77 lines
2.6 KiB
Python
77 lines
2.6 KiB
Python
|
import torch
|
||
|
|
|
||
|
|
from ..utils import _log_api_usage_once
|
||
|
|
from ._utils import _loss_inter_union, _upcast_non_float
|
||
|
|
|
||
|
|
|
||
|
|
def generalized_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 and scales with the size of their smallest enclosing box.
|
||
|
|
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
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
Tensor: Loss tensor with the reduction option applied.
|
||
|
|
|
||
|
|
Reference:
|
||
|
|
Hamid Rezatofighi et al.: Generalized Intersection over Union:
|
||
|
|
A Metric and A Loss for Bounding Box Regression:
|
||
|
|
https://arxiv.org/abs/1902.09630
|
||
|
|
"""
|
||
|
|
|
||
|
|
# Original implementation from https://github.com/facebookresearch/fvcore/blob/bfff2ef/fvcore/nn/giou_loss.py
|
||
|
|
|
||
|
|
if not torch.jit.is_scripting() and not torch.jit.is_tracing():
|
||
|
|
_log_api_usage_once(generalized_box_iou_loss)
|
||
|
|
|
||
|
|
boxes1 = _upcast_non_float(boxes1)
|
||
|
|
boxes2 = _upcast_non_float(boxes2)
|
||
|
|
intsctk, unionk = _loss_inter_union(boxes1, boxes2)
|
||
|
|
iouk = intsctk / (unionk + eps)
|
||
|
|
|
||
|
|
x1, y1, x2, y2 = boxes1.unbind(dim=-1)
|
||
|
|
x1g, y1g, x2g, y2g = boxes2.unbind(dim=-1)
|
||
|
|
|
||
|
|
# smallest enclosing box
|
||
|
|
xc1 = torch.min(x1, x1g)
|
||
|
|
yc1 = torch.min(y1, y1g)
|
||
|
|
xc2 = torch.max(x2, x2g)
|
||
|
|
yc2 = torch.max(y2, y2g)
|
||
|
|
|
||
|
|
area_c = (xc2 - xc1) * (yc2 - yc1)
|
||
|
|
miouk = iouk - ((area_c - unionk) / (area_c + eps))
|
||
|
|
|
||
|
|
loss = 1 - miouk
|
||
|
|
|
||
|
|
# Check reduction option and return loss accordingly
|
||
|
|
if reduction == "none":
|
||
|
|
pass
|
||
|
|
elif reduction == "mean":
|
||
|
|
loss = loss.mean() if loss.numel() > 0 else 0.0 * loss.sum()
|
||
|
|
elif reduction == "sum":
|
||
|
|
loss = loss.sum()
|
||
|
|
else:
|
||
|
|
raise ValueError(
|
||
|
|
f"Invalid Value for arg 'reduction': '{reduction} \n Supported reduction modes: 'none', 'mean', 'sum'"
|
||
|
|
)
|
||
|
|
return loss
|