[CodeStyle][W191][E101] remove tabs in python files (#46288)

python/paddle/nn/functional/loss.py

@@ -473,7 +473,6 @@ def edit_distance(input,
 
     Returns:
         Tuple:
-
             distance(Tensor): edit distance result, its data type is float32, and its shape is (batch_size, 1).
             sequence_num(Tensor): sequence number, its data type is float32, and its shape is (1,).
 
@@ -3266,8 +3265,8 @@ def triplet_margin_with_distance_loss(input,
 
         distance_function (callable, optional): Quantifies the distance between two tensors. if not specified, 2 norm functions will be used.
 
-	    margin (float, optional):Default: :math:`1`.A nonnegative margin representing the minimum difference
-            between the positive and negative distances required for the loss to be 0.
+        margin (float, optional): A nonnegative margin representing the minimum difference
+            between the positive and negative distances required for the loss to be 0. Default value is :math:`1`.
 
         swap (bool, optional):The distance swap changes the negative distance to the swap distance (distance between positive samples
                 and negative samples) if swap distance smaller than negative distance. Default: ``False``.

python/paddle/nn/layer/norm.py

@@ -210,7 +210,7 @@ Where `H` means height of feature map, `W` means width of feature map.
             If it is set to None or one attribute of ParamAttr, instance_norm
             will create ParamAttr as bias_attr, the name of bias can be set in ParamAttr.
             If the Initializer of the bias_attr is not set, the bias is initialized zero.
-             If it is set to False, will not create bias_attr. Default: None.
+    `       If it is set to False, will not create bias_attr. Default: None.
         data_format(str, optional): Specify the input data format, could be "NCHW". Default: NCHW.
         name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 

python/paddle/optimizer/adagrad.py

@@ -45,18 +45,18 @@ class Adagrad(Optimizer):
             It can be a float value or a ``Variable`` with a float type.
         epsilon (float, optional): A small float value for numerical stability.
             The default value is 1e-06.
-	parameters (list|tuple, optional): List/Tuple of ``Tensor`` to update to minimize ``loss``. \
-	    This parameter is required in dygraph mode. And you can specify different options for \
-            different parameter groups such as the learning rate, weight decay, etc, \
-            then the parameters are list of dict. Note that the learning_rate in paramter groups \
-            represents the scale of base learning_rate. \
+        parameters (list|tuple, optional): List/Tuple of ``Tensor`` to update to minimize ``loss``.
+            This parameter is required in dygraph mode. And you can specify different options for
+            different parameter groups such as the learning rate, weight decay, etc,
+            then the parameters are list of dict. Note that the learning_rate in paramter groups
+            represents the scale of base learning_rate.
             The default value is None in static mode, at this time all parameters will be updated.
-	weight_decay (float|WeightDecayRegularizer, optional): The strategy of regularization. \
-	    It canbe a float value as coeff of L2 regularization or \
+        weight_decay (float|WeightDecayRegularizer, optional): The strategy of regularization.
+            It canbe a float value as coeff of L2 regularization or
             :ref:`api_paddle_regularizer_L1Decay`, :ref:`api_paddle_regularizer_L2Decay`.
-	    If a parameter has set regularizer using :ref:`api_paddle_fluid_param_attr_aramAttr` already, \
-	    the regularization setting here in optimizer will be ignored for this parameter. \
-	    Otherwise, the regularization setting here in optimizer will take effect. \
+            If a parameter has set regularizer using :ref:`api_paddle_fluid_param_attr_aramAttr` already,
+            the regularization setting here in optimizer will be ignored for this parameter.
+            Otherwise, the regularization setting here in optimizer will take effect.
             Default None, meaning there is no regularization.
         grad_clip (GradientClipBase, optional): Gradient cliping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three cliping strategies,

python/paddle/optimizer/adam.py

@@ -67,18 +67,18 @@ class Adam(Optimizer):
         epsilon (float|Tensor, optional): A small float value for numerical stability.
             It should be a float number or a Tensor with shape [1] and data type as float32.
             The default value is 1e-08.
-	parameters (list|tuple, optional): List/Tuple of ``Tensor`` to update to minimize ``loss``. \
-	    This parameter is required in dygraph mode. And you can specify different options for \
-            different parameter groups such as the learning rate, weight decay, etc, \
-            then the parameters are list of dict. Note that the learning_rate in paramter groups \
-            represents the scale of base learning_rate. \
+        parameters (list|tuple, optional): List/Tuple of ``Tensor`` to update to minimize ``loss``.
+            This parameter is required in dygraph mode. And you can specify different options for
+            different parameter groups such as the learning rate, weight decay, etc,
+            then the parameters are list of dict. Note that the learning_rate in paramter groups
+            represents the scale of base learning_rate.
             The default value is None in static mode, at this time all parameters will be updated.
-	weight_decay (float|WeightDecayRegularizer, optional): The strategy of regularization. \
-	    It canbe a float value as coeff of L2 regularization or \
+        weight_decay (float|WeightDecayRegularizer, optional): The strategy of regularization.
+            It canbe a float value as coeff of L2 regularization or
             :ref:`api_fluid_regularizer_L1Decay`, :ref:`api_fluid_regularizer_L2Decay`.
-	    If a parameter has set regularizer using :ref:`api_fluid_ParamAttr` already, \
-	    the regularization setting here in optimizer will be ignored for this parameter. \
-	    Otherwise, the regularization setting here in optimizer will take effect. \
+            If a parameter has set regularizer using :ref:`api_fluid_ParamAttr` already,
+            the regularization setting here in optimizer will be ignored for this parameter.
+            Otherwise, the regularization setting here in optimizer will take effect.
             Default None, meaning there is no regularization.
         grad_clip (GradientClipBase, optional): Gradient cliping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three cliping strategies

python/paddle/optimizer/adamax.py

@@ -57,18 +57,18 @@ class Adamax(Optimizer):
             The default value is 0.999.
         epsilon (float, optional): A small float value for numerical stability.
             The default value is 1e-08.
-	parameters (list|tuple, optional): List/Tuple of ``Tensor`` to update to minimize ``loss``. \
-	    This parameter is required in dygraph mode. And you can specify different options for \
-            different parameter groups such as the learning rate, weight decay, etc, \
-            then the parameters are list of dict. Note that the learning_rate in paramter groups \
-            represents the scale of base learning_rate. \
+        parameters (list|tuple, optional): List/Tuple of ``Tensor`` to update to minimize ``loss``.
+            This parameter is required in dygraph mode. And you can specify different options for
+            different parameter groups such as the learning rate, weight decay, etc,
+            then the parameters are list of dict. Note that the learning_rate in paramter groups
+            represents the scale of base learning_rate.
             The default value is None in static mode, at this time all parameters will be updated.
-	weight_decay (float|WeightDecayRegularizer, optional): The strategy of regularization. \
-	    It canbe a float value as coeff of L2 regularization or \
+        weight_decay (float|WeightDecayRegularizer, optional): The strategy of regularization.
+            It canbe a float value as coeff of L2 regularization or
             :ref:`api_fluid_regularizer_L1Decay`, :ref:`api_fluid_regularizer_L2Decay`.
-	    If a parameter has set regularizer using :ref:`api_fluid_ParamAttr` already, \
-	    the regularization setting here in optimizer will be ignored for this parameter. \
-	    Otherwise, the regularization setting here in optimizer will take effect. \
+            If a parameter has set regularizer using :ref:`api_fluid_ParamAttr` already,
+            the regularization setting here in optimizer will be ignored for this parameter.
+            Otherwise, the regularization setting here in optimizer will take effect.
             Default None, meaning there is no regularization.
         grad_clip (GradientClipBase, optional): Gradient cliping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three cliping strategies

python/paddle/optimizer/adamw.py

@@ -54,11 +54,11 @@ class AdamW(Optimizer):
     Args:
         learning_rate (float|LRScheduler, optional): The learning rate used to update ``Parameter``.
             It can be a float value or a LRScheduler. The default value is 0.001.
-        parameters (list|tuple, optional): List/Tuple of ``Tensor`` names to update to minimize ``loss``. \
-            This parameter is required in dygraph mode. And you can specify different options for \
-            different parameter groups such as the learning rate, weight decay, etc, \
-            then the parameters are list of dict. Note that the learning_rate in paramter groups \
-            represents the scale of base learning_rate. \
+        parameters (list|tuple, optional): List/Tuple of ``Tensor`` names to update to minimize ``loss``.
+            This parameter is required in dygraph mode. And you can specify different options for
+            different parameter groups such as the learning rate, weight decay, etc,
+            then the parameters are list of dict. Note that the learning_rate in paramter groups
+            represents the scale of base learning_rate.
             The default value is None in static mode, at this time all parameters will be updated.
         beta1 (float|Tensor, optional): The exponential decay rate for the 1st moment estimates.
             It should be a float number or a Tensor with shape [1] and data type as float32.

python/paddle/tensor/attribute.py

@@ -63,12 +63,6 @@ def rank(input):
 
 def shape(input):
     """
-    :alias_main: paddle.shape
-	:alias: paddle.shape,paddle.tensor.shape,paddle.tensor.attribute.shape
-	:old_api: paddle.fluid.layers.shape
-
-    **Shape Layer**
-
     Get the shape of the input.
 
     .. code-block:: text

python/paddle/tensor/manipulation.py

@@ -416,12 +416,6 @@ def transpose(x, perm, name=None):
 
 def unstack(x, axis=0, num=None):
     """
-    :alias_main: paddle.unstack
-	:alias: paddle.unstack,paddle.tensor.unstack,paddle.tensor.manipulation.unstack
-	:old_api: paddle.fluid.layers.unstack
-
-    **UnStack Layer**
-
     This layer unstacks input Tensor :code:`x` into several Tensors along :code:`axis`.
 
     If :code:`axis` < 0, it would be replaced with :code:`axis+rank(x)`.