Python 如何应用距离欠条损失？

我当前正在使用此存储库培训自定义数据集：

训练的结果对我来说并不令人满意，所以我将把回归损失，也就是L1平滑损失，改为距离IoU损失

本回购协议的回归损失代码如下：

                anchor_widths_pi = anchor_widths[positive_indices]
                anchor_heights_pi = anchor_heights[positive_indices]
                anchor_ctr_x_pi = anchor_ctr_x[positive_indices]
                anchor_ctr_y_pi = anchor_ctr_y[positive_indices]

                gt_widths = assigned_annotations[:, 2] - assigned_annotations[:, 0]
                gt_heights = assigned_annotations[:, 3] - assigned_annotations[:, 1]
                gt_ctr_x = assigned_annotations[:, 0] + 0.5 * gt_widths
                gt_ctr_y = assigned_annotations[:, 1] + 0.5 * gt_heights

                # efficientdet style
                gt_widths = torch.clamp(gt_widths, min=1)
                gt_heights = torch.clamp(gt_heights, min=1)

                targets_dx = (gt_ctr_x - anchor_ctr_x_pi) / anchor_widths_pi
                targets_dy = (gt_ctr_y - anchor_ctr_y_pi) / anchor_heights_pi
                targets_dw = torch.log(gt_widths / anchor_widths_pi)
                targets_dh = torch.log(gt_heights / anchor_heights_pi)

                targets = torch.stack((targets_dy, targets_dx, targets_dh, targets_dw))
                targets = targets.t()
                
                
                # L1 loss
                regression_diff = torch.abs(targets - regression[positive_indices, :])

                regression_loss = torch.where(
                    torch.le(regression_diff, 1.0 / 9.0),
                    0.5 * 9.0 * torch.pow(regression_diff, 2),
                    regression_diff - 0.5 / 9.0

    rows = bboxes1.shape[0]
    cols = bboxes2.shape[0]
    dious = torch.zeros((rows, cols))
    if rows * cols == 0:
        return dious
    exchange = False
    
    bboxes1 = bboxes1.index_select(1, torch.LongTensor([1, 0, 3, 2]).to('cuda'))
    
    if bboxes1.shape[0] > bboxes2.shape[0]:
        bboxes1, bboxes2 = bboxes2, bboxes1
        dious = torch.zeros((cols, rows))
        exchange = True

    w1 = bboxes1[:, 2] - bboxes1[:, 0]
    h1 = bboxes1[:, 3] - bboxes1[:, 1] 
    w2 = bboxes2[:, 2] - bboxes2[:, 0]
    h2 = bboxes2[:, 3] - bboxes2[:, 1]
    
    area1 = w1 * h1
    area2 = w2 * h2
 
    center_x1 = (bboxes1[:, 2] + bboxes1[:, 0]) / 2 
    center_y1 = (bboxes1[:, 3] + bboxes1[:, 1]) / 2 
    center_x2 = (bboxes2[:, 2] + bboxes2[:, 0]) / 2
    center_y2 = (bboxes2[:, 3] + bboxes2[:, 1]) / 2
 
    inter_max_xy = torch.min(bboxes1[:, 2:],bboxes2[:, 2:]) 
    inter_min_xy = torch.max(bboxes1[:, :2],bboxes2[:, :2]) 
    out_max_xy = torch.max(bboxes1[:, 2:],bboxes2[:, 2:]) 
    out_min_xy = torch.min(bboxes1[:, :2],bboxes2[:, :2])
 
    inter = torch.clamp((inter_max_xy - inter_min_xy), min=0)
    inter_area = inter[:, 0] * inter[:, 1]
    inter_diag = (center_x2 - center_x1)**2 + (center_y2 - center_y1)**2
    outer = torch.clamp((out_max_xy - out_min_xy), min=0)
    outer_diag = (outer[:, 0] ** 2) + (outer[:, 1] ** 2)
    union = area1+area2-inter_area
    dious = inter_area / union - (inter_diag) / outer_diag
    dious = torch.clamp(dious,min=-1.0,max = 1.0)
    if exchange:
        dious = dious.T
        
    loss = 1 - dious
    return loss

我用作距离IoU的代码如下：

                anchor_widths_pi = anchor_widths[positive_indices]
                anchor_heights_pi = anchor_heights[positive_indices]
                anchor_ctr_x_pi = anchor_ctr_x[positive_indices]
                anchor_ctr_y_pi = anchor_ctr_y[positive_indices]

                gt_widths = assigned_annotations[:, 2] - assigned_annotations[:, 0]
                gt_heights = assigned_annotations[:, 3] - assigned_annotations[:, 1]
                gt_ctr_x = assigned_annotations[:, 0] + 0.5 * gt_widths
                gt_ctr_y = assigned_annotations[:, 1] + 0.5 * gt_heights

                # efficientdet style
                gt_widths = torch.clamp(gt_widths, min=1)
                gt_heights = torch.clamp(gt_heights, min=1)

                targets_dx = (gt_ctr_x - anchor_ctr_x_pi) / anchor_widths_pi
                targets_dy = (gt_ctr_y - anchor_ctr_y_pi) / anchor_heights_pi
                targets_dw = torch.log(gt_widths / anchor_widths_pi)
                targets_dh = torch.log(gt_heights / anchor_heights_pi)

                targets = torch.stack((targets_dy, targets_dx, targets_dh, targets_dw))
                targets = targets.t()
                
                
                # L1 loss
                regression_diff = torch.abs(targets - regression[positive_indices, :])

                regression_loss = torch.where(
                    torch.le(regression_diff, 1.0 / 9.0),
                    0.5 * 9.0 * torch.pow(regression_diff, 2),
                    regression_diff - 0.5 / 9.0

    rows = bboxes1.shape[0]
    cols = bboxes2.shape[0]
    dious = torch.zeros((rows, cols))
    if rows * cols == 0:
        return dious
    exchange = False
    
    bboxes1 = bboxes1.index_select(1, torch.LongTensor([1, 0, 3, 2]).to('cuda'))
    
    if bboxes1.shape[0] > bboxes2.shape[0]:
        bboxes1, bboxes2 = bboxes2, bboxes1
        dious = torch.zeros((cols, rows))
        exchange = True

    w1 = bboxes1[:, 2] - bboxes1[:, 0]
    h1 = bboxes1[:, 3] - bboxes1[:, 1] 
    w2 = bboxes2[:, 2] - bboxes2[:, 0]
    h2 = bboxes2[:, 3] - bboxes2[:, 1]
    
    area1 = w1 * h1
    area2 = w2 * h2
 
    center_x1 = (bboxes1[:, 2] + bboxes1[:, 0]) / 2 
    center_y1 = (bboxes1[:, 3] + bboxes1[:, 1]) / 2 
    center_x2 = (bboxes2[:, 2] + bboxes2[:, 0]) / 2
    center_y2 = (bboxes2[:, 3] + bboxes2[:, 1]) / 2
 
    inter_max_xy = torch.min(bboxes1[:, 2:],bboxes2[:, 2:]) 
    inter_min_xy = torch.max(bboxes1[:, :2],bboxes2[:, :2]) 
    out_max_xy = torch.max(bboxes1[:, 2:],bboxes2[:, 2:]) 
    out_min_xy = torch.min(bboxes1[:, :2],bboxes2[:, :2])
 
    inter = torch.clamp((inter_max_xy - inter_min_xy), min=0)
    inter_area = inter[:, 0] * inter[:, 1]
    inter_diag = (center_x2 - center_x1)**2 + (center_y2 - center_y1)**2
    outer = torch.clamp((out_max_xy - out_min_xy), min=0)
    outer_diag = (outer[:, 0] ** 2) + (outer[:, 1] ** 2)
    union = area1+area2-inter_area
    dious = inter_area / union - (inter_diag) / outer_diag
    dious = torch.clamp(dious,min=-1.0,max = 1.0)
    if exchange:
        dious = dious.T
        
    loss = 1 - dious
    return loss

问题是：

我是否应该将一个目标bbox的距离IoU损失应用于所有pred bbox？ 例如，有2个带注释的bbox和1000个预测的bbox。 我是否应该计算两次损失，就像每个带注释的bbox与1000个预测的bbox一样

我应该将预测的bbox转换为实际坐标进行计算吗

我见过这样做的几种方法，但通常这些方法是通过分配框来工作的。通过计算1000x2 IOU数组，您可以为每个预测框指定一个地面真实值目标，并为视网膜网中的好/坏预测设置IOU阈值，或者为每个地面真实值目标指定一个最佳预测框，如老YOLO中所示。无论哪种方式，损失仅应用于指定的盒子对，而不是每个组合，因此每个指定的预测都集中在单个目标上

DIOU对尺度是不变的