对多个文档按照要求修改 对应中文的#5453 (#48886)

* fix doc

* test=document_fix
Co-authored-by: NLigoml <39876205+Ligoml@users.noreply.github.com>

python/paddle/nn/functional/activation.py

@@ -813,9 +813,9 @@ def maxout(x, groups, axis=1, name=None):
     Parameters:
         x (Tensor): The input is 4-D Tensor with shape [N, C, H, W] or [N, H, W, C], the data type
             of input is float32 or float64.
-        groups (int, optional): The groups number of maxout. `groups` specifies the
+        groups (int): The groups number of maxout. `groups` specifies the
             index of channel dimension where maxout will be performed. This must be
-            a factor of number of features. Default is 1.
+            a factor of number of features.
         axis (int, optional): The axis along which to perform maxout calculations.
             It should be 1 when data format is NCHW, be -1 or 3 when data format
             is NHWC. If ``axis`` < 0, it works the same way as :math:`axis + D` ,

python/paddle/nn/functional/common.py

@@ -70,17 +70,17 @@ def unfold(x, kernel_sizes, strides=1, paddings=0, dilations=1, name=None):
                                   data type can be float32 or float64
         kernel_sizes(int|list):   The size of convolution kernel, should be [k_h, k_w]
                                   or an integer k treated as [k, k].
-        strides(int|list):        The strides, should be [stride_h, stride_w]
+        strides(int|list, optional):        The strides, should be [stride_h, stride_w]
                                   or an integer stride treated as [sride, stride].
                                   For default, strides will be [1, 1].
-        paddings(int|list):       The paddings of each dimension, should be
+        paddings(int|list, optional):       The paddings of each dimension, should be
                                   [padding_top, padding_left, padding_bottom, padding_right]
                                   or [padding_h, padding_w] or an integer padding.
                                   If [padding_h, padding_w] was given, it will expanded to
                                   [padding_h, padding_w, padding_h, padding_w]. If an integer
                                   padding was given, [padding, padding, padding, padding] will
                                   be used. For default, paddings will be [0, 0, 0, 0]
-        dilations(int|list):      the dilations of convolution kernel, should be
+        dilations(int|list, optional):      the dilations of convolution kernel, should be
                                   [dilation_h, dilation_w], or an integer dilation treated as
                                   [dilation, dilation]. For default, it will be [1, 1].
         name(str, optional): The default value is None.

python/paddle/nn/layer/activation.py

@@ -1401,7 +1401,7 @@ class Maxout(Layer):
         \end{array}
 
     Parameters:
-        groups (int, optional): The groups number of maxout. `groups` specifies the
+        groups (int): The groups number of maxout. `groups` specifies the
             index of channel dimension where maxout will be performed. This must be
             a factor of number of features. Default is 1.
         axis (int, optional): The axis along which to perform maxout calculations.

python/paddle/nn/layer/common.py

@@ -1533,7 +1533,7 @@ class Embedding(Layer):
 
 class Unfold(Layer):
     """
-    This op returns a col buffer of sliding local blocks of input x, also known
+    Returns a col buffer of sliding local blocks of input x, also known
     as im2col for batched 2D image tensors. For each block under the convolution filter,
     all element will be rearranged as a column. While the convolution filter sliding over
     the input feature map, a series of such columns will be formed.

python/paddle/nn/layer/loss.py

@@ -539,7 +539,7 @@ class MSELoss(Layer):
         Out = \operatorname{sum}((input - label)^2)
     where `input` and `label` are `float32` tensors of same shape.
     Parameters:
-        reduction (string, optional): The reduction method for the output,
+        reduction (str, optional): The reduction method for the output,
             could be 'none' | 'mean' | 'sum'.
             If :attr:`reduction` is ``'mean'``, the reduced mean loss is returned.
             If :attr:`size_average` is ``'sum'``, the reduced sum loss is returned.