[Docathon] Fix NO.8-NO.11 API label (PaddlePaddle#57614)

python/paddle/base/layers/math_op_patch.py

@@ -241,7 +241,7 @@ def place(self):
     def astype(self, dtype):
         """
         **Notes**:
-            **The variable must be a** :ref:`api_base_Tensor`
+            **The variable must be a** :ref:`api_paddle_Tensor`
 
         Cast a variable to a specified data type.
 

python/paddle/incubate/optimizer/lars_momentum.py

@@ -50,8 +50,8 @@ class LarsMomentumOptimizer(Optimizer):
             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
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): This parameter is used by developers to print debugging information. \
             For details, please refer to :ref:`api_guide_Name`. Default is None.
         exclude_from_weight_decay (list[str], optional): Name string of layers which will be exclude from lars weight decay. Default is None.

python/paddle/incubate/optimizer/lbfgs.py

@@ -64,8 +64,8 @@ class LBFGS(Optimizer):
             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 \
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` , \
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` , \
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): Normally there is no need for user to set this property.
             For more information, please refer to :ref:`api_guide_Name`.
             The default value is None.

python/paddle/nn/clip.py

@@ -950,16 +950,16 @@ def set_gradient_clip(clip, param_list=None, program=None):
         and it may be removed in future releases, so it is not recommended.
         It is recommended to set ``grad_clip`` when initializing the ``optimizer`` ,
         this is a better method to clip gradient. There are three clipping strategies:
-         :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-         :ref:`api_base_clip_GradientClipByValue` .
+         :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+         :ref:`api_paddle_nn_ClipGradByValue` .
 
     To specify parameters that require gradient clip.
 
     Args:
         grad_clip (GradientClipBase, optional): Gradient cliping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three cliping strategies
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default value: None, and there is no
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default value: None, and there is no
             gradient clipping.
         param_list (list(Variable), optional): Parameters that require gradient clip.
                 It can be a list of parameter or a list of parameter's name.

python/paddle/optimizer/adadelta.py

@@ -61,8 +61,8 @@ class Adadelta(Optimizer):
             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
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): The default value is None. Normally there is no need for user
                 to set this property. For more information, please refer to
                 :ref:`api_guide_Name` .

python/paddle/optimizer/adam.py

@@ -79,8 +79,8 @@ class Adam(Optimizer):
             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
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         lazy_mode (bool, optional): The official Adam algorithm has two moving-average accumulators.
             The accumulators are updated at every step. Every element of the two moving-average
             is updated in both dense mode and sparse mode. If the size of parameter is very large,

python/paddle/optimizer/adamax.py

@@ -74,8 +74,8 @@ class Adamax(Optimizer):
             Default None, meaning there is no regularization.
         grad_clip (GradientClipBase, optional): Gradient clipping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three clipping strategies
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): Normally there is no need for user to set this property.
             For more information, please refer to :ref:`api_guide_Name`.
             The default value is None.

python/paddle/optimizer/adamw.py

@@ -77,8 +77,8 @@ class AdamW(Optimizer):
             Default: None.
         grad_clip (GradientClipBase, optional): Gradient clipping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three clipping strategies
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         lazy_mode (bool, optional): The official Adam algorithm has two moving-average accumulators.
             The accumulators are updated at every step. Every element of the two moving-average
             is updated in both dense mode and sparse mode. If the size of parameter is very large,

python/paddle/optimizer/lbfgs.py

@@ -346,8 +346,8 @@ class LBFGS(Optimizer):
             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 \
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` , \
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` , \
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): Normally there is no need for user to set this property.
             For more information, please refer to :ref:`api_guide_Name`.
             The default value is None.

python/paddle/optimizer/momentum.py

@@ -66,8 +66,8 @@ class Momentum(Optimizer):
             Default None, meaning there is no regularization.
         grad_clip (GradientClipBase, optional): Gradient clipping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three clipping strategies
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         multi_precision (bool, optional): Whether to use multi-precision during weight updating. Default is false.
         rescale_grad (float, optional): Multiply the gradient with `rescale_grad` before updating. \
             Often choose to be ``1.0/batch_size``.

python/paddle/optimizer/optimizer.py

@@ -115,8 +115,8 @@ class Optimizer:
             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 \
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` , \
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` , \
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): Normally there is no need for user to set this property.
             For more information, please refer to :ref:`api_guide_Name`.
             The default value is None.

python/paddle/optimizer/rmsprop.py

@@ -98,8 +98,8 @@ class RMSProp(Optimizer):
           Default None, meaning there is no regularization.
         grad_clip (GradientClipBase, optional): Gradient clipping strategy, it's an instance of
           some derived class of ``GradientClipBase`` . There are three clipping strategies
-          ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-          :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+          ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+          :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): This parameter is used by developers to print debugging information.
           For details, please refer to :ref:`api_guide_Name`. Default is None.
 

python/paddle/optimizer/sgd.py

@@ -47,8 +47,8 @@ class SGD(Optimizer):
             Default None, meaning there is no regularization.
         grad_clip (GradientClipBase, optional): Gradient clipping strategy, it's an instance of
             some derived class of ``GradientClipBase`` . There are three clipping strategies
-            ( :ref:`api_base_clip_GradientClipByGlobalNorm` , :ref:`api_base_clip_GradientClipByNorm` ,
-            :ref:`api_base_clip_GradientClipByValue` ). Default None, meaning there is no gradient clipping.
+            ( :ref:`api_paddle_nn_ClipGradByGlobalNorm` , :ref:`api_paddle_nn_ClipGradByNorm` ,
+            :ref:`api_paddle_nn_ClipGradByValue` ). Default None, meaning there is no gradient clipping.
         name (str, optional): The default value is None. Normally there is no need for user
                 to set this property. For more information, please refer to
                 :ref:`api_guide_Name` .