InstanceNorm1D、InstanceNorm2D、InstanceNorm3D (#48940)

* modified:   python/paddle/nn/layer/norm.py

* modified:   python/paddle/nn/layer/norm.py

* modified:   python/paddle/nn/layer/norm.py

* modified:   python/paddle/nn/layer/norm.py

* modified:   python/paddle/nn/layer/norm.py

* modified:   python/paddle/nn/layer/norm.py

* test=docs_preview

* InstanceNorm2D中文档格式修改

* test=docs_preview

* modified:   python/paddle/nn/functional/loss.py
	modified:   python/paddle/nn/functional/norm.py
	modified:   python/paddle/nn/layer/loss.py
	modified:   python/paddle/nn/layer/norm.py

* test=docs_preview

* test=docs_preview

python/paddle/nn/functional/loss.py

@@ -1546,33 +1546,27 @@ def kl_div(input, label, reduction='mean', name=None):
 
     $$l(x, y) = y * (\log(y) - x)$$
 
-    While :math:`x` is input and :math:`y` is label.
+    Here :math:`x` is input and :math:`y` is label.
 
-    While :attr:`reduction` is :attr:`none`, output loss is in
-    the same shape as input, loss in each point is calculated
-    separately and no reduction is applied.
+    If `reduction` is ``'none'``, the output loss is the same shape as the input, and the loss at each point is calculated separately. There is no reduction to the result.
 
-    While :attr:`reduction` is :attr:`mean`, output loss is in
-    shape of [1] and loss value is the mean value of all losses.
+    If `reduction` is ``'mean'``, the output loss is the shape of [1], and the output is the average of all losses.
 
-    While :attr:`reduction` is :attr:`sum`, output loss is in
-    shape of [1] and loss value is the sum value of all losses.
+    If `reduction` is ``'sum'``, the output loss is the shape of [1], and the output is the sum of all losses.
 
-    While :attr:`reduction` is :attr:`batchmean`, output loss is
-    in shape of [1] and loss value is the sum value of all losses
-    divided by batch size.
+    If `reduction` is ``'batchmean'``, the output loss is the shape of [N], N is the batch size, and the output is the sum of all losses divided by the batch size.
 
     Args:
         input (Tensor): The input tensor. The shapes is [N, *], where N is batch size and `*` means
-             any number of additional dimensions. It's data type should be float32, float64.
+            any number of additional dimensions. It's data type should be float32, float64.
         label (Tensor): label. The shapes is [N, *], same shape as ``input`` . It's data type should be float32, float64.
-        reduction (Tensor): Indicate how to average the loss,
-             the candicates are ``'none'`` | ``'batchmean'`` | ``'mean'`` | ``'sum'``.
-             If `reduction` is ``'mean'``, the reduced mean loss is returned;
-             If `reduction` is ``'batchmean'``, the sum loss divided by batch size is returned;
-             if `reduction` is ``'sum'``, the reduced sum loss is returned;
-             if `reduction` is ``'none'``, no reduction will be apllied.
-             Default is ``'mean'``.
+        reduction (str, optional): Indicate how to average the loss,
+            the candicates are ``'none'`` | ``'batchmean'`` | ``'mean'`` | ``'sum'``.
+            If `reduction` is ``'mean'``, the reduced mean loss is returned;
+            If `reduction` is ``'batchmean'``, the sum loss divided by batch size is returned;
+            if `reduction` is ``'sum'``, the reduced sum loss is returned;
+            if `reduction` is ``'none'``, no reduction will be apllied.
+            Default is ``'mean'``.
         name(str, optional): Name for the operation (optional, default is None). For more information,
             please refer to :ref:`api_guide_Name`.
 

python/paddle/nn/functional/norm.py

@@ -327,7 +327,8 @@ def layer_norm(
     x, normalized_shape, weight=None, bias=None, epsilon=1e-05, name=None
 ):
     """
-    see more detail in paddle.nn.LayerNorm
+    nn.LayerNorm is recommended.
+    For more information, please refer to :ref:`api_paddle_nn_LayerNorm` .
 
     Parameters:
         x(Tensor): Input Tensor. It's data type should be float32, float64.
@@ -335,11 +336,11 @@ def layer_norm(
             size :math:`[*, normalized_shape[0], normalized_shape[1], ..., normalized_shape[-1]]`.
             If it is a single integer, this module will normalize over the last dimension
             which is expected to be of that specific size.
-        epsilon(float, optional): The small value added to the variance to prevent
-            division by zero. Default: 1e-05.
         weight(Tensor, optional): The weight tensor of batch_norm. Default: None.
         bias(Tensor, optional): The bias tensor of batch_norm. Default: None.
-        name(str, optional): Name for the LayerNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
+        epsilon(float, optional): The small value added to the variance to prevent
+            division by zero. Default: 1e-05.
+        name(str, optional): Name for the LayerNorm, default is None. For more information, please refer to :ref:`api_guide_Name` .
 
     Returns:
         None
@@ -448,7 +449,7 @@ def instance_norm(
     name=None,
 ):
     """
-    See more detail in nn.layer.InstanceNorm2D.
+    It is recommended to use :ref:`api_paddle_nn_InstanceNorm1D` , :ref:`api_paddle_nn_InstanceNorm2D` , :ref:`api_paddle_nn_InstanceNorm3D` to call this method internally.
 
     Parameters:
         x(Tensor): Input Tensor. It's data type should be float32, float64.

python/paddle/nn/layer/loss.py

@@ -891,19 +891,32 @@ class KLDivLoss(Layer):
 
     $$l(x, y) = y * (\log(y) - x)$$
 
+    Here :math:`x` is input and :math:`y` is label.
+
+    If `reduction` is ``'none'``, the output loss is the same shape as the input, and the loss at each point is calculated separately. There is no reduction to the result.
+
+    If `reduction` is ``'mean'``, the output loss is the shape of [1], and the output is the average of all losses.
+
+    If `reduction` is ``'sum'``, the output loss is the shape of [1], and the output is the sum of all losses.
+
+    If `reduction` is ``'batchmean'``, the output loss is the shape of [N], N is the batch size, and the output is the sum of all losses divided by the batch size.
+
     Parameters:
-        reduction (Tensor): Indicate how to average the loss,
-             the candicates are ``'none'`` | ``'batchmean'`` | ``'mean'`` | ``'sum'``.
-             If `reduction` is ``'mean'``, the reduced mean loss is returned;
-             If `reduction` is ``'batchmean'``, the sum loss divided by batch size is returned;
-             if `reduction` is ``'sum'``, the reduced sum loss is returned;
-             if `reduction` is ``'none'``, no reduction will be apllied.
-             Default is ``'mean'``.
+        reduction (str, optional): Indicate how to average the loss,
+            the candicates are ``'none'`` | ``'batchmean'`` | ``'mean'`` | ``'sum'``.
+            If `reduction` is ``'mean'``, the reduced mean loss is returned;
+            If `reduction` is ``'batchmean'``, the sum loss divided by batch size is returned;
+            if `reduction` is ``'sum'``, the reduced sum loss is returned;
+            if `reduction` is ``'none'``, no reduction will be apllied.
+            Default is ``'mean'``.
 
     Shape:
-        - input (Tensor): ``(N, *)``, where ``*`` means, any number of additional dimensions.
-        - label (Tensor): ``(N, *)``, same shape as input.
-        - output (Tensor): tensor with shape: [1] by default.
+
+        input (Tensor): ``(N, *)``, where ``*`` means, any number of additional dimensions.
+
+        label (Tensor): ``(N, *)``, same shape as input.
+
+        output (Tensor): tensor with shape: [1] by default.
 
     Examples:
         .. code-block:: python

python/paddle/nn/layer/norm.py

@@ -132,25 +132,25 @@ class InstanceNorm1D(_InstanceNormBase):
         \sigma_{\beta}^{2} + \epsilon}} \qquad &//\ normalize \\
         y_i &\gets \gamma \hat{x_i} + \beta \qquad &//\ scale\ and\ shift
 
-Where `H` means height of feature map, `W` means width of feature map.
+    Where `H` means height of feature map, `W` means width of feature map.
 
     Parameters:
         num_features(int): Indicate the number of channels of the input ``Tensor``.
         epsilon(float, optional): A value added to the denominator for
             numerical stability. Default is 1e-5.
         momentum(float, optional): The value used for the moving_mean and moving_var computation. Default: 0.9.
-        weight_attr(ParamAttr|bool, optional): The parameter attribute for Parameter `scale`
-            of instance_norm. If it is set to None or one attribute of ParamAttr, instance_norm
+        weight_attr(ParamAttr|bool, optional): The parameter attribute for Parameter `scale` of instance_norm.
+            If it is set to None or one attribute of ParamAttr, instance_norm
             will create ParamAttr as weight_attr, the name of scale can be set in ParamAttr.
             If the Initializer of the weight_attr is not set, the parameter is initialized
-            one. If it is set to False, will not create weight_attr. Default: None.
+            one. If it is set to False, will not create weight_attr. Default: None. For more information, please refer to :ref:`api_paddle_ParamAttr` .
         bias_attr(ParamAttr|bool, optional): The parameter attribute for the bias of instance_norm.
             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. For more information, please refer to :ref:`api_paddle_ParamAttr` .
         data_format(str, optional): Specify the input data format, may be "NC", "NCL". Default "NCL".
-        name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
+        name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name` .
 
 
     Shape:
@@ -175,6 +175,26 @@ Where `H` means height of feature map, `W` means width of feature map.
 
     """
 
+    def __init__(
+        self,
+        num_features,
+        epsilon=0.00001,
+        momentum=0.9,
+        weight_attr=None,
+        bias_attr=None,
+        data_format="NCL",
+        name=None,
+    ):
+        super().__init__(
+            num_features,
+            epsilon,
+            momentum,
+            weight_attr,
+            bias_attr,
+            data_format,
+            name,
+        )
+
     def _check_input_dim(self, input):
         if len(input.shape) != 2 and len(input.shape) != 3:
             raise ValueError(
@@ -203,7 +223,7 @@ class InstanceNorm2D(_InstanceNormBase):
         \sigma_{\beta}^{2} + \epsilon}} \qquad &//\ normalize \\
         y_i &\gets \gamma \hat{x_i} + \beta \qquad &//\ scale\ and\ shift
 
-Where `H` means height of feature map, `W` means width of feature map.
+    Where `H` means height of feature map, `W` means width of feature map.
 
     Parameters:
         num_features(int): Indicate the number of channels of the input ``Tensor``.
@@ -214,14 +234,14 @@ Where `H` means height of feature map, `W` means width of feature map.
             of instance_norm. If it is set to None or one attribute of ParamAttr, instance_norm
             will create ParamAttr as weight_attr, the name of scale can be set in ParamAttr.
             If the Initializer of the weight_attr is not set, the parameter is initialized
-            one. If it is set to False, will not create weight_attr. Default: None.
+            one. If it is set to False, will not create weight_attr. Default: None. For more information, please refer to :ref:`api_paddle_ParamAttr` .
         bias_attr(ParamAttr|bool, optional): The parameter attribute for the bias of instance_norm.
             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. For more information, please refer to :ref:`api_paddle_ParamAttr` .
         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`..
+        name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name` .
 
     Shape:
         - x: 4-D tensor with shape: (batch, num_features, height, weight).
@@ -244,6 +264,26 @@ Where `H` means height of feature map, `W` means width of feature map.
             print(instance_norm_out)
     """
 
+    def __init__(
+        self,
+        num_features,
+        epsilon=0.00001,
+        momentum=0.9,
+        weight_attr=None,
+        bias_attr=None,
+        data_format="NCHW",
+        name=None,
+    ):
+        super().__init__(
+            num_features,
+            epsilon,
+            momentum,
+            weight_attr,
+            bias_attr,
+            data_format,
+            name,
+        )
+
     def _check_input_dim(self, input):
         if len(input.shape) != 4:
             raise ValueError(
@@ -255,7 +295,7 @@ class InstanceNorm3D(_InstanceNormBase):
     r"""
     Create a callable object of `InstanceNorm3D`. Applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization .
 
-    DataLayout: NCHW `[batch, in_channels, D, in_height, in_width]`
+    DataLayout: NCDHW `[batch, in_channels, D, in_height, in_width]`
 
 
     :math:`input` is the input features over a mini-batch.
@@ -270,7 +310,7 @@ class InstanceNorm3D(_InstanceNormBase):
         \sigma_{\beta}^{2} + \epsilon}} \qquad &//\ normalize \\
         y_i &\gets \gamma \hat{x_i} + \beta \qquad &//\ scale\ and\ shift
 
-Where `H` means height of feature map, `W` means width of feature map.
+    Where `H` means height of feature map, `W` means width of feature map.
 
     Parameters:
         num_features(int): Indicate the number of channels of the input ``Tensor``.
@@ -281,14 +321,14 @@ Where `H` means height of feature map, `W` means width of feature map.
             of instance_norm. If it is set to None or one attribute of ParamAttr, instance_norm
             will create ParamAttr as weight_attr, the name of scale can be set in ParamAttr.
             If the Initializer of the weight_attr is not set, the parameter is initialized
-            one. If it is set to False, will not create weight_attr. Default: None.
+            one. If it is set to False, will not create weight_attr. Default: None. For more information, please refer to :ref:`api_paddle_ParamAttr` .
         bias_attr(ParamAttr|bool, optional): The parameter attribute for the bias of instance_norm.
             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. For more information, please refer to :ref:`api_paddle_ParamAttr` .
         data_format(str, optional): Specify the input data format, could be "NCDHW". Default: NCDHW.
-        name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
+        name(str, optional): Name for the InstanceNorm, default is None. For more information, please refer to :ref:`api_guide_Name` .
 
     Shape:
         - x: 5-D tensor with shape: (batch, num_features, dims, height, weight).
@@ -311,6 +351,26 @@ Where `H` means height of feature map, `W` means width of feature map.
             print(instance_norm_out.numpy)
     """
 
+    def __init__(
+        self,
+        num_features,
+        epsilon=0.00001,
+        momentum=0.9,
+        weight_attr=None,
+        bias_attr=None,
+        data_format="NCDHW",
+        name=None,
+    ):
+        super().__init__(
+            num_features,
+            epsilon,
+            momentum,
+            weight_attr,
+            bias_attr,
+            data_format,
+            name,
+        )
+
     def _check_input_dim(self, input):
         if len(input.shape) != 5:
             raise ValueError(
@@ -508,11 +568,11 @@ class LayerNorm(Layer):
             division by zero. Default: 1e-05.
         weight_attr(ParamAttr|bool, optional): The parameter attribute for the learnable
             gain :math:`g`. If False, weight is None. If is None, a default :code:`ParamAttr` would be added as scale. The
-            :attr:`param_attr` is initialized as 1 if it is added. Default: None.
+            :attr:`param_attr` is initialized as 1 if it is added. Default: None. For more information, please refer to :ref:`api_paddle_ParamAttr` .
         bias_attr(ParamAttr|bool, optional): The parameter attribute for the learnable
             bias :math:`b`. If is False, bias is None. If is None, a default :code:`ParamAttr` would be added as bias. The
-            :attr:`bias_attr` is initialized as 0 if it is added. Default: None.
-        name(str, optional): Name for the LayerNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
+            :attr:`bias_attr` is initialized as 0 if it is added. Default: None. For more information, please refer to :ref:`api_paddle_ParamAttr` .
+        name(str, optional): Name for the LayerNorm, default is None. For more information, please refer to :ref:`api_guide_Name` .
 
     Shape:
         - x: 2-D, 3-D, 4-D or 5-D tensor.