add doc for ErrorClipByValue GradientClipByValue and GradientClipByGlobalNorm

python/paddle/fluid/clip.py

@@ -24,8 +24,6 @@ __all__ = [
     'GradientClipByValue',
     'GradientClipByNorm',
     'GradientClipByGlobalNorm',
-    'append_gradient_clip_ops',
-    'error_clip_callback',
 ]
 
 
@@ -38,6 +36,25 @@ class BaseErrorClipAttr(object):
 
 
 class ErrorClipByValue(BaseErrorClipAttr):
+    """
+    Clips tensor values to the range [min, max].
+
+    Given a tensor t, this operation clips its value to min and max inplace.
+
+    - Any values less than min are set to min.
+    - Any values greater than max are set to max.
+
+    Args:
+        max (float): The maximum value to clip by.
+        min (float, optional): The minimum value to clip by. if not set by user, \
+        will be set to -max by framework.
+
+    Examples:
+        .. code-block:: python
+
+            var = fluid.framework.Variable(..., error_clip=ErrorClipByValue(max=5.0), ...)
+    """
+
     def __init__(self, max, min=None):
         max = float(max)
         if min is None:
@@ -99,6 +116,31 @@ class NullGradientClipAttr(BaseGradientClipAttr):
 
 
 class GradientClipByValue(BaseGradientClipAttr):
+    """
+    Clips gradient values to the range [min, max].
+
+    Given a tensor t, this operation clips its value to min and max inplace.
+
+    - Any values less than min are set to min.
+    - Any values greater than max are set to max.
+
+    Args:
+        max (float): The maximum value to clip by.
+        min (float, optional): The minimum value to clip by. if not set by user, \
+        will be set to -max by framework.
+
+    Examples:
+        .. code-block:: python
+
+            w_param_attrs = ParamAttr(name=None,
+              initializer=UniformInitializer(low=-1.0, high=1.0, seed=0),
+              learning_rate=1.0,
+              regularizer=L1Decay(1.0),
+              trainable=True,
+              clip=GradientClipByValue(-1.0, 1.0))
+            y_predict = fluid.layers.fc(input=x, size=1, param_attr=w_param_attrs)
+    """
+
     def __init__(self, max, min=None):
         max = float(max)
         if min is None:
@@ -120,6 +162,37 @@ class GradientClipByValue(BaseGradientClipAttr):
 
 
 class GradientClipByNorm(BaseGradientClipAttr):
+    """
+    Clips tensor values to a maximum L2-norm.
+
+    This operator limits the L2 norm of the input :math:`X` within :math:`max\_norm`.
+    If the L2 norm of :math:`X` is less than or equal to :math:`max\_norm`, :math:`Out`
+    will be the same as :math:`X`. If the L2 norm of :math:`X` is greater than
+    :math:`max\_norm`, :math:`X` will be linearly scaled to make the L2 norm of
+    :math:`Out` equal to :math:`max\_norm`, as shown in the following formula:
+
+    .. math::
+
+        Out = \\frac{max\_norm * X}{norm(X)},
+
+    where :math:`norm(X)` represents the L2 norm of :math:`X`.
+
+    Args:
+        clip_norm (float): The maximum norm value
+
+    Examples:
+        .. code-block:: python
+
+            w_param_attrs = ParamAttr(name=None,
+              initializer=UniformInitializer(low=-1.0, high=1.0, seed=0),
+              learning_rate=1.0,
+              regularizer=L1Decay(1.0),
+              trainable=True,
+              clip=GradientClipByNorm(clip_norm=2.0))
+            y_predict = fluid.layers.fc(input=x, size=1, param_attr=w_param_attrs)
+
+    """
+
     def __init__(self, clip_norm):
         self.clip_norm = clip_norm
 
@@ -183,15 +256,16 @@ class GradientClipByGlobalNorm(BaseGradientClipAttr):
 
 def set_gradient_clip(clip, param_list=None, program=None):
     """
-        To specify parameters that require gradient clip.
-        Args:
-            clip(BaseGradientClipAttr): An instance of some derived class of BaseGradientClipAttr, 
-                    which describes the type and detailed attributes of required gradient clip.
-            param_list(list, None by default): Parameters that require gradient clip. 
-                    It can be a list of parameter or a list of parameter's name. 
-                    When it's None, all parameters in the program will be included. 
-            program(Program, None by default): The program where parameters are. 
-                    Will be the default main program when assigned with None.
+    To specify parameters that require gradient clip.
+
+    Args:
+        clip(BaseGradientClipAttr): An instance of some derived class of BaseGradientClipAttr,
+                which describes the type and detailed attributes of required gradient clip.
+        param_list(list(Variable)): Parameters that require gradient clip.
+                It can be a list of parameter or a list of parameter's name.
+                When it's None, all parameters in the program will be included.
+        program(Program): The program where parameters are.
+                Will be the default main program when assigned with None.
     """
     if not isinstance(clip, BaseGradientClipAttr):
         raise TypeError(