一,什么是损失函数:
简单的理解就是每一个样本经过模型后会得到一个预测值,然后得到的预测值和真实值的差值就成为损失(当然损失值越小证明模型越是成功),我们知道有许多不同种类的损失函数,这些函数本质上就是计算预测值和真实值的差距的一类型函数,然后经过库(如pytorch,tensorflow等)的封装形成了有具体名字的函数。
二,损失函数的作用:
我们上文说到损失函数是计算预测值和真实值的一类函数,而在机器学习中,我们想让预测值无限接近于真实值,所以需要将差值降到最低(在这个过程中就需要引入损失函数)。而在此过程中损失函数的选择是十分关键的,在具体的项目中,有些损失函数计算的差值梯度下降的快,而有些下降的慢,所以选择合适的损失函数也是十分关键的。
三,yolov7损失函数的修改
在general.py中改成:
if GIoU or DIoU or CIoU or EIoU or SIoU:
cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width
ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height
if SIoU: # SIoU Loss https://arxiv.org/pdf/2205.12740.pdf
s_cw = (b2_x1 + b2_x2 - b1_x1 - b1_x2) * 0.5
s_ch = (b2_y1 + b2_y2 - b1_y1 - b1_y2) * 0.5
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 = 1 - 2 * torch.pow( torch.sin(torch.arcsin(sin_alpha) - np.pi/4), 2)
angle_cost = torch.cos(torch.arcsin(sin_alpha) * 2 - np.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)
return iou - 0.5 * (distance_cost + shape_cost)
if CIoU or DIoU or EIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared
rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
(b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared
if DIoU:
return iou - rho2 / c2 # DIoU
elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / (h2 + eps)) - torch.atan(w1 / (h1 + eps)), 2)
with torch.no_grad():
alpha = v / (v - iou + (1 + eps))
return iou - (rho2 / c2 + v * alpha) # CIoU
elif EIoU:
rho_w2 = ((b2_x2 - b2_x1) - (b1_x2 - b1_x1)) ** 2
rho_h2 = ((b2_y2 - b2_y1) - (b1_y2 - b1_y1)) ** 2
cw2 = cw ** 2 + eps
ch2 = ch ** 2 + eps
return iou - (rho2 / c2 + rho_w2 / cw2 + rho_h2 / ch2)
else: # GIoU https://arxiv.org/pdf/1902.09630.pdf
c_area = cw * ch + eps # convex area
return iou - (c_area - union) / c_area # GIoU
else:
return iou # IoU
在loss.py中改:
原始:
iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target)
改成(根据你的需求修改):
iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, GIoU=True) # iou(prediction, target)