【AI达人特训营】SIOU论文复现：Powerful的回归框学习能力

!git clone https://gitee.com/paddlepaddle/PaddleDetection.git

# 按照Paddledetection%cd PaddleDetection/
!pip install -r /home/aistudio/PaddleDetection/requirements.txt  
!python setup.py install
%cd ..

# 下载数据集%cd PaddleDetection/
!python dataset/roadsign_voc/download_roadsign_voc.py

# 利用paddledetection自带的脚本，来将数据集转成coco形式%cd /home/aistudio/PaddleDetection/#转换train!python tools/x2coco.py \
        --dataset_type voc \
        --voc_anno_dir /home/aistudio/PaddleDetection/dataset/roadsign_voc/ \
--voc_anno_list /home/aistudio/PaddleDetection/dataset/roadsign_voc/train.txt \
--voc_label_list /home/aistudio/PaddleDetection/dataset/roadsign_voc/label_list.txt \
--voc_out_name /home/aistudio/PaddleDetection/dataset/roadsign_voc/voc_train.json#转换val!python tools/x2coco.py \
        --dataset_type voc \
        --voc_anno_dir /home/aistudio/PaddleDetection/dataset/roadsign_voc/ \
--voc_anno_list /home/aistudio/PaddleDetection/dataset/roadsign_voc/valid.txt \
--voc_label_list /home/aistudio/PaddleDetection/dataset/roadsign_voc/label_list.txt \
--voc_out_name /home/aistudio/PaddleDetection/dataset/roadsign_voc/voc_val.json# 移入coco数据集!mv dataset/roadsign_voc/* dataset/coco

from ..losses import GIoULoss, DIouLoss

class DIouLoss(GIoULoss):    """
    Distance-IoU Loss, see https://arxiv.org/abs/1911.08287
    Args:
        loss_weight (float): giou loss weight, default as 1
        eps (float): epsilon to avoid divide by zero, default as 1e-10
        use_complete_iou_loss (bool): whether to use complete iou loss
    """

    def __init__(self, loss_weight=1., eps=1e-10, siou=False,use_complete_iou_loss=True):
        super(DIouLoss, self).__init__(loss_weight=loss_weight, eps=eps)
        self.use_complete_iou_loss = use_complete_iou_loss
        self.siou = siou

    def __call__(self, pbox, gbox, iou_weight=1.):
        x1, y1, x2, y2 = paddle.split(pbox, num_or_sections=4, axis=-1)
        x1g, y1g, x2g, y2g = paddle.split(gbox, num_or_sections=4, axis=-1)
        cx = (x1 + x2) / 2
        cy = (y1 + y2) / 2
        w = x2 - x1        h = y2 - y1        cxg = (x1g + x2g) / 2
        cyg = (y1g + y2g) / 2
        wg = x2g - x1g        hg = y2g - y1g        x2 = paddle.maximum(x1, x2)        y2 = paddle.maximum(y1, y2)        # A and B
        xkis1 = paddle.maximum(x1, x1g)        ykis1 = paddle.maximum(y1, y1g)        xkis2 = paddle.minimum(x2, x2g)        ykis2 = paddle.minimum(y2, y2g)        # A or B
        xc1 = paddle.minimum(x1, x1g)        yc1 = paddle.minimum(y1, y1g)        xc2 = paddle.maximum(x2, x2g)        yc2 = paddle.maximum(y2, y2g)        intsctk = (xkis2 - xkis1) * (ykis2 - ykis1)        intsctk = intsctk * paddle.greater_than(
            xkis2, xkis1) * paddle.greater_than(ykis2, ykis1)        unionk = (x2 - x1) * (y2 - y1) + (x2g - x1g) * (y2g - y1g
                                                        ) - intsctk + self.eps        iouk = intsctk / unionk        if self.siou:            cw = xc2 - xc1            ch = yc2 - yc1            s_cw = (x1g + x1 - x2g - x2) * 0.5
            s_ch = (y1g + y1 - y2g - y2) * 0.5
            sigma = paddle.pow(s_cw ** 2 + s_ch ** 2, 0.5) + self.eps            sin_alpha_1 = paddle.abs(s_cw) / sigma            sin_alpha_2 = paddle.abs(s_ch) / sigma            threshold = pow(2, 0.5) / 2
            sin_alpha = paddle.where(sin_alpha_1 > threshold, sin_alpha_2, sin_alpha_1)            angle_cost = paddle.sin(paddle.asin(sin_alpha) * 2)            rho_x = (s_cw / (cw + self.eps)) ** 2
            rho_y = (s_ch / (ch + self.eps)) ** 2
            gamma = angle_cost - 2
            distance_cost = 2 - paddle.exp(gamma * rho_x) - paddle.exp(gamma * rho_y)            omiga_w = paddle.abs(w - wg) / paddle.maximum(w, wg)            omiga_h = paddle.abs(h - hg) / paddle.maximum(h, hg)            shape_cost = paddle.pow(1 - paddle.exp(-1 * omiga_w), 4) + paddle.pow(1 - paddle.exp(-1 * omiga_h), 4)
            return paddle.mean((1- (iouk - 0.5 * (distance_cost + shape_cost))))*self.loss_weight        # DIOU term
        dist_intersection = (cx - cxg) * (cx - cxg) + (cy - cyg) * (cy - cyg)        dist_union = (xc2 - xc1) * (xc2 - xc1) + (yc2 - yc1) * (yc2 - yc1)        diou_term = (dist_intersection + self.eps) / (dist_union + self.eps)        # CIOU term
        ciou_term = 0
        if self.use_complete_iou_loss:            ar_gt = wg / hg            ar_pred = w / h            arctan = paddle.atan(ar_gt) - paddle.atan(ar_pred)            ar_loss = 4. / np.pi / np.pi * arctan * arctan            alpha = ar_loss / (1 - iouk + ar_loss + self.eps)
            alpha.stop_gradient = True            ciou_term = alpha * ar_loss        diou = paddle.mean((1 - iouk + ciou_term + diou_term) * iou_weight)

        return diou * self.loss_weight

        self.iou_loss = DIouLoss(siou=True, use_complete_iou_loss=False)

%cd PaddleDetection/
!python tools/train.py -c ../myconfig/ppyoloe_crn_m_300e_coco.yml --use_vdl=true --vdl_log_dir=vdl_dir/Test --eval \