diff --git a/ppdet/modeling/losses/diou_loss_yolo.py b/ppdet/modeling/losses/diou_loss_yolo.py
index d85154d085e0f7873f86e87f031320db9f16b724..9d83eecde5e9bd67a149fa21dfec194c432e3f97 100644
--- a/ppdet/modeling/losses/diou_loss_yolo.py
+++ b/ppdet/modeling/losses/diou_loss_yolo.py
@@ -54,7 +54,8 @@ class DiouLossYolo(IouLoss):
                  anchors,
                  downsample_ratio,
                  batch_size,
-                 eps=1.e-10):
+                 eps=1.e-10,
+                 **kwargs):
         '''
         Args:
             x  | y | w | h  ([Variables]): the output of yolov3 for encoded x|y|w|h
diff --git a/ppdet/modeling/losses/yolo_loss.py b/ppdet/modeling/losses/yolo_loss.py
index 9445f6a231ee9eabc6e8a54fab07c5b6e0128a0a..c16c6cb11b1c6f0d5925fd68955c94b4f9e07dbf 100644
--- a/ppdet/modeling/losses/yolo_loss.py
+++ b/ppdet/modeling/losses/yolo_loss.py
@@ -180,9 +180,19 @@ class YOLOv3Loss(object):
             loss_h = fluid.layers.abs(h - th) * tscale_tobj
             loss_h = fluid.layers.reduce_sum(loss_h, dim=[1, 2, 3])
             if self._iou_loss is not None:
-                loss_iou = self._iou_loss(x, y, w, h, tx, ty, tw, th, anchors,
-                                          downsample, self._train_batch_size,
-                                          scale_x_y)
+                loss_iou = self._iou_loss(
+                    x,
+                    y,
+                    w,
+                    h,
+                    tx,
+                    ty,
+                    tw,
+                    th,
+                    anchors,
+                    downsample,
+                    self._train_batch_size,
+                    scale_x_y=scale_x_y)
                 loss_iou = loss_iou * tscale_tobj
                 loss_iou = fluid.layers.reduce_sum(loss_iou, dim=[1, 2, 3])
                 loss_ious.append(fluid.layers.reduce_mean(loss_iou))