Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
ciou_loss.py 3.05 KB
Newer Older
Abhijit Deo's avatar
Added CIOU loss function (#5776)  
Abhijit Deo committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92 
import torch

from ..utils import _log_api_usage_once
from .giou_loss import _upcast


def complete_box_iou_loss(
    boxes1: torch.Tensor,
    boxes2: torch.Tensor,
    reduction: str = "none",
    eps: float = 1e-7,
) -> torch.Tensor:

    """
    Gradient-friendly IoU loss with an additional penalty that is non-zero when the
    boxes do not overlap overlap area, This loss function considers important geometrical
    factors such as  overlap area, normalized central point distance and aspect ratio.
    This loss is symmetric, so the boxes1 and boxes2 arguments are interchangeable.

    Both sets of boxes are expected to be in ``(x1, y1, x2, y2)`` format with
    ``0 <= x1 < x2`` and ``0 <= y1 < y2``, and The two boxes should have the
    same dimensions.

    Args:
        boxes1 : (Tensor[N, 4] or Tensor[4]) first set of boxes
        boxes2 : (Tensor[N, 4] or Tensor[4]) second set of boxes
        reduction : (string, optional) Specifies the reduction to apply to the output:
            ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: No reduction will be
            applied to the output. ``'mean'``: The output will be averaged.
            ``'sum'``: The output will be summed. Default: ``'none'``
        eps : (float): small number to prevent division by zero. Default: 1e-7

    Reference:

    Complete Intersection over Union Loss (Zhaohui Zheng et. al)
    https://arxiv.org/abs/1911.08287

    """

    # Original Implementation : https://github.com/facebookresearch/detectron2/blob/main/detectron2/layers/losses.py

    if not torch.jit.is_scripting() and not torch.jit.is_tracing():
        _log_api_usage_once(complete_box_iou_loss)

    boxes1 = _upcast(boxes1)
    boxes2 = _upcast(boxes2)

    x1, y1, x2, y2 = boxes1.unbind(dim=-1)
    x1g, y1g, x2g, y2g = boxes2.unbind(dim=-1)

    # Intersection keypoints
    xkis1 = torch.max(x1, x1g)
    ykis1 = torch.max(y1, y1g)
    xkis2 = torch.min(x2, x2g)
    ykis2 = torch.min(y2, y2g)

    intsct = torch.zeros_like(x1)
    mask = (ykis2 > ykis1) & (xkis2 > xkis1)
    intsct[mask] = (xkis2[mask] - xkis1[mask]) * (ykis2[mask] - ykis1[mask])
    union = (x2 - x1) * (y2 - y1) + (x2g - x1g) * (y2g - y1g) - intsct + eps
    iou = intsct / union

    # smallest enclosing box
    xc1 = torch.min(x1, x1g)
    yc1 = torch.min(y1, y1g)
    xc2 = torch.max(x2, x2g)
    yc2 = torch.max(y2, y2g)
    diag_len = ((xc2 - xc1) ** 2) + ((yc2 - yc1) ** 2) + eps

    # centers of boxes
    x_p = (x2 + x1) / 2
    y_p = (y2 + y1) / 2
    x_g = (x1g + x2g) / 2
    y_g = (y1g + y2g) / 2
    distance = ((x_p - x_g) ** 2) + ((y_p - y_g) ** 2)

    # width and height of boxes
    w_pred = x2 - x1
    h_pred = y2 - y1
    w_gt = x2g - x1g
    h_gt = y2g - y1g
    v = (4 / (torch.pi ** 2)) * torch.pow((torch.atan(w_gt / h_gt) - torch.atan(w_pred / h_pred)), 2)
    with torch.no_grad():
        alpha = v / (1 - iou + v + eps)

    loss = 1 - iou + (distance / diag_len) + alpha * v
    if reduction == "mean":
        loss = loss.mean() if loss.numel() > 0 else 0.0 * loss.sum()
    elif reduction == "sum":
        loss = loss.sum()

    return loss