _box_xywh_to_xyxy(boxes)
elif in_fmt == "cxcywh":
boxes = _box_cxcywh_to_xyxy(boxes)
in_fmt = 'xyxy'
if in_fmt == "xyxy":
if out_fmt == "xywh":
boxes = _box_xyxy_to_xywh(boxes)
elif out_fmt == "cxcywh":
boxes = _box_xyxy_to_cxcywh(boxes)
elif out_fmt == "xyxy":
if in_fmt == "xywh":
boxes = _box_xywh_to_xyxy(boxes)
elif in_fmt == "cxcywh":
boxes = _box_cxcywh_to_xyxy(boxes)
return boxes
[docs]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
[docs]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
# Implementation adapted from https://github.com/facebookresearch/detr/blob/master/util/box_ops.py
[docs]def generalized_box_iou(boxes1: Tensor, boxes2: Tensor) -> Tensor:
"""
Return generalized 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:
generalized_iou (Tensor[N, M]): the NxM matrix containing the pairwise generalized_IoU values
for every element in boxes1 and boxes2
"""
# degenerate boxes gives inf / nan results
# so do an early check
assert (boxes1[:, 2:] >= boxes1[:, :2]).all()
assert (boxes2[:, 2:] >= boxes2[:, :2]).all()
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]
union = area1[:, None] + area2 - inter
iou = inter / union
lti = torch.min(boxes1[:, None, :2], boxes2[:, :2])
rbi = torch.max(boxes1[:, None, 2:], boxes2[:, 2:])
whi = (rbi - lti).clamp(min=0) # [N,M,2]
areai = whi[:, :, 0] * whi[:, :, 1]
return iou - (areai - union) / areai
