paddle/nn fix formula bugs

python/paddle/fluid/clip.py

@@ -286,18 +286,18 @@ class ClipGradByNorm(ClipGradBase):
 
     .. math::
         Out =
-        \\left \{
-        \\begin{aligned}
-        & X & & if (norm(X) \\leq clip\_norm) \\\\
-        & \\frac{clip\_norm*X}{norm(X)} & & if (norm(X) > clip\_norm) \\\\
-        \\end{aligned}
-        \\right.
+        \left\{
+            \begin{array}{ccl}
+                X & & if (norm(X) \leq clip\_norm) \\
+                \frac{clip\_norm*X}{norm(X)} & & if (norm(X) > clip\_norm) \\
+        \end{array}
+        \right.
 
 
     where :math:`norm(X)` represents the L2 norm of :math:`X`.
 
     .. math::
-        norm(X) = ( \\sum_{i=1}^{n}|x\_i|^2)^{ \\frac{1}{2}}
+        norm(X) = ( \sum_{i=1}^{n}|x\_i|^2)^{ \frac{1}{2}}
 
     Note:
         ``need_clip`` of ``ClipGradByNorm`` HAS BEEN DEPRECATED since 2.0. 
@@ -389,7 +389,7 @@ class ClipGradByGlobalNorm(ClipGradBase):
 
     .. math::
 
-        t\_list[i] = t\_list[i] * \\frac{clip\_norm}{\max(global\_norm, clip\_norm)}
+        t\_list[i] = t\_list[i] * \frac{clip\_norm}{\max(global\_norm, clip\_norm)}
 
     where:
 

python/paddle/fluid/dygraph/nn.py

@@ -1151,9 +1151,6 @@ def forward(self, input):
 
 class BatchNorm(layers.Layer):
     r"""
-    :alias_main: paddle.nn.BatchNorm
-	:alias: paddle.nn.BatchNorm,paddle.nn.layer.BatchNorm,paddle.nn.layer.norm.BatchNorm
-	:old_api: paddle.fluid.dygraph.BatchNorm
 
     This interface is used to construct a callable object of the ``BatchNorm`` class.
     For more details, refer to code examples.
@@ -1164,16 +1161,16 @@ class BatchNorm(layers.Layer):
     Internal Covariate Shift <https://arxiv.org/pdf/1502.03167.pdf>`_
     for more details.
 
-    When use_global_stats = False, the :math:`\\mu_{\\beta}` 
-    and :math:`\\sigma_{\\beta}^{2}` are the statistics of one mini-batch.
+    When use_global_stats = False, the :math:`\mu_{\beta}` 
+    and :math:`\sigma_{\beta}^{2}` are the statistics of one mini-batch.
     Calculated as follows:
 
     ..  math::
 
-        \\mu_{\\beta} &\\gets \\frac{1}{m} \\sum_{i=1}^{m} x_i \\qquad &//\\
-        \ mini-batch\ mean \\\\
-        \\sigma_{\\beta}^{2} &\\gets \\frac{1}{m} \\sum_{i=1}^{m}(x_i - \\
-        \\mu_{\\beta})^2 \\qquad &//\ mini-batch\ variance \\\\
+        \mu_{\beta} &\gets \frac{1}{m} \sum_{i=1}^{m} x_i \qquad &
+        //\ mini-batch\ mean \\
+        \sigma_{\beta}^{2} &\gets \frac{1}{m} \sum_{i=1}^{m}(x_i - \mu_{\beta})^2 \qquad &
+        //\ mini-batch\ variance \\
 
     - :math:`x` : mini-batch data
     - :math:`m` : the size of the mini-batch data
@@ -1191,13 +1188,14 @@ class BatchNorm(layers.Layer):
 
     ..  math::
 
-        \\hat{x_i} &\\gets \\frac{x_i - \\mu_\\beta} {\\sqrt{\\
-        \\sigma_{\\beta}^{2} + \\epsilon}} \\qquad &//\ normalize \\\\
-        y_i &\\gets \\gamma \\hat{x_i} + \\beta \\qquad &//\ scale\ and\ shift
+        \hat{x_i} &\gets \frac{x_i - \mu_\beta} {\sqrt{\
+        \sigma_{\beta}^{2} + \epsilon}} \qquad &//\ normalize \\
+        y_i &\gets \gamma \hat{x_i} + \beta \qquad &//\ scale\ and\ shift
+
 
-    - :math:`\\epsilon` : add a smaller value to the variance to prevent division by zero
-    - :math:`\\gamma` : trainable proportional parameter
-    - :math:`\\beta` : trainable deviation parameter
+    - :math:`\epsilon` : add a smaller value to the variance to prevent division by zero
+    - :math:`\gamma` : trainable proportional parameter
+    - :math:`\beta` : trainable deviation parameter
 
     Parameters:
         num_channels(int): Indicate the number of channels of the input ``Tensor``.
@@ -3011,9 +3009,9 @@ class SpectralNorm(layers.Layer):
 
     .. math::
 
-        \mathbf{v} := \\frac{\mathbf{W}^{T} \mathbf{u}}{\|\mathbf{W}^{T} \mathbf{u}\|_2}
+        \mathbf{v} := \frac{\mathbf{W}^{T} \mathbf{u}}{\|\mathbf{W}^{T} \mathbf{u}\|_2}
 
-        \mathbf{u} := \\frac{\mathbf{W}^{T} \mathbf{v}}{\|\mathbf{W}^{T} \mathbf{v}\|_2}
+        \mathbf{u} := \frac{\mathbf{W}^{T} \mathbf{v}}{\|\mathbf{W}^{T} \mathbf{v}\|_2}
 
     Step 3:
     Calculate :math:`\sigma(\mathbf{W})` and normalize weight values.
@@ -3022,7 +3020,7 @@ class SpectralNorm(layers.Layer):
 
         \sigma(\mathbf{W}) = \mathbf{u}^{T} \mathbf{W} \mathbf{v}
 
-        \mathbf{W} = \\frac{\mathbf{W}}{\sigma(\mathbf{W})}
+        \mathbf{W} = \frac{\mathbf{W}}{\sigma(\mathbf{W})}
 
 
     Refer to `Spectral Normalization <https://arxiv.org/abs/1802.05957>`_ .

python/paddle/nn/initializer/kaiming.py

@@ -33,7 +33,7 @@ class KaimingNormal(MSRAInitializer):
 
     .. math::
 
-        \sqrt{\\frac{2.0}{fan\_in}}
+        \sqrt{\frac{2.0}{fan\_in}}
 
     Args:
         fan_in (float32|None): fan_in for Kaiming normal Initializer. If None, it is\
@@ -75,7 +75,7 @@ class KaimingUniform(MSRAInitializer):
 
     .. math::
 
-        x = \sqrt{\\frac{6.0}{fan\_in}}
+        x = \sqrt{\frac{6.0}{fan\_in}}
 
     Args:
         fan_in (float32|None): fan_in for Kaiming uniform Initializer. If None, it is\

python/paddle/nn/initializer/xavier.py

@@ -28,7 +28,7 @@ class XavierNormal(XavierInitializer):
 
     .. math::
 
-        \sqrt{\\frac{2.0}{fan\_in + fan\_out}}
+        \sqrt{\frac{2.0}{fan\_in + fan\_out}}
 
 
     Args:
@@ -83,7 +83,7 @@ class XavierUniform(XavierInitializer):
 
     .. math::
 
-        x = \sqrt{\\frac{6.0}{fan\_in + fan\_out}}
+        x = \sqrt{\frac{6.0}{fan\_in + fan\_out}}
 
     Args:
         fan_in (float, optional): fan_in for Xavier initialization, it is