English API Docs Optimization Part 1 (#24536)

* test=develop, test=document_fix

* test=develop, test=document_fix

Co-authored-by: swtkiwi <1208425345@qq.com>

python/paddle/fluid/backward.py

@@ -1196,6 +1196,8 @@ def append_backward(loss,
                     callbacks=None,
                     checkpoints=None):
     """
+    :api_attr: Static Graph
+
     This function appends backward part to main_program.
 
     A complete neural network training is made up of forward and backward
@@ -1724,6 +1726,8 @@ def calc_gradient(targets, inputs, target_gradients=None, no_grad_set=None):
 
 def gradients(targets, inputs, target_gradients=None, no_grad_set=None):
     """
+    :api_attr: Static Graph
+    
     Backpropagate the gradients of targets to inputs.
 
     Args:

python/paddle/fluid/clip.py

@@ -158,6 +158,10 @@ class GradientClipBase(object):
 
 class GradientClipByValue(GradientClipBase):
     """
+    :alias_main: paddle.nn.GradientClipByValue
+	:alias: paddle.nn.GradientClipByValue,paddle.nn.clip.GradientClipByValue
+	:old_api: paddle.fluid.clip.GradientClipByValue
+
     Limit the value of multi-dimensional Tensor :math:`X` to the range [min, max].
     
     - Any values less than min are set to ``min``.
@@ -296,6 +300,10 @@ class GradientClipByValue(GradientClipBase):
 
 class GradientClipByNorm(GradientClipBase):
     """
+    :alias_main: paddle.nn.GradientClipByNorm
+	:alias: paddle.nn.GradientClipByNorm,paddle.nn.clip.GradientClipByNorm
+	:old_api: paddle.fluid.clip.GradientClipByNorm
+
     Limit the l2 norm of multi-dimensional Tensor :math:`X` to ``clip_norm`` .
     
     - If the l2 norm of :math:`X` is greater than ``clip_norm`` , :math:`X` will be compressed by a ratio.
@@ -447,6 +455,10 @@ class GradientClipByNorm(GradientClipBase):
 
 class GradientClipByGlobalNorm(GradientClipBase):
     """
+    :alias_main: paddle.nn.GradientClipByGlobalNorm
+	:alias: paddle.nn.GradientClipByGlobalNorm,paddle.nn.clip.GradientClipByGlobalNorm
+	:old_api: paddle.fluid.clip.GradientClipByGlobalNorm
+
     Given a list of Tensor :math:`t\_list` , calculate the global norm for the elements of all tensors in 
     :math:`t\_list` , and limit it to ``clip_norm`` .
     
@@ -691,6 +703,8 @@ class GradientClipByGlobalNorm(GradientClipBase):
 @framework.dygraph_not_support
 def set_gradient_clip(clip, param_list=None, program=None):
     """
+    :api_attr: Static Graph
+    
     Warning:
     
         This API must be used after building network, and before ``minimize`` , 

python/paddle/fluid/compiler.py

@@ -86,6 +86,8 @@ def _has_optimizer_in_control_flow(program):
 
 class CompiledProgram(object):
     """
+    :api_attr: Static Graph
+    
     The CompiledProgram is used to transform a program or graph for
     various optimizations according to the configuration of build_strategy,
     for example, the operators' fusion in the computation graph, memory

python/paddle/fluid/data.py

@@ -24,6 +24,11 @@ __all__ = ['data']
 
 def data(name, shape, dtype='float32', lod_level=0):
     """
+    :api_attr: Static Graph
+	:alias_main: paddle.nn.data
+	:alias: paddle.nn.data,paddle.nn.input.data
+	:old_api: paddle.fluid.data
+
     **Data Layer**
 
     This function creates a variable on the global block. The global variable

python/paddle/fluid/data_feed_desc.py

@@ -20,6 +20,8 @@ __all__ = ['DataFeedDesc']
 
 class DataFeedDesc(object):
     """
+    :api_attr: Static Graph
+    
     Datafeed descriptor, describing input training data format. This class is
     currently only used for AsyncExecutor (See comments for class AsyncExecutor
     for a brief introduction)

python/paddle/fluid/data_feeder.py

@@ -211,6 +211,8 @@ class BatchedTensorProvider(object):
 
 class DataFeeder(object):
     """
+    :api_attr: Static Graph
+    
     DataFeeder converts the data that returned by a reader into a data
     structure that can feed into Executor. The reader is usually a 
     python generator that returns a list of mini-batch data entries. 

python/paddle/fluid/dataset.py

@@ -728,6 +728,8 @@ class InMemoryDataset(DatasetBase):
 
     def release_memory(self):
         """
+        :api_attr: Static Graph
+        
         Release InMemoryDataset memory data, when data will not be used again.
 
         Examples:

python/paddle/fluid/dygraph/base.py

@@ -111,6 +111,10 @@ def enabled():
 
 def enable_dygraph(place=None):
     """
+    :alias_main: paddle.enable_dygraph
+	:alias: paddle.enable_dygraph,paddle.enable_imperative.enable_dygraph
+	:old_api: paddle.fluid.dygraph.base.enable_dygraph
+
     This function enables dynamic graph mode.
 
     Parameters:
@@ -141,6 +145,10 @@ def enable_dygraph(place=None):
 
 def disable_dygraph():
     """
+    :alias_main: paddle.disable_dygraph
+	:alias: paddle.disable_dygraph,paddle.disable_imperative.disable_dygraph
+	:old_api: paddle.fluid.dygraph.base.disable_dygraph
+
     This function disables dynamic graph mode.
 
     return:
@@ -178,6 +186,8 @@ def _switch_tracer_mode_guard_(is_train=True):
 
 def no_grad(func=None):
     """
+    :api_attr: imperative
+
     Create a context which disables dygraph gradient calculation.
     In this mode, the result of every computation will have `stop_gradient=True`.
 
@@ -236,6 +246,8 @@ def no_grad(func=None):
 @signature_safe_contextmanager
 def guard(place=None):
     """
+    :api_attr: imperative
+
     This context will create a dygraph context for dygraph to run, using python ``with`` statement.
 
     Parameters:
@@ -520,6 +532,8 @@ def grad(outputs,
 @framework.dygraph_only
 def to_variable(value, name=None, zero_copy=None):
     """
+    :api_attr: imperative
+
     The API will create a ``Variable`` or ``ComplexVariable`` object from 
     numpy\.ndarray, Variable or ComplexVariable object.
 

python/paddle/fluid/dygraph/checkpoint.py

@@ -32,6 +32,8 @@ __all__ = [
 @dygraph_only
 def save_dygraph(state_dict, model_path):
     '''
+    :api_attr: imperative
+
     Save Layer's state_dict to disk. This will generate a file with suffix ".pdparams"
     
     The state_dict is get from Layers.state_dict function
@@ -95,6 +97,8 @@ def save_dygraph(state_dict, model_path):
 @dygraph_only
 def load_dygraph(model_path, keep_name_table=False):
     '''
+    :api_attr: imperative
+    
     Load parameter state_dict from disk.
 
     Args:

python/paddle/fluid/dygraph/jit.py

@@ -203,6 +203,8 @@ def _trace(layer,
 
 class TracedLayer(object):
     """
+    :api_attr: imperative
+    
     TracedLayer is used to convert a forward dygraph model to a static
     graph model. This is mainly used to save the dygraph model for online
     inference using C++. Besides, users can also do inference in Python

python/paddle/fluid/dygraph/layers.py

@@ -58,7 +58,12 @@ class HookRemoveHelper(object):
 
 
 class Layer(core.Layer):
-    """Dynamic graph Layer based on OOD, includes the parameters of the layer, the structure of the forward graph and so on.
+    """
+    :alias_main: paddle.nn.Layer
+	:alias: paddle.nn.Layer
+	:old_api: paddle.fluid.dygraph.layers.Layer
+
+    Dynamic graph Layer based on OOD, includes the parameters of the layer, the structure of the forward graph and so on.
 
     Parameters:
         name_scope (str, optional): prefix name used by the layer to name parameters.

python/paddle/fluid/dygraph/learning_rate_scheduler.py

@@ -69,6 +69,8 @@ class LearningRateDecay(object):
 
 class PiecewiseDecay(LearningRateDecay):
     """
+    :api_attr: imperative
+    
     Piecewise decay scheduler.
 
     The algorithm can be described as the code below.
@@ -128,6 +130,8 @@ class PiecewiseDecay(LearningRateDecay):
 
 class NaturalExpDecay(LearningRateDecay):
     """
+    :api_attr: imperative
+
     Applies natural exponential decay to the initial learning rate.
     
     The algorithm can be described as following.
@@ -207,6 +211,8 @@ class NaturalExpDecay(LearningRateDecay):
 
 class ExponentialDecay(LearningRateDecay):
     """
+    :api_attr: imperative
+
     Applies exponential decay to the learning rate.
 
     The algorithm can be described as following.
@@ -287,6 +293,8 @@ class ExponentialDecay(LearningRateDecay):
 
 class InverseTimeDecay(LearningRateDecay):
     """
+    :api_attr: imperative
+
     Applies inverse time decay to the initial learning rate.
 
     The algorithm can be described as following.
@@ -363,6 +371,8 @@ class InverseTimeDecay(LearningRateDecay):
 
 class PolynomialDecay(LearningRateDecay):
     """
+    :api_attr: imperative
+
     Applies polynomial decay to the initial learning rate.
 
     The algorithm can be described as following.
@@ -455,6 +465,8 @@ class PolynomialDecay(LearningRateDecay):
 
 class CosineDecay(LearningRateDecay):
     """
+    :api_attr: imperative
+
     Applies cosine decay to the learning rate.
 
     The algorithm can be described as following.
@@ -511,6 +523,8 @@ class CosineDecay(LearningRateDecay):
 
 class NoamDecay(LearningRateDecay):
     """
+    :api_attr: imperative
+
     Applies Noam decay to the initial learning rate. 
 
     The algorithm can be described as following.

python/paddle/fluid/dygraph/nn.py

@@ -696,6 +696,10 @@ class Conv3DTranspose(layers.Layer):
 
 class Pool2D(layers.Layer):
     """
+    :alias_main: paddle.nn.Pool2D
+	:alias: paddle.nn.Pool2D,paddle.nn.layer.Pool2D,paddle.nn.layer.common.Pool2D
+	:old_api: paddle.fluid.dygraph.Pool2D
+
     This interface is used to construct a callable object of the ``Pool2D`` class.
     For more details, refer to code examples.
     The pooling2d operation calculates the output based on the input, pool_type and pool_size, pool_stride,
@@ -867,6 +871,10 @@ class Pool2D(layers.Layer):
 
 class Linear(layers.Layer):
     """
+    :alias_main: paddle.nn.Linear
+	:alias: paddle.nn.Linear,paddle.nn.layer.Linear,paddle.nn.layer.common.Linear
+	:old_api: paddle.fluid.dygraph.Linear
+    
     Fully-connected linear transformation layer:
 
     .. math::
@@ -1100,6 +1108,10 @@ class InstanceNorm(layers.Layer):
 
 class BatchNorm(layers.Layer):
     """
+    :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.
     It implements the function of the Batch Normalization Layer and can be used 
@@ -1443,6 +1455,10 @@ class Dropout(layers.Layer):
 
 class Embedding(layers.Layer):
     """
+    :alias_main: paddle.nn.Embedding
+	:alias: paddle.nn.Embedding,paddle.nn.layer.Embedding,paddle.nn.layer.common.Embedding
+	:old_api: paddle.fluid.dygraph.Embedding
+
     **Embedding Layer**
 
     This interface is used to construct a callable object of the ``Embedding`` class.
@@ -1599,6 +1615,10 @@ class Embedding(layers.Layer):
 
 class LayerNorm(layers.Layer):
     """
+    :alias_main: paddle.nn.LayerNorm
+	:alias: paddle.nn.LayerNorm,paddle.nn.layer.LayerNorm,paddle.nn.layer.norm.LayerNorm
+	:old_api: paddle.fluid.dygraph.LayerNorm
+
     This interface is used to construct a callable object of the ``LayerNorm`` class.
     For more details, refer to code examples.
     It implements the function of the Layer Normalization Layer and can be applied to mini-batch input data.
@@ -2289,6 +2309,10 @@ class PRelu(layers.Layer):
 
 class BilinearTensorProduct(layers.Layer):
     """
+    :alias_main: paddle.nn.BilinearTensorProduct
+	:alias: paddle.nn.BilinearTensorProduct,paddle.nn.layer.BilinearTensorProduct,paddle.nn.layer.common.BilinearTensorProduct
+	:old_api: paddle.fluid.dygraph.BilinearTensorProduct
+
     **Add Bilinear Tensor Product Layer**
 
     This layer performs bilinear tensor product on two inputs.
@@ -2809,6 +2833,10 @@ class RowConv(layers.Layer):
 
 class GroupNorm(layers.Layer):
     """
+    :alias_main: paddle.nn.GroupNorm
+	:alias: paddle.nn.GroupNorm,paddle.nn.layer.GroupNorm,paddle.nn.layer.norm.GroupNorm
+	:old_api: paddle.fluid.dygraph.GroupNorm
+
     This interface is used to construct a callable object of the ``GroupNorm`` class.
     For more details, refer to code examples.
     It implements the function of the Group Normalization Layer.
@@ -2909,6 +2937,10 @@ class GroupNorm(layers.Layer):
 
 class SpectralNorm(layers.Layer):
     """
+    :alias_main: paddle.nn.SpectralNorm
+	:alias: paddle.nn.SpectralNorm,paddle.nn.layer.SpectralNorm,paddle.nn.layer.norm.SpectralNorm
+	:old_api: paddle.fluid.dygraph.SpectralNorm
+
     This interface is used to construct a callable object of the ``SpectralNorm`` class.
     For more details, refer to code examples. It implements the function of the Spectral Normalization Layer.
     This layer calculates the spectral normalization value of weight parameters of

python/paddle/fluid/dygraph/parallel.py

@@ -28,6 +28,9 @@ ParallelStrategy = core.ParallelStrategy
 
 
 def prepare_context(strategy=None):
+    '''
+    :api_attr: imperative
+    '''
     if strategy is None:
         strategy = ParallelStrategy()
         strategy.nranks = Env().nranks

python/paddle/fluid/dygraph/tracer.py

@@ -23,6 +23,8 @@ from paddle.fluid import framework
 
 class Tracer(core.Tracer):
     """
+    :api_attr: imperative
+    
     Tracer is used to execute and record the operators executed, to construct the 
     computation graph in dygraph model. Tracer has two mode, :code:`train_mode`
     and :code:`eval_mode`. In :code:`train_mode`, Tracer would add backward network 

python/paddle/fluid/executor.py

@@ -40,6 +40,8 @@ InferAnalysisConfig = core.AnalysisConfig
 
 def global_scope():
     """
+    :api_attr: Static Graph
+
     Get the global/default scope instance. There are a lot of APIs use
     :code:`global_scope` as its default value, e.g., :code:`Executor.run`
 
@@ -68,6 +70,8 @@ def _switch_scope(scope):
 @signature_safe_contextmanager
 def scope_guard(scope):
     """
+    :api_attr: Static Graph
+    
     This function switches scope through python `with` statement.
     Scope records the mapping between variable names and variables ( :ref:`api_guide_Variable` ),
     similar to brackets in programming languages.
@@ -456,6 +460,8 @@ handler = FetchHandlerExample(var_dict=var_dict)
 
 class Executor(object):
     """
+    :api_attr: Static Graph
+
     An Executor in Python, supports single/multiple-GPU running,
     and single/multiple-CPU running.
 

python/paddle/fluid/framework.py

@@ -179,6 +179,10 @@ def require_version(min_version, max_version=None):
 
 def in_dygraph_mode():
     """
+    :alias_main: paddle.in_dygraph_mode
+	:alias: paddle.in_dygraph_mode
+	:old_api: paddle.fluid.framework.in_dygraph_mode
+
     This function checks whether the program runs in dynamic graph mode or not.
     You can enter dynamic graph mode with :ref:`api_fluid_dygraph_guard` api,
     or enable and disable dynamic graph mode with :ref:`api_fluid_dygraph_enable`
@@ -436,6 +440,8 @@ _name_scope = NameScope()
 @signature_safe_contextmanager
 def name_scope(prefix=None):
     """
+    :api_attr: Static Graph
+
     Generate hierarchical name prefix for the operators.
 
     Note: 
@@ -5277,6 +5283,8 @@ def switch_startup_program(program):
 @signature_safe_contextmanager
 def program_guard(main_program, startup_program=None):
     """
+    :api_attr: Static Graph
+
     Change the global main program and startup program with `"with"` statement.
     Layer functions in the Python `"with"` block will append operators and
     variables to the new main programs.
@@ -5376,6 +5384,8 @@ def _dygraph_place_guard(place):
 
 def load_op_library(lib_filename):
     """
+    :api_attr: Static Graph
+    
     Load a dynamic library, including custom operators and kernels.
     When library is loaded, ops and kernels registered in the library
     will be available in PaddlePaddle main process.

python/paddle/fluid/input.py

@@ -23,6 +23,9 @@ __all__ = ['one_hot', 'embedding']
 
 def one_hot(input, depth, allow_out_of_range=False):
     """
+    :alias_main: paddle.nn.functional.one_hot
+	:alias: paddle.nn.functional.one_hot,paddle.nn.functional.common.one_hot
+	:old_api: paddle.fluid.one_hot
 
     The operator converts each id in the input to an one-hot vector with a
     depth length. The value in the vector dimension corresponding to the id
@@ -132,6 +135,7 @@ def embedding(input,
               param_attr=None,
               dtype='float32'):
     """
+    :api_attr: Static Graph
 
     The operator is used to lookup embeddings vector of ids provided by :attr:`input` . 
     It automatically constructs a 2D embedding matrix based on the

python/paddle/fluid/io.py

@@ -124,6 +124,8 @@ def is_belong_to_optimizer(var):
 @dygraph_not_support
 def get_program_parameter(program):
     """
+    :api_attr: Static Graph
+
     Get all the parameters from Program.
 
     Args:
@@ -147,6 +149,8 @@ def get_program_parameter(program):
 @dygraph_not_support
 def get_program_persistable_vars(program):
     """
+    :api_attr: Static Graph
+
     Get all the persistable vars from Program.
 
     Args:
@@ -223,6 +227,8 @@ def save_vars(executor,
               predicate=None,
               filename=None):
     """
+    :api_attr: Static Graph
+
     This API saves specific variables in the `Program` to files.
 
     There are two ways to specify the variables to be saved: set variables in 
@@ -365,6 +371,8 @@ def save_vars(executor,
 @dygraph_not_support
 def save_params(executor, dirname, main_program=None, filename=None):
     """
+    :api_attr: Static Graph
+
     This operator saves all parameters from the :code:`main_program` to
     the folder :code:`dirname` or file :code:`filename`. You can refer to 
     :ref:`api_guide_model_save_reader_en` for more details.
@@ -588,6 +596,8 @@ def _save_distributed_persistables(executor, dirname, main_program):
 @dygraph_not_support
 def save_persistables(executor, dirname, main_program=None, filename=None):
     """
+    :api_attr: Static Graph
+
     This operator saves all persistable variables from :code:`main_program` to 
     the folder :code:`dirname` or file :code:`filename`. You can refer to 
     :ref:`api_guide_model_save_reader_en` for more details. And then
@@ -661,6 +671,8 @@ def load_vars(executor,
               predicate=None,
               filename=None):
     """
+    :api_attr: Static Graph
+
     This API loads variables from files by executor.
 
     There are two ways to specify the variables to be loaded: the first way, set
@@ -829,6 +841,8 @@ def load_vars(executor,
 @dygraph_not_support
 def load_params(executor, dirname, main_program=None, filename=None):
     """
+    :api_attr: Static Graph
+
     This API filters out all parameters from the give ``main_program``
     and then tries to load these parameters from the directory ``dirname`` or
     the file ``filename``.
@@ -887,6 +901,8 @@ def load_params(executor, dirname, main_program=None, filename=None):
 @dygraph_not_support
 def load_persistables(executor, dirname, main_program=None, filename=None):
     """
+    :api_attr: Static Graph
+    
     This API filters out all variables with ``persistable==True`` from the
     given ``main_program`` and then tries to load these variables from the
     directory ``dirname`` or the file ``filename``.
@@ -1084,6 +1100,8 @@ def save_inference_model(dirname,
                          export_for_deployment=True,
                          program_only=False):
     """
+    :api_attr: Static Graph
+
     Prune the given `main_program` to build a new program especially for inference,
     and then save it and all related parameters to given `dirname` .
     If you just want to save parameters of your trained model, please use the
@@ -1288,6 +1306,8 @@ def load_inference_model(dirname,
                          params_filename=None,
                          pserver_endpoints=None):
     """
+    :api_attr: Static Graph
+
     Load the inference model from a given directory. By this API, you can get the model
     structure(Inference Program) and model parameters. If you just want to load
     parameters of the pre-trained model, please use the :ref:`api_fluid_io_load_params` API.
@@ -1577,6 +1597,11 @@ def _load_persistable_nodes(executor, dirname, graph):
 @dygraph_not_support
 def save(program, model_path):
     """
+    :api_attr: Static Graph
+	:alias_main: paddle.save
+	:alias: paddle.save,paddle.tensor.save,paddle.tensor.io.save
+	:old_api: paddle.fluid.save
+
     This function save parameters, optimizer information and network description to  model_path.
 
     The parameters contains all the trainable Variable, will save to a file with suffix ".pdparams".
@@ -1636,6 +1661,11 @@ def save(program, model_path):
 @dygraph_not_support
 def load(program, model_path, executor=None, var_list=None):
     """
+    :api_attr: Static Graph
+	:alias_main: paddle.load
+	:alias: paddle.load,paddle.tensor.load,paddle.tensor.io.load
+	:old_api: paddle.fluid.io.load
+
     This function get parameters and optimizer information from program, and then get corresponding value from file.
     An exception will throw if shape or dtype of the parameters is not match.
 
@@ -1803,6 +1833,8 @@ def load(program, model_path, executor=None, var_list=None):
 @dygraph_not_support
 def load_program_state(model_path, var_list=None):
     """
+    :api_attr: Static Graph
+
     Load program state from local file
     
     Args:
@@ -1934,6 +1966,8 @@ def load_program_state(model_path, var_list=None):
 @dygraph_not_support
 def set_program_state(program, state_dict):
     """
+    :api_attr: Static Graph
+
     Set program parameter from state_dict
 
     An exception will throw if shape or dtype of the parameters is not match. 

python/paddle/fluid/layers/control_flow.py

@@ -222,6 +222,8 @@ def Print(input,
           print_tensor_lod=True,
           print_phase='both'):
     '''
+    :api_attr: Static Graph
+
     **Print operator**
 
     This creates a print op that will print when a tensor is accessed.
@@ -446,6 +448,8 @@ class StaticRNNMemoryLink(object):
 
 class StaticRNN(object):
     """
+    :api_attr: Static Graph
+
     StaticRNN class.
 
     The StaticRNN can process a batch of sequence data. The first dimension of inputs
@@ -923,6 +927,8 @@ class WhileGuard(BlockGuard):
 
 class While(object):
     """
+    :api_attr: Static Graph
+    
     while loop control flow. Repeat while body until cond is False.
 
     Note:
@@ -1061,6 +1067,11 @@ def assign_skip_lod_tensor_array(inputs, outputs):
 
 def while_loop(cond, body, loop_vars, is_test=False, name=None):
     """
+    :api_attr: Static Graph
+	:alias_main: paddle.nn.while_loop
+	:alias: paddle.nn.while_loop,paddle.nn.control_flow.while_loop
+	:old_api: paddle.fluid.layers.while_loop
+
     while_loop is one of the control flows. Repeats while_loop `body` until `cond` returns False.
 
     Notice:
@@ -1529,6 +1540,10 @@ def create_array(dtype):
 @templatedoc()
 def less_than(x, y, force_cpu=None, cond=None):
     """
+    :alias_main: paddle.less_than
+	:alias: paddle.less_than,paddle.tensor.less_than,paddle.tensor.logic.less_than
+	:old_api: paddle.fluid.layers.less_than
+
     ${comment}
 
     Args:
@@ -1594,6 +1609,10 @@ def less_than(x, y, force_cpu=None, cond=None):
 @templatedoc()
 def less_equal(x, y, cond=None):
     """
+    :alias_main: paddle.less_equal
+	:alias: paddle.less_equal,paddle.tensor.less_equal,paddle.tensor.logic.less_equal
+	:old_api: paddle.fluid.layers.less_equal
+
     This OP returns the truth value of :math:`x <= y` elementwise, which is equivalent function to the overloaded operator `<=`.
 
     Args:
@@ -1642,6 +1661,10 @@ def less_equal(x, y, cond=None):
 @templatedoc()
 def greater_than(x, y, cond=None):
     """
+    :alias_main: paddle.greater_than
+	:alias: paddle.greater_than,paddle.tensor.greater_than,paddle.tensor.logic.greater_than
+	:old_api: paddle.fluid.layers.greater_than
+
     This OP returns the truth value of :math:`x > y` elementwise, which is equivalent function to the overloaded operator `>`.
 
     Args:
@@ -1689,6 +1712,10 @@ def greater_than(x, y, cond=None):
 @templatedoc()
 def greater_equal(x, y, cond=None):
     """
+    :alias_main: paddle.greater_equal
+	:alias: paddle.greater_equal,paddle.tensor.greater_equal,paddle.tensor.logic.greater_equal
+	:old_api: paddle.fluid.layers.greater_equal
+
     This OP returns the truth value of :math:`x >= y` elementwise, which is equivalent function to the overloaded operator `>=`.
 
     Args:
@@ -1782,6 +1809,10 @@ def equal(x, y, cond=None):
 
 def not_equal(x, y, cond=None):
     """
+    :alias_main: paddle.not_equal
+	:alias: paddle.not_equal,paddle.tensor.not_equal,paddle.tensor.logic.not_equal
+	:old_api: paddle.fluid.layers.not_equal
+
     This OP returns the truth value of :math:`x != y` elementwise, which is equivalent function to the overloaded operator `!=`.
 
     Args:
@@ -2225,6 +2256,11 @@ def copy_var_to_parent_block(var, layer_helper):
 
 def cond(pred, true_fn=None, false_fn=None, name=None):
     """
+    :api_attr: Static Graph
+	:alias_main: paddle.nn.cond
+	:alias: paddle.nn.cond,paddle.nn.control_flow.cond
+	:old_api: paddle.fluid.layers.cond
+    
     This API returns ``true_fn()`` if the predicate ``pred`` is true else
     ``false_fn()`` . Users could also set ``true_fn`` or ``false_fn`` to
     ``None`` if do nothing and this API will treat the callable simply returns
@@ -2410,6 +2446,11 @@ def _error_message(what, arg_name, op_name, right_value, error_value):
 
 def case(pred_fn_pairs, default=None, name=None):
     '''
+    :api_attr: Static Graph
+	:alias_main: paddle.nn.case
+	:alias: paddle.nn.case,paddle.nn.control_flow.case
+	:old_api: paddle.fluid.layers.case
+
     This operator works like an if-elif-elif-else chain.
 
     Args:
@@ -2520,6 +2561,7 @@ def case(pred_fn_pairs, default=None, name=None):
 
 class Switch(object):
     """
+    :api_attr: Static Graph
 
     This class is used to implement Switch branch control function. 
     Switch branch contains several case branches and one default branch. 
@@ -2677,6 +2719,8 @@ class IfElseBlockGuard(object):
 
 class IfElse(object):
     """
+    :api_attr: Static Graph
+
     This class is used to implement IfElse branch control function. IfElse contains two blocks, true_block and false_block. IfElse will put data satisfying True or False conditions into different blocks to run.
 
     Cond is a 2-D Tensor with shape [N, 1] and data type bool, representing the execution conditions of the corresponding part of the input data.
@@ -2853,6 +2897,8 @@ class IfElse(object):
 
 class DynamicRNN(object):
     """
+    :api_attr: Static Graph
+
     **Note: the input of this class should be LoDTensor which holds the
     information of variable-length sequences. If the input is fixed-length Tensor,
     please use StaticRNN (fluid.layers.** :ref:`api_fluid_layers_StaticRNN` **) for
@@ -3518,6 +3564,8 @@ class DynamicRNN(object):
 
 def switch_case(branch_index, branch_fns, default=None, name=None):
     '''
+    :api_attr: Static Graph
+
     This operator is like a C++ switch/case statement.
 
     Args:
@@ -3701,6 +3749,10 @@ def reorder_lod_tensor_by_rank(x, rank_table):
 
 def is_empty(x, cond=None):
     """
+    :alias_main: paddle.is_empty
+	:alias: paddle.is_empty,paddle.tensor.is_empty,paddle.tensor.logic.is_empty
+	:old_api: paddle.fluid.layers.is_empty
+
     Test whether a Variable is empty.
 
     Args:

python/paddle/fluid/layers/loss.py

@@ -57,6 +57,11 @@ def center_loss(input,
                 param_attr,
                 update_center=True):
     """
+    :api_attr: Static Graph
+	:alias_main: paddle.nn.functional.center_loss
+	:alias: paddle.nn.functional.center_loss,paddle.nn.functional.loss.center_loss
+	:old_api: paddle.fluid.layers.center_loss
+
     **Center loss Cost layer**
     
     This OP accepts input (deep features,the output of the last hidden layer)
@@ -147,6 +152,10 @@ def center_loss(input,
 
 def bpr_loss(input, label, name=None):
     """
+    :alias_main: paddle.nn.functional.bpr_loss
+	:alias: paddle.nn.functional.bpr_loss,paddle.nn.functional.loss.bpr_loss
+	:old_api: paddle.fluid.layers.bpr_loss
+
     **Bayesian Personalized Ranking Loss Operator**
 
     This operator belongs to pairwise ranking loss. Label is the desired item.
@@ -195,6 +204,10 @@ def bpr_loss(input, label, name=None):
 
 def cross_entropy(input, label, soft_label=False, ignore_index=kIgnoreIndex):
     """
+    :alias_main: paddle.nn.functional.cross_entropy
+	:alias: paddle.nn.functional.cross_entropy,paddle.nn.functional.loss.cross_entropy
+	:old_api: paddle.fluid.layers.cross_entropy
+
     This operator computes the cross entropy between input and label. It
     supports both hard-label and and soft-label cross entropy computation.
 
@@ -288,6 +301,10 @@ def cross_entropy2(input, label, ignore_index=kIgnoreIndex):
 
 def square_error_cost(input, label):
     """
+    :alias_main: paddle.nn.functional.square_error_cost
+	:alias: paddle.nn.functional.square_error_cost,paddle.nn.functional.loss.square_error_cost
+	:old_api: paddle.fluid.layers.square_error_cost
+
     This op accepts input predictions and target label and returns the
     squared error cost.
 
@@ -663,6 +680,8 @@ def nce(input,
         seed=0,
         is_sparse=False):
     """
+    :api_attr: Static Graph
+
     ${comment}
 
     Args:
@@ -874,6 +893,8 @@ def hsigmoid(input,
              is_custom=False,
              is_sparse=False):
     """
+    :api_attr: Static Graph
+    
     The hierarchical sigmoid organizes the classes into a complete binary tree to reduce the computational complexity
     and speed up the model training, especially the training of language model.
     Each leaf node of the complete binary tree represents a class(word) and each non-leaf node acts as a binary classifier.
@@ -1167,6 +1188,10 @@ def softmax_with_cross_entropy(logits,
                                return_softmax=False,
                                axis=-1):
     """
+    :alias_main: paddle.nn.functional.softmax_with_cross_entropy
+	:alias: paddle.nn.functional.softmax_with_cross_entropy,paddle.nn.functional.loss.softmax_with_cross_entropy
+	:old_api: paddle.fluid.layers.softmax_with_cross_entropy
+
     This operator implements the cross entropy loss function with softmax. This function 
     combines the calculation of the softmax operation and the cross entropy loss function 
     to provide a more numerically stable gradient.
@@ -1290,6 +1315,10 @@ def softmax_with_cross_entropy(logits,
 
 def rank_loss(label, left, right, name=None):
     """
+    :alias_main: paddle.nn.functional.rank_loss
+	:alias: paddle.nn.functional.rank_loss,paddle.nn.functional.loss.rank_loss
+	:old_api: paddle.fluid.layers.rank_loss
+
     This operator implements the sort loss layer in the RankNet model. RankNet is a pairwise ranking model 
     with a training sample consisting of a pair of documents (A and B), The label (P) 
     indicates whether A is ranked higher than B or not. Please refer to more details: 
@@ -1407,6 +1436,10 @@ def sigmoid_cross_entropy_with_logits(x,
                                       name=None,
                                       normalize=False):
     """
+    :alias_main: paddle.nn.functional.sigmoid_cross_entropy_with_logits
+	:alias: paddle.nn.functional.sigmoid_cross_entropy_with_logits,paddle.nn.functional.loss.sigmoid_cross_entropy_with_logits
+	:old_api: paddle.fluid.layers.sigmoid_cross_entropy_with_logits
+
     ${comment}
 
     Args:
@@ -1464,6 +1497,10 @@ def teacher_student_sigmoid_loss(input,
                                  soft_max_up_bound=15.0,
                                  soft_max_lower_bound=-15.0):
     """
+    :alias_main: paddle.nn.functional.teacher_student_sigmoid_loss
+	:alias: paddle.nn.functional.teacher_student_sigmoid_loss,paddle.nn.functional.loss.teacher_student_sigmoid_loss
+	:old_api: paddle.fluid.layers.teacher_student_sigmoid_loss
+
     **Teacher Student Log Loss Layer**
 
     This layer accepts input predictions and target label and returns the
@@ -1583,6 +1620,10 @@ def huber_loss(input, label, delta):
 @templatedoc()
 def kldiv_loss(x, target, reduction='mean', name=None):
     """
+    :alias_main: paddle.nn.functional.kldiv_loss
+	:alias: paddle.nn.functional.kldiv_loss,paddle.nn.functional.loss.kldiv_loss
+	:old_api: paddle.fluid.layers.kldiv_loss
+
     ${comment}
 
     Args:
@@ -1643,6 +1684,10 @@ from .control_flow import equal
 
 def npair_loss(anchor, positive, labels, l2_reg=0.002):
     '''
+    :alias_main: paddle.nn.functional.npair_loss
+	:alias: paddle.nn.functional.npair_loss,paddle.nn.functional.loss.npair_loss
+	:old_api: paddle.fluid.layers.npair_loss
+
   **Npair Loss Layer**
 
   Read `Improved Deep Metric Learning with Multi class N pair Loss Objective\
@@ -1709,6 +1754,10 @@ def npair_loss(anchor, positive, labels, l2_reg=0.002):
 
 def mse_loss(input, label):
     """
+    :alias_main: paddle.nn.functional.mse_loss
+	:alias: paddle.nn.functional.mse_loss,paddle.nn.functional.loss.mse_loss
+	:old_api: paddle.fluid.layers.mse_loss
+
     This op accepts input predications and target label and returns the mean square error.
 
     The loss can be described as: