# 以下函数已保存在d2lzh_pytorch包中方便以后使用
def assign_anchor(bb, anchor, jaccard_threshold=0.5):
    """
    # 按照「9.4.1. 生成多个锚框」图9.3所讲为每个anchor分配真实的bb, anchor表示成归一化(xmin, ymin, xmax, ymax).
    https://zh.d2l.ai/chapter_computer-vision/anchor.html
    Args:
        bb: 真实边界框(bounding box), shape:（nb, 4）
        anchor: 待分配的anchor, shape:（na, 4）
        jaccard_threshold: 预先设定的阈值
    Returns:
        assigned_idx: shape: (na, ), 每个anchor分配的真实bb对应的索引, 若未分配任何bb则为-1
    """
    na = anchor.shape[0]
    nb = bb.shape[0]
    jaccard = compute_jaccard(anchor, bb).detach().cpu().numpy() # shape: (na, nb)
    assigned_idx = np.ones(na) * -1  # 初始全为-1
    
    # 先为每个bb分配一个anchor(不要求满足jaccard_threshold)
    jaccard_cp = jaccard.copy()
    for j in range(nb):
        i = np.argmax(jaccard_cp[:, j])
        assigned_idx[i] = j
        jaccard_cp[i, :] = float("-inf") # 赋值为负无穷, 相当于去掉这一行
     
    # 处理还未被分配的anchor, 要求满足jaccard_threshold
    for i in range(na):
        if assigned_idx[i] == -1:
            j = np.argmax(jaccard[i, :])
            if jaccard[i, j] >= jaccard_threshold:
                assigned_idx[i] = j
    
    return torch.tensor(assigned_idx, dtype=torch.long)


def xy_to_cxcy(xy):
    """
    将(x_min, y_min, x_max, y_max)形式的anchor转换成(center_x, center_y, w, h)形式的.
    https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Object-Detection/blob/master/utils.py
    Args:
        xy: bounding boxes in boundary coordinates, a tensor of size (n_boxes, 4)
    Returns: 
        bounding boxes in center-size coordinates, a tensor of size (n_boxes, 4)
    """
    return torch.cat([(xy[:, 2:] + xy[:, :2]) / 2,  # c_x, c_y
                      xy[:, 2:] - xy[:, :2]], 1)  # w, h

def MultiBoxTarget(anchor, label):
    """
    # 按照「9.4.1. 生成多个锚框」所讲的实现, anchor表示成归一化(xmin, ymin, xmax, ymax).
    https://zh.d2l.ai/chapter_computer-vision/anchor.html
    Args:
        anchor: torch tensor, 输入的锚框, 一般是通过MultiBoxPrior生成, shape:（1，锚框总数，4）
        label: 真实标签, shape为(bn, 每张图片最多的真实锚框数, 5)
               第二维中，如果给定图片没有这么多锚框, 可以先用-1填充空白, 最后一维中的元素为[类别标签, 四个坐标值]
    Returns:
        列表, [bbox_offset, bbox_mask, cls_labels]
        bbox_offset: 每个锚框的标注偏移量，形状为(bn，锚框总数*4)
        bbox_mask: 形状同bbox_offset, 每个锚框的掩码, 一一对应上面的偏移量, 负类锚框(背景)对应的掩码均为0, 正类锚框的掩码均为1
        cls_labels: 每个锚框的标注类别, 其中0表示为背景, 形状为(bn，锚框总数)
    """
    assert len(anchor.shape) == 3 and len(label.shape) == 3
    bn = label.shape[0]
    
    def MultiBoxTarget_one(anc, lab, eps=1e-6):
        """
        MultiBoxTarget函数的辅助函数, 处理batch中的一个
        Args:
            anc: shape of (锚框总数, 4)
            lab: shape of (真实锚框数, 5), 5代表[类别标签, 四个坐标值]
            eps: 一个极小值, 防止log0
        Returns:
            offset: (锚框总数*4, )
            bbox_mask: (锚框总数*4, ), 0代表背景, 1代表非背景
            cls_labels: (锚框总数, 4), 0代表背景
        """
        an = anc.shape[0]
        assigned_idx = assign_anchor(lab[:, 1:], anc) # (锚框总数, )
        bbox_mask = ((assigned_idx >= 0).float().unsqueeze(-1)).repeat(1, 4) # (锚框总数, 4)

        cls_labels = torch.zeros(an, dtype=torch.long) # 0表示背景
        assigned_bb = torch.zeros((an, 4), dtype=torch.float32) # 所有anchor对应的bb坐标
        for i in range(an):
            bb_idx = assigned_idx[i]
            if bb_idx >= 0: # 即非背景
                cls_labels[i] = lab[bb_idx, 0].long().item() + 1 # 注意要加一
                assigned_bb[i, :] = lab[bb_idx, 1:]

        center_anc = xy_to_cxcy(anc) # (center_x, center_y, w, h)
        center_assigned_bb = xy_to_cxcy(assigned_bb)

        offset_xy = 10.0 * (center_assigned_bb[:, :2] - center_anc[:, :2]) / center_anc[:, 2:]
        offset_wh = 5.0 * torch.log(eps + center_assigned_bb[:, 2:] / center_anc[:, 2:])
        offset = torch.cat([offset_xy, offset_wh], dim = 1) * bbox_mask # (锚框总数, 4)

        return offset.view(-1), bbox_mask.view(-1), cls_labels
    
    batch_offset = []
    batch_mask = []
    batch_cls_labels = []
    for b in range(bn):
        offset, bbox_mask, cls_labels = MultiBoxTarget_one(anchor[0, :, :], label[b, :, :])
        
        batch_offset.append(offset)
        batch_mask.append(bbox_mask)
        batch_cls_labels.append(cls_labels)
    
    bbox_offset = torch.stack(batch_offset)
    bbox_mask = torch.stack(batch_mask)
    cls_labels = torch.stack(batch_cls_labels)
    
    return [bbox_offset, bbox_mask, cls_labels]