fix nce, multinomial, Categorical, Normal, Uniform en doc (#28541)

* fix Categorical en doc

* fix doc for apis

* remove numpy in sample code

python/paddle/distribution.py

@@ -197,11 +197,9 @@ class Uniform(Distribution):
     Examples:
         .. code-block:: python
 
-          import numpy as np
           import paddle
           from paddle.distribution import Uniform
 
-          paddle.disable_static()
           # Without broadcasting, a single uniform distribution [3, 4]:
           u1 = Uniform(low=3.0, high=4.0)
           # 2 distributions [1, 3], [2, 4]
@@ -214,8 +212,7 @@ class Uniform(Distribution):
           u4 = Uniform(low=3.0, high=[5.0, 6.0, 7.0])
 
           # Complete example
-          value_npdata = np.array([0.8], dtype="float32")
-          value_tensor = paddle.to_tensor(value_npdata)
+          value_tensor = paddle.to_tensor([0.8], dtype="float32")
 
           uniform = Uniform([0.], [2.])
 
@@ -419,11 +416,9 @@ class Normal(Distribution):
     Examples:
         .. code-block:: python
           
-          import numpy as np
           import paddle
           from paddle.distribution import Normal
 
-          paddle.disable_static()
           # Define a single scalar Normal distribution.
           dist = Normal(loc=0., scale=3.)
           # Define a batch of two scalar valued Normals.
@@ -437,8 +432,7 @@ class Normal(Distribution):
           dist = Normal(loc=1., scale=[11., 22.])
 
           # Complete example
-          value_npdata = np.array([0.8], dtype="float32")
-          value_tensor = paddle.to_tensor(value_npdata)
+          value_tensor = paddle.to_tensor([0.8], dtype="float32")
 
           normal_a = Normal([0.], [1.])
           normal_b = Normal([0.5], [2.])
@@ -672,13 +666,13 @@ class Categorical(Distribution):
 
             paddle.seed(100) # on CPU device
             x = paddle.rand([6])
-            print(x.numpy())
+            print(x)
             # [0.5535528  0.20714243 0.01162981
             #  0.51577556 0.36369765 0.2609165 ]
 
             paddle.seed(200) # on CPU device
             y = paddle.rand([6])
-            print(y.numpy())
+            print(y)
             # [0.77663314 0.90824795 0.15685187
             #  0.04279523 0.34468332 0.7955718 ]
 
@@ -746,7 +740,7 @@ class Categorical(Distribution):
 
                 paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
-                print(x.numpy())
+                print(x)
                 # [0.5535528  0.20714243 0.01162981
                 #  0.51577556 0.36369765 0.2609165 ]
 
@@ -793,13 +787,13 @@ class Categorical(Distribution):
 
                 paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
-                print(x.numpy())
+                print(x)
                 # [0.5535528  0.20714243 0.01162981
                 #  0.51577556 0.36369765 0.2609165 ]
 
                 paddle.seed(200) # on CPU device
                 y = paddle.rand([6])
-                print(y.numpy())
+                print(y)
                 # [0.77663314 0.90824795 0.15685187
                 #  0.04279523 0.34468332 0.7955718 ]
 
@@ -844,7 +838,7 @@ class Categorical(Distribution):
 
                 paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
-                print(x.numpy())
+                print(x)
                 # [0.5535528  0.20714243 0.01162981
                 #  0.51577556 0.36369765 0.2609165 ]
 
@@ -889,7 +883,7 @@ class Categorical(Distribution):
 
                 paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
-                print(x.numpy())
+                print(x)
                 # [0.5535528  0.20714243 0.01162981
                 #  0.51577556 0.36369765 0.2609165 ]
 
@@ -955,7 +949,7 @@ class Categorical(Distribution):
 
                 paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
-                print(x.numpy())
+                print(x)
                 # [0.5535528  0.20714243 0.01162981
                 #  0.51577556 0.36369765 0.2609165 ]
 

python/paddle/fluid/layers/loss.py

@@ -659,12 +659,12 @@ def nce(input,
     ${comment}
 
     Args:
-        input (Variable): Input variable, 2-D tensor with shape [batch_size, dim], 
+        input (Tensor): Input tensor, 2-D tensor with shape [batch_size, dim], 
             and data type is float32 or float64.
-        label (Variable): Input label, 2-D tensor with shape [batch_size, num_true_class],
+        label (Tensor): Input label, 2-D tensor with shape [batch_size, num_true_class],
             and data type is int64.
         num_total_classes (int):${num_total_classes_comment}.
-        sample_weight (Variable|None): A Variable of shape [batch_size, 1]
+        sample_weight (Tensor|None): A Tensor of shape [batch_size, 1]
             storing a weight for each sample. The default weight for each
             sample is 1.0.
         param_attr (ParamAttr|None): To specify the weight parameter attribute. 
@@ -688,19 +688,21 @@ def nce(input,
             the weight@GRAD and bias@GRAD will be changed to SelectedRows. Default False.
 
     Returns:
-        Variable: The output nce loss.
+        Tensor: The output nce loss.
 
     Examples:
         .. code-block:: python
 
 
-            import paddle.fluid as fluid
+            import paddle
             import numpy as np
 
+            paddle.enable_static()
+
             window_size = 5
             words = []
             for i in range(window_size):
-                words.append(fluid.data(
+                words.append(paddle.static.data(
                     name='word_{0}'.format(i), shape=[-1, 1], dtype='int64'))
 
             dict_size = 10000
@@ -711,18 +713,18 @@ def nce(input,
                 if i == label_word:
                     continue
 
-                emb = fluid.layers.embedding(input=words[i], size=[dict_size, 32],
+                emb = paddle.static.nn.embedding(input=words[i], size=[dict_size, 32],
                                     param_attr='embed', is_sparse=True)
                 embs.append(emb)
 
-            embs = fluid.layers.concat(input=embs, axis=1)
-            loss = fluid.layers.nce(input=embs, label=words[label_word],
+            embs = paddle.concat(x=embs, axis=1)
+            loss = paddle.static.nn.nce(input=embs, label=words[label_word],
                         num_total_classes=dict_size, param_attr='nce.w_0',
                         bias_attr='nce.b_0')
 
             #or use custom distribution
             dist = np.array([0.05,0.5,0.1,0.3,0.05])
-            loss = fluid.layers.nce(input=embs, label=words[label_word],
+            loss = paddle.static.nn.nce(input=embs, label=words[label_word],
                     num_total_classes=5, param_attr='nce.w_1',
                     bias_attr='nce.b_1',
                     num_neg_samples=3,

python/paddle/tensor/random.py

@@ -113,13 +113,13 @@ def multinomial(x, num_samples=1, replacement=False, name=None):
 
             paddle.seed(100) # on CPU device
             x = paddle.rand([2,4])
-            print(x.numpy())
+            print(x)
             # [[0.5535528  0.20714243 0.01162981 0.51577556]
             # [0.36369765 0.2609165  0.18905126 0.5621971 ]]
 
             paddle.seed(200) # on CPU device
             out1 = paddle.multinomial(x, num_samples=5, replacement=True)
-            print(out1.numpy())
+            print(out1)
             # [[3 3 0 0 0]
             # [3 3 3 1 0]]
 
@@ -129,7 +129,7 @@ def multinomial(x, num_samples=1, replacement=False, name=None):
 
             paddle.seed(300) # on CPU device
             out3 = paddle.multinomial(x, num_samples=3)
-            print(out3.numpy())
+            print(out3)
             # [[3 0 1]
             # [3 1 0]]