def get_FAinner_iou(box1, box2, xywh=True, eps=1e-7, ratio=0.7,alpha=1):
if not xywh:
box1, box2 = ops.xyxy2xywh(box1), ops.xyxy2xywh(box2)
(x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1)
b1_x1, b1_x2, b1_y1, b1_y2 = x1 - (w1 * ratio) / 2, x1 + (w1 * ratio) / 2, y1 - (h1 * ratio) / 2, y1 + (
h1 * ratio) / 2
b2_x1, b2_x2, b2_y1, b2_y2 = x2 - (w2 * ratio) / 2, x2 + (w2 * ratio) / 2, y2 - (h2 * ratio) / 2, y2 + (
h2 * ratio) / 2
# Intersection area
inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp_(0) * \
(b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1)).clamp_(0)
# Union Area
union = w1 * h1 * ratio * ratio + w2 * h2 * ratio * ratio - inter + eps
# return inter / union # ori
return torch.pow(inter/(union + eps), alpha)
def bbox_FAinner_iou(box1, box2, xywh=True, EIoU=False, SIoU=False,Focal=False,alpha=1,gamma=0.5,eps=1e-7,ratio=0.7):
"""
Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4).
Args:
box1 (torch.Tensor): A tensor representing a single bounding box with shape (1, 4).
box2 (torch.Tensor): A tensor representing n bounding boxes with shape (n, 4).
xywh (bool, optional): If True, input boxes are in (x, y, w, h) format. If False, input boxes are in
(x1, y1, x2, y2) format. Defaults to True.
GIoU (bool, optional): If True, calculate Generalized IoU. Defaults to False.
DIoU (bool, optional): If True, calculate Distance IoU. Defaults to False.
CIoU (bool, optional): If True, calculate Complete IoU. Defaults to False.
EIoU (bool, optional): If True, calculate Efficient IoU. Defaults to False.
SIoU (bool, optional): If True, calculate Scylla IoU. Defaults to False.
eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.
Returns:
(torch.Tensor): IoU, GIoU, DIoU, or CIoU values depending on the specified flags.
"""
# Get the coordinates of bounding boxes
if xywh: # transform from xywh to xyxy
(x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, -1), box2.chunk(4, -1)
w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2
b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_
b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_
else: # x1, y1, x2, y2 = box1
b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, -1)
b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, -1)
w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
innner_iou = get_FAinner_iou(box1, box2, xywh=xywh, ratio=ratio,alpha=alpha)
# Intersection area
inter = (b1_x2.minimum(b2_x2) - b1_x1.maximum(b2_x1)).clamp_(0) * \
(b1_y2.minimum(b2_y2) - b1_y1.maximum(b2_y1)).clamp_(0)
# Union Area
union = w1 * h1 + w2 * h2 - inter + eps
# IoU
# iou = inter / union # ori iou
iou = torch.pow(inter / (union + eps), alpha) # alpha iou
if EIoU or SIoU:
cw = b1_x2.maximum(b2_x2) - b1_x1.minimum(b2_x1) # convex (smallest enclosing box) width
ch = b1_y2.maximum(b2_y2) - b1_y1.minimum(b2_y1) # convex height
if EIoU or SIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
c2 = (cw ** 2 + ch ** 2)**alpha + eps # convex diagonal squared
rho2 = (((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 ) ** alpha # center dist ** 2
if EIoU:
rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2
rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2
cw2 = torch.pow(cw ** 2 + eps,alpha)
ch2 = torch.pow(ch ** 2 + eps,alpha)
if Focal:
return innner_iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2), torch.pow(inter / (union + eps),gamma) # Focal_EIou
else:
return innner_iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2) # EIou
# return innner_iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2) # EIoU ori
elif SIoU:
# SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
s_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5 + eps
s_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5 + eps
sigma = torch.pow(s_cw ** 2 + s_ch ** 2, 0.5)
sin_alpha_1 = torch.abs(s_cw) / sigma
sin_alpha_2 = torch.abs(s_ch) / sigma
threshold = pow(2, 0.5) / 2
sin_alpha = torch.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)
angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - math.pi / 2)
rho_x = (s_cw / cw) ** 2
rho_y = (s_ch / ch) ** 2
gamma = angle_cost - 2
distance_cost = 2 - torch.exp(gamma * rho_x) - torch.exp(gamma * rho_y)
omiga_w = torch.abs(w1 - w2) / torch.max(w1, w2)
omiga_h = torch.abs(h1 - h2) / torch.max(h1, h2)
shape_cost = torch.pow(1 - torch.exp(-1 * omiga_w), 4) + torch.pow(1 - torch.exp(-1 * omiga_h), 4)
if Focal:
return innner_iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha), torch.pow(inter / (union + eps), gamma) # Focal_SIou
else:
return innner_iou - torch.pow(0.5 * (distance_cost + shape_cost) + eps, alpha) # SIou
# return innner_iou - 0.5 * (distance_cost + shape_cost) + eps # SIoU ori
c_area = cw * ch + eps # convex area
if Focal:
return iou, torch.pow(inter / (union + eps), gamma) # Focal_IoU
else:
return iou # IoU
# return innner_iou # IoU or
loss.py中
iou = bbox_FAinner_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh=False, EIoU=True, Focal=True,alpha=3,ratio=0.8) # 使用focal和α,ratio(0.5-1.5)
if type(iou) is tuple:
loss_iou = ((1.0 - iou[0]) * iou[1].detach() * weight).sum() / target_scores_sum
else:
loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
tal中,找到该函数,替换你使用的iou函数。
def get_box_metrics(self, pd_scores, pd_bboxes, gt_labels, gt_bboxes, mask_gt):
"""Compute alignment metric given predicted and ground truth bounding boxes."""
na = pd_bboxes.shape[-2]
mask_gt = mask_gt.bool() # b, max_num_obj, h*w
overlaps = torch.zeros([self.bs, self.n_max_boxes, na], dtype=pd_bboxes.dtype, device=pd_bboxes.device)
bbox_scores = torch.zeros([self.bs, self.n_max_boxes, na], dtype=pd_scores.dtype, device=pd_scores.device)
ind = torch.zeros([2, self.bs, self.n_max_boxes], dtype=torch.long) # 2, b, max_num_obj
ind[0] = torch.arange(end=self.bs).view(-1, 1).expand(-1, self.n_max_boxes) # b, max_num_obj
ind[1] = gt_labels.squeeze(-1) # b, max_num_obj
# Get the scores of each grid for each gt cls
bbox_scores[mask_gt] = pd_scores[ind[0], :, ind[1]][mask_gt] # b, max_num_obj, h*w
# (b, max_num_obj, 1, 4), (b, 1, h*w, 4)
pd_boxes = pd_bboxes.unsqueeze(1).expand(-1, self.n_max_boxes, -1, -1)[mask_gt]
gt_boxes = gt_bboxes.unsqueeze(2).expand(-1, -1, na, -1)[mask_gt]
# overlaps[mask_gt] = bbox_iou(gt_boxes, pd_boxes, xywh=False, CIoU=True).squeeze(-1).clamp_(0) # ori
overlaps[mask_gt] = bbox_iou(gt_boxes, pd_boxes, xywh=False, EIoU=True).squeeze(-1).clamp_(0)
# overlaps[mask_gt] = wasserstein_loss(gt_boxes, pd_boxes).squeeze(-1).clamp_(0)
align_metric = bbox_scores.pow(self.alpha) * overlaps.pow(self.beta)
return align_metric, overlaps