[cherry-pick] Fix 2.0 bugs (#29992)

* fix doc bugs test=document_fix

* fix code bugs test=document_fix

* fix code bugs test=document_fix

* fix doc bugs test=document_fix

* fix doc bugs test=document_fix

* fix doc bugs test=document_fix

python/paddle/nn/functional/loss.py

@@ -513,7 +513,7 @@ def smooth_l1_loss(input, label, reduction='mean', delta=1.0, name=None):
             label_data = np.random.rand(3,3).astype("float32")
             input = paddle.to_tensor(input_data)
             label = paddle.to_tensor(label_data)
-            output = paddle.nn.functioanl.smooth_l1_loss(input, label)
+            output = paddle.nn.functional.smooth_l1_loss(input, label)
             print(output)
     """
     fluid.data_feeder.check_variable_and_dtype(
@@ -1187,12 +1187,16 @@ def cross_entropy(input,
         .. code-block:: python
 
             import paddle
+            import numpy as np
+
             input_data = np.random.random([5, 100]).astype("float64")
             label_data = np.random.randint(0, 100, size=(5)).astype(np.int64)
             weight_data = np.random.random([100]).astype("float64")
+
             input =  paddle.to_tensor(input_data)
             label =  paddle.to_tensor(label_data)
             weight = paddle.to_tensor(weight_data)
+
             loss = paddle.nn.functional.cross_entropy(input=input, label=label, weight=weight)
             print(loss)
             # [4.28546723]

python/paddle/nn/functional/norm.py

@@ -271,9 +271,7 @@ def layer_norm(x,
           np.random.seed(123)
           x_data = np.random.random(size=(2, 2, 2, 3)).astype('float32')
           x = paddle.to_tensor(x_data) 
-          layer_norm = paddle.nn.functional.layer_norm(x, x.shape[1:])
-          layer_norm_out = layer_norm(x)
-
+          layer_norm_out = paddle.nn.functional.layer_norm(x, x.shape[1:])
           print(layer_norm_out)
     """
     input_shape = list(x.shape)
@@ -363,7 +361,7 @@ def instance_norm(x,
           np.random.seed(123)
           x_data = np.random.random(size=(2, 2, 2, 3)).astype('float32')
           x = paddle.to_tensor(x_data) 
-          instance_norm_out = paddle.nn.functional.instancenorm(x)
+          instance_norm_out = paddle.nn.functional.instance_norm(x)
 
           print(instance_norm_out)
 

python/paddle/nn/functional/pooling.py

@@ -198,11 +198,14 @@ def avg_pool1d(x,
 
     Examples:
         .. code-block:: python
-          import paddle
-          import paddle.nn.functional as F
-          data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
-          out = F.avg_pool1d(data, kernel_size=2, stride=2, padding=0)
-          # out shape: [1, 3, 16]
+          
+            import paddle
+            import paddle.nn.functional as F
+            import numpy as np
+
+            data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
+            out = F.avg_pool1d(data, kernel_size=2, stride=2, padding=0)
+            # out shape: [1, 3, 16]
     """
     """NCL to NCHW"""
     data_format = "NCHW"
@@ -302,23 +305,28 @@ def avg_pool2d(x,
         name(str, optional): For detailed information, please refer
                              to :ref:`api_guide_Name`. Usually name is no need to set and
                              None by default.
+    
     Returns:
         Tensor: The output tensor of pooling result. The data type is same as input tensor.
+    
     Raises:
         ValueError: If `padding` is a string, but not "SAME" or "VALID".
         ValueError: If `padding` is "VALID", but `ceil_mode` is True.
         ShapeError: If the output's shape calculated is not greater than 0.
+    
     Examples:
         .. code-block:: python
-          import paddle
-          import paddle.nn.functional as F
-          import numpy as np
-          # avg pool2d
-          x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32]).astype(np.float32))
-          out = F.avg_pool2d(x,
-                                kernel_size=2,
-                                stride=2, padding=0)
-          # out.shape [1, 3, 16, 16]
+          
+            import paddle
+            import paddle.nn.functional as F
+            import numpy as np
+            
+            # avg pool2d
+            x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32]).astype(np.float32))
+            out = F.avg_pool2d(x,
+                            kernel_size=2,
+                            stride=2, padding=0)
+            # out.shape [1, 3, 16, 16]
     """
     check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'avg_pool2d')
     kernel_size = utils.convert_to_list(kernel_size, 2, 'pool_size')
@@ -415,16 +423,21 @@ def avg_pool3d(x,
         name(str, optional): For detailed information, please refer
                              to :ref:`api_guide_Name`. Usually name is no need to set and
                              None by default.
+    
     Returns:
         Tensor: The output tensor of pooling result. The data type is same as input tensor.
+    
     Raises:
         ValueError: If `padding` is a string, but not "SAME" or "VALID".
         ValueError: If `padding` is "VALID", but `ceil_mode` is True.
         ShapeError: If the output's shape calculated is not greater than 0.
+    
     Examples:
         .. code-block:: python
-          import paddle.fluid as fluid
+          
           import paddle
+          import numpy as np
+
           x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32, 32]).astype(np.float32))
           # avg pool3d
           out = paddle.nn.functional.avg_pool3d(
@@ -537,6 +550,8 @@ def max_pool1d(x,
 
           import paddle
           import paddle.nn.functional as F
+          import numpy as np
+
           data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
           pool_out = F.max_pool1d(data, kernel_size=2, stride=2, padding=0)
           # pool_out shape: [1, 3, 16]
@@ -650,29 +665,32 @@ def max_pool2d(x,
                              None by default.
     Returns:
         Tensor: The output tensor of pooling result. The data type is same as input tensor.
-    Raises:
+   
+   Raises:
         ValueError: If `padding` is a string, but not "SAME" or "VALID".
         ValueError: If `padding` is "VALID", but `ceil_mode` is True.
         ShapeError: If the output's shape calculated is not greater than 0.
+    
     Examples:
         .. code-block:: python
 
-          import paddle
-          import paddle.nn.functional as F
-          import numpy as np
-          # max pool2d
-          x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32]).astype(np.float32))
-          out = F.max_pool2d(x,
-                                kernel_size=2,
-                                stride=2, padding=0)
-          # output.shape [1, 3, 16, 16]
-          # for return_mask=True
-          out, max_indices = F.max_pool2d(x,
-                                             kernel_size=2,
-                                             stride=2,
-                                             padding=0,
-                                             return_mask=True)
-          # out.shape [1, 3, 16, 16], max_indices.shape [1, 3, 16, 16],
+            import paddle
+            import paddle.nn.functional as F
+            import numpy as np
+            
+            # max pool2d
+            x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32]).astype(np.float32))
+            out = F.max_pool2d(x,
+                                  kernel_size=2,
+                                  stride=2, padding=0)
+            # output.shape [1, 3, 16, 16]
+            # for return_mask=True
+            out, max_indices = F.max_pool2d(x,
+                                               kernel_size=2,
+                                               stride=2,
+                                               padding=0,
+                                               return_mask=True)
+            # out.shape [1, 3, 16, 16], max_indices.shape [1, 3, 16, 16],
     """
     check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool2d')
     kernel_size = utils.convert_to_list(kernel_size, 2, 'pool_size')
@@ -778,33 +796,36 @@ def max_pool3d(x,
         name(str, optional): For detailed information, please refer
                              to :ref:`api_guide_Name`. Usually name is no need to set and
                              None by default.
+    
     Returns:
         Tensor: The output tensor of pooling result. The data type is same as input tensor.
+    
     Raises:
         ValueError: If `padding` is a string, but not "SAME" or "VALID".
         ValueError: If `padding` is "VALID", but `ceil_mode` is True.
         ShapeError: If the output's shape calculated is not greater than 0.
+    
     Examples:
         .. code-block:: python
 
-          import paddle
-          import paddle.nn.functional as F
-          import numpy as np
+            import paddle
+            import paddle.nn.functional as F
+            import numpy as np
 
-          # max pool3d
-          x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32, 32]).astype(np.float32))
-          output = F.max_pool2d(x,
-                                kernel_size=2,
-                                stride=2, padding=0)
-          output.shape [1, 3, 16, 16, 16]
-          # for return_mask=True
-          x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32, 32]).astype(np.float32))
-          output, max_indices = paddle.nn.functional.max_pool3d(x,
-                                        kernel_size = 2,
-                                        stride = 2,
-                                        padding=0,
-                                        return_mask=True)
-          # output.shape [None, 3, 16, 16, 16], max_indices.shape [None, 3, 16, 16, 16],
+            # max pool3d
+            x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32, 32]).astype(np.float32))
+            output = F.max_pool2d(x,
+                                  kernel_size=2,
+                                  stride=2, padding=0)
+            output.shape [1, 3, 16, 16, 16]
+            # for return_mask=True
+            x = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32, 32]).astype(np.float32))
+            output, max_indices = paddle.nn.functional.max_pool3d(x,
+                                          kernel_size = 2,
+                                          stride = 2,
+                                          padding=0,
+                                          return_mask=True)
+            # output.shape [None, 3, 16, 16, 16], max_indices.shape [None, 3, 16, 16, 16],
     """
     check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool3d')
     kernel_size = utils.convert_to_list(kernel_size, 3, 'pool_size')
@@ -905,6 +926,7 @@ def adaptive_avg_pool1d(x, output_size, name=None):
               #
               import paddle
               import paddle.nn.functional as F
+              import numpy as np
 
               data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
               pool_out = F.adaptive_average_pool1d(data, output_size=16)
@@ -1187,6 +1209,7 @@ def adaptive_max_pool1d(x, output_size, return_mask=False, name=None):
               #
               import paddle
               import paddle.nn.functional as F
+              import numpy as np
 
               data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
               pool_out = F.adaptive_max_pool1d(data, output_size=16)

python/paddle/nn/layer/activation.py

@@ -515,6 +515,7 @@ class LeakyReLU(layers.Layer):
         .. code-block:: python
 
             import paddle
+            import numpy as np
 
             m = paddle.nn.LeakyReLU()
             x = paddle.to_tensor(np.array([-2, 0, 1], 'float32'))

python/paddle/nn/layer/common.py

@@ -332,6 +332,7 @@ class Upsample(layers.Layer):
 
     Examples:
         .. code-block:: python
+            
             import paddle
             import paddle.nn as nn
             import numpy as np

python/paddle/nn/layer/loss.py

@@ -207,6 +207,7 @@ class CrossEntropyLoss(fluid.dygraph.Layer):
 
     Examples:
         .. code-block:: python
+            
             import paddle
             import numpy as np
 
@@ -491,28 +492,28 @@ class L1Loss(fluid.dygraph.Layer):
 
     Examples:
         .. code-block:: python
+            
             import paddle
             import numpy as np
 
-            paddle.disable_static()
             input_data = np.array([[1.5, 0.8], [0.2, 1.3]]).astype("float32")
             label_data = np.array([[1.7, 1], [0.4, 0.5]]).astype("float32")
             input = paddle.to_tensor(input_data)
             label = paddle.to_tensor(label_data)
 
-            l1_loss = paddle.nn.loss.L1Loss()
+            l1_loss = paddle.nn.L1Loss()
             output = l1_loss(input, label)
             print(output.numpy())
             # [0.35]
 
-            l1_loss = paddle.nn.loss.L1Loss(reduction='sum')
+            l1_loss = paddle.nn.L1Loss(reduction='sum')
             output = l1_loss(input, label)
             print(output.numpy())
             # [1.4]
 
-            l1_loss = paddle.nn.loss.L1Loss(reduction='none')
+            l1_loss = paddle.nn.L1Loss(reduction='none')
             output = l1_loss(input, label)
-            print(output.numpy())
+            print(output)
             # [[0.20000005 0.19999999]
             # [0.2        0.79999995]]
     """
@@ -596,12 +597,11 @@ class BCELoss(fluid.dygraph.Layer):
             input_data = np.array([0.5, 0.6, 0.7]).astype("float32")
             label_data = np.array([1.0, 0.0, 1.0]).astype("float32")
 
-            paddle.disable_static()
             input = paddle.to_tensor(input_data)
             label = paddle.to_tensor(label_data)
-            bce_loss = paddle.nn.loss.BCELoss()
+            bce_loss = paddle.nn.BCELoss()
             output = bce_loss(input, label)
-            print(output.numpy())  # [0.65537095]
+            print(output)  # [0.65537095]
 
     """
 
@@ -850,8 +850,8 @@ class MarginRankingLoss(fluid.dygraph.Layer):
 
             import paddle
 
-            input = paddle.to_tensor([[1, 2], [3, 4]]), dtype="float32")
-            other = paddle.to_tensor([[2, 1], [2, 4]]), dtype="float32")
+            input = paddle.to_tensor([[1, 2], [3, 4]], dtype="float32")
+            other = paddle.to_tensor([[2, 1], [2, 4]], dtype="float32")
             label = paddle.to_tensor([[1, -1], [-1, -1]], dtype="float32")
             margin_rank_loss = paddle.nn.MarginRankingLoss()
             loss = margin_rank_loss(input, other, label)

python/paddle/nn/layer/pooling.py

@@ -90,6 +90,7 @@ class AvgPool1D(layers.Layer):
 
           import paddle
           import paddle.nn as nn
+          import numpy as np
 
           data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
           AvgPool1D = nn.AvgPool1D(kernel_size=2, stride=2, padding=0)
@@ -185,7 +186,7 @@ class AvgPool2D(layers.Layer):
           input = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32, 32]).astype(np.float32))
           AvgPool2D = nn.AvgPool2D(kernel_size=2,
                                 stride=2, padding=0)
-          output = AvgPoo2d(input)
+          output = AvgPool2D(input)
           # output.shape [1, 3, 16, 16]
 
     """
@@ -367,6 +368,7 @@ class MaxPool1D(layers.Layer):
 
           import paddle
           import paddle.nn as nn
+          import numpy as np
 
           data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
           MaxPool1D = nn.MaxPool1D(kernel_size=2, stride=2, padding=0)
@@ -646,6 +648,7 @@ class AdaptiveAvgPool1D(layers.Layer):
           #
           import paddle
           import paddle.nn as nn
+          import numpy as np
 
           data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
           AdaptiveAvgPool1D = nn.AdaptiveAvgPool1D(output_size=16)
@@ -884,8 +887,9 @@ class AdaptiveMaxPool1D(layers.Layer):
           #         lend = ceil((i + 1) * L / m)
           #         output[:, :, i] = max(input[:, :, lstart: lend])
           #
-                    import paddle
+          import paddle
           import paddle.nn as nn
+          import numpy as np
 
           data = paddle.to_tensor(np.random.uniform(-1, 1, [1, 3, 32]).astype(np.float32))
           AdaptiveMaxPool1D = nn.AdaptiveMaxPool1D(output_size=16)

python/paddle/nn/layer/transformer.py

@@ -120,7 +120,7 @@ class MultiHeadAttention(Layer):
             query = paddle.rand((2, 4, 128))
             # self attention mask: [batch_size, num_heads, query_len, query_len]
             attn_mask = paddle.rand((2, 2, 4, 4))
-            multi_head_attn = paddle.MultiHeadAttention(128, 2)
+            multi_head_attn = paddle.nn.MultiHeadAttention(128, 2)
             output = multi_head_attn(query, None, None, attn_mask=attn_mask)  # [2, 4, 128]
     """
 

python/paddle/nn/utils/weight_norm_hook.py

@@ -212,6 +212,7 @@ def remove_weight_norm(layer, name='weight'):
 
     Examples:
         .. code-block:: python
+          
           import paddle
           from paddle.nn import Conv2D
           from paddle.nn.utils import weight_norm, remove_weight_norm

python/paddle/optimizer/adamax.py

@@ -78,10 +78,10 @@ class Adamax(Optimizer):
 
     Examples:
         .. code-block:: python
+            
             import paddle
             import numpy as np
 
-            paddle.disable_static()
             inp = np.random.uniform(-0.1, 0.1, [10, 10]).astype("float32")
             linear = paddle.nn.Linear(10, 10)
             inp = paddle.to_tensor(inp)

python/paddle/optimizer/adamw.py

@@ -79,6 +79,7 @@ class AdamW(Adam):
 
     Examples:
         .. code-block:: python
+            
             import paddle
 
             linear = paddle.nn.Linear(10, 10)

python/paddle/optimizer/lamb.py

@@ -65,6 +65,7 @@ class Lamb(Optimizer):
             :ref:`api_guide_Name` . Usually name is no need to set and None by default.
     Examples:
         .. code-block:: python
+            
             import paddle
             import numpy as np
             inp = paddle.uniform(min=-0.1, max=0.1, shape=[10, 10], dtype='float32')

python/paddle/static/__init__.py

@@ -26,6 +26,12 @@ __all__ = [
 from . import nn
 from .io import save_inference_model  #DEFINE_ALIAS
 from .io import load_inference_model  #DEFINE_ALIAS
+from .io import deserialize_persistables  #DEFINE_ALIAS
+from .io import serialize_persistables  #DEFINE_ALIAS
+from .io import deserialize_program  #DEFINE_ALIAS
+from .io import serialize_program  #DEFINE_ALIAS
+from .io import load_from_file  #DEFINE_ALIAS
+from .io import save_to_file  #DEFINE_ALIAS
 from ..fluid import Scope  #DEFINE_ALIAS
 from .input import data  #DEFINE_ALIAS
 from .input import InputSpec  #DEFINE_ALIAS

python/paddle/static/io.py

@@ -213,8 +213,7 @@ def serialize_program(feed_vars, fetch_vars, **kwargs):
     Args:
         feed_vars(Variable | list[Variable]): Variables needed by inference.
         fetch_vars(Variable | list[Variable]): Variables returned by inference.
-        kwargs: Supported keys including 'program'.
-                Attention please, kwargs is used for backward compatibility mainly.
+        kwargs: Supported keys including 'program'.Attention please, kwargs is used for backward compatibility mainly.
           - program(Program): specify a program if you don't want to use default main program.
 
     Returns:
@@ -277,8 +276,7 @@ def serialize_persistables(feed_vars, fetch_vars, executor, **kwargs):
     Args:
         feed_vars(Variable | list[Variable]): Variables needed by inference.
         fetch_vars(Variable | list[Variable]): Variables returned by inference.
-        kwargs: Supported keys including 'program'.
-                Attention please, kwargs is used for backward compatibility mainly.
+        kwargs: Supported keys including 'program'.Attention please, kwargs is used for backward compatibility mainly.
           - program(Program): specify a program if you don't want to use default main program.
 
     Returns:
@@ -403,8 +401,7 @@ def save_inference_model(path_prefix, feed_vars, fetch_vars, executor,
         fetch_vars(Variable | list[Variable]): Variables returned by inference.
         executor(Executor): The executor that saves the inference model. You can refer
                             to :ref:`api_guide_executor_en` for more details.
-        kwargs: Supported keys including 'program'.
-                Attention please, kwargs is used for backward compatibility mainly.
+        kwargs: Supported keys including 'program'.Attention please, kwargs is used for backward compatibility mainly.
           - program(Program): specify a program if you don't want to use default main program.
     Returns:
         None
@@ -645,8 +642,7 @@ def load_inference_model(path_prefix, executor, **kwargs):
           - Set to None when reading the model from memory.
         executor(Executor): The executor to run for loading inference model.
                             See :ref:`api_guide_executor_en` for more details about it.
-        kwargs: Supported keys including 'model_filename', 'params_filename'.
-                Attention please, kwargs is used for backward compatibility mainly.
+        kwargs: Supported keys including 'model_filename', 'params_filename'.Attention please, kwargs is used for backward compatibility mainly.
           - model_filename(str): specify model_filename if you don't want to use default name.
           - params_filename(str): specify params_filename if you don't want to use default name.
 

python/paddle/tensor/manipulation.py

@@ -284,6 +284,7 @@ def roll(x, shifts, axis=None, name=None):
 
     Examples:
         .. code-block:: python
+            
             import paddle
 
             x = paddle.to_tensor([[1.0, 2.0, 3.0],

python/paddle/tensor/math.py

@@ -174,7 +174,8 @@ def pow(x, y, name=None):
             print(res) # [1 4 9]
             
             # example 2: y is a Tensor
-            y = paddle.full(shape=[1], fill_value=2, dtype='float32')
+            y = paddle.full(shape=[1], fill_value=2, dtype='int64')
+        
             res = paddle.pow(x, y)
             print(res) # [1 4 9]