diff --git a/python/paddle/fluid/contrib/optimizer.py b/python/paddle/fluid/contrib/optimizer.py
index 347edc85783e99242ba2b6e1cd648366b6ebbab9..968bfa92b510aed9b85920f1805b2835a39df63e 100644
--- a/python/paddle/fluid/contrib/optimizer.py
+++ b/python/paddle/fluid/contrib/optimizer.py
@@ -24,7 +24,7 @@ __all__ = ['Momentum']
 
 
 class Momentum(Optimizer):
-    """
+    r"""
 
     Simple Momentum optimizer with velocity state
 
diff --git a/python/paddle/fluid/dygraph/nn.py b/python/paddle/fluid/dygraph/nn.py
index 9382f6b8e7352e26ab5af350cc850d58daf4e0b3..12ea7c5ff6c6b497c0d28be9f2eda44cfa68c45d 100644
--- a/python/paddle/fluid/dygraph/nn.py
+++ b/python/paddle/fluid/dygraph/nn.py
@@ -2979,7 +2979,7 @@ class GroupNorm(layers.Layer):
 
 
 class SpectralNorm(layers.Layer):
-    """
+    r"""
     This interface is used to construct a callable object of the ``SpectralNorm`` class.
     For more details, refer to code examples. It implements the function of the Spectral Normalization Layer.
     This layer calculates the spectral normalization value of weight parameters of
diff --git a/python/paddle/nn/functional/loss.py b/python/paddle/nn/functional/loss.py
index 7b7521d53a56f559c9aece9f45c073de2331a0d7..cc1010772c2f9362cb344ab0c14da5fab7764264 100755
--- a/python/paddle/nn/functional/loss.py
+++ b/python/paddle/nn/functional/loss.py
@@ -1123,7 +1123,7 @@ def cross_entropy(input,
                   soft_label=False,
                   axis=-1,
                   name=None):
-    """
+    r"""
     This operator implements the cross entropy loss function with softmax. This function 
     combines the calculation of the softmax operation and the cross entropy loss function 
     to provide a more numerically stable gradient.
diff --git a/python/paddle/nn/layer/loss.py b/python/paddle/nn/layer/loss.py
index 14992d1019ee8fe168c9051dbac0b16f6a791b0f..ae5f730f2df6c7bb99b723410db5151c00792adf 100644
--- a/python/paddle/nn/layer/loss.py
+++ b/python/paddle/nn/layer/loss.py
@@ -141,7 +141,7 @@ class BCEWithLogitsLoss(fluid.dygraph.Layer):
 
 
 class CrossEntropyLoss(fluid.dygraph.Layer):
-    """
+    r"""
     This operator implements the cross entropy loss function with softmax. This function 
     combines the calculation of the softmax operation and the cross entropy loss function 
     to provide a more numerically stable gradient.
@@ -623,7 +623,7 @@ class BCELoss(fluid.dygraph.Layer):
 
 
 class NLLLoss(fluid.dygraph.Layer):
-    """
+    r"""
 	:alias_main: paddle.nn.NLLLoss
 	:alias: paddle.nn.NLLLoss,paddle.nn.layer.NLLLoss,paddle.nn.layer.loss.NLLLoss
 
diff --git a/python/paddle/optimizer/lamb.py b/python/paddle/optimizer/lamb.py
index de62257588eaa798b7747641d2be5ac5bd73e543..c6275a823022ae3d5ed30356c62ffd66d3fd218e 100644
--- a/python/paddle/optimizer/lamb.py
+++ b/python/paddle/optimizer/lamb.py
@@ -21,7 +21,7 @@ __all__ = ["Lamb"]
 
 
 class Lamb(Optimizer):
-    """
+    r"""
     LAMB (Layer-wise Adaptive Moments optimizer for Batching training) Optimizer.
 
     LAMB Optimizer is designed to scale up the batch size of training without losing
diff --git a/python/paddle/vision/ops.py b/python/paddle/vision/ops.py
index 892f3a258146a0c860f105837ba037e18d78b633..1fd0b1d717cefba3e7472405101198e719626207 100644
--- a/python/paddle/vision/ops.py
+++ b/python/paddle/vision/ops.py
@@ -34,7 +34,7 @@ def yolo_loss(x,
               use_label_smooth=True,
               name=None,
               scale_x_y=1.):
-    """
+    r"""
 
     This operator generates YOLOv3 loss based on given predict result and ground
     truth boxes.
@@ -242,7 +242,7 @@ def yolo_box(x,
              clip_bbox=True,
              name=None,
              scale_x_y=1.):
-    """
+    r"""
 
     This operator generates YOLO detection boxes from output of YOLOv3 network.