diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index b24c844b4b212f4d857bc305a7cd244f1accedd3..799fbb0f752487820bb0c1a20a86dc4bb79d918d 100644
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -324,7 +324,7 @@ paddle.fluid.layers.iou_similarity ArgSpec(args=['x', 'y', 'name'], varargs=None
 paddle.fluid.layers.box_coder ArgSpec(args=['prior_box', 'prior_box_var', 'target_box', 'code_type', 'box_normalized', 'name'], varargs=None, keywords=None, defaults=('encode_center_size', True, None))
 paddle.fluid.layers.polygon_box_transform ArgSpec(args=['input', 'name'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.layers.yolov3_loss ArgSpec(args=['x', 'gtbox', 'gtlabel', 'anchors', 'class_num', 'ignore_thresh', 'loss_weight_xy', 'loss_weight_wh', 'loss_weight_conf_target', 'loss_weight_conf_notarget', 'loss_weight_class', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, None, None))
-paddle.fluid.layers.box_clip ArgSpec(args=['input', 'im_info', 'inplace', 'name'], varargs=None, keywords=None, defaults=(False, None))
+paddle.fluid.layers.box_clip ArgSpec(args=['input', 'im_info', 'name'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.layers.accuracy ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None))
 paddle.fluid.layers.auc ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1))
 paddle.fluid.layers.exponential_decay ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,))
diff --git a/python/paddle/fluid/layers/detection.py b/python/paddle/fluid/layers/detection.py
index 4fd7e5739c746c7f52c8cdec32b856474a1f4eff..fe2baa108cb6b5f1020b6c1213ac31412a2f2144 100644
--- a/python/paddle/fluid/layers/detection.py
+++ b/python/paddle/fluid/layers/detection.py
@@ -1963,7 +1963,7 @@ def generate_proposals(scores,
     return rpn_rois, rpn_roi_probs
 
 
-def box_clip(input, im_info, inplace=False, name=None):
+def box_clip(input, im_info, name=None):
     """
     Clip the box into the size given by im_info
     For each input box, The formula is given as follows:
@@ -1988,15 +1988,6 @@ def box_clip(input, im_info, inplace=False, name=None):
                             layout (height, width, scale). height and width
                             is the input size and scale is the ratio of input
                             size and original size.
-        inplace(bool): Must use :attr:`False` if :attr:`input` is used in 
-                       multiple operators. If this flag is set :attr:`True`, 
-                       reuse input :attr:`input` to clip, which will 
-                       change the value of tensor variable :attr:`input` 
-                       and might cause errors when :attr:`input` is used 
-                       in multiple operators. If :attr:`False`, preserve the 
-                       value pf :attr:`input` and create a new output 
-                       tensor variable whose data is copied from input x but 
-                       cliped.
         name (str): The name of this layer. It is optional.
     
     Returns:
@@ -2013,8 +2004,7 @@ def box_clip(input, im_info, inplace=False, name=None):
     """
 
     helper = LayerHelper("box_clip", **locals())
-    output = x if inplace else helper.create_variable_for_type_inference(\
-             dtype=input.dtype)
+    output = helper.create_variable_for_type_inference(dtype=input.dtype)
     inputs = {"Input": input, "ImInfo": im_info}
     helper.append_op(type="box_clip", inputs=inputs, outputs={"Output": output})