fix doc, use to_tensor

fix doc, use to_tensor for the loss ops

python/paddle/nn/functional/loss.py

@@ -147,7 +147,6 @@ def binary_cross_entropy(input, label, weight=None, reduction='mean',
             label = paddle.to_tensor(label_data)
             output = paddle.nn.functional.binary_cross_entropy(input, label)
             print(output.numpy())  # [0.65537095]
-            paddle.enable_static()
 
     """
     if reduction not in ['sum', 'mean', 'none']:
@@ -165,8 +164,7 @@ def binary_cross_entropy(input, label, weight=None, reduction='mean',
             return core.ops.reduce_sum(out, 'dim', [0], 'keep_dim', False,
                                        "reduce_all", True)
         elif reduction == 'mean':
-            return core.ops.reduce_mean(out, 'dim', [0], 'keep_dim', False,
-                                        "reduce_all", True)
+            return core.ops.mean(out)
         else:
             return out
 
@@ -467,14 +465,12 @@ def margin_ranking_loss(input,
 
         .. code-block:: python
 
-            import numpy as np
             import paddle
-
             paddle.disable_static()
 
-            input = paddle.to_variable(np.array([[1, 2], [3, 4]]).astype('float32'))
-            other = paddle.to_variable(np.array([[2, 1], [2, 4]]).astype('float32'))
-            label = paddle.to_variable(np.array([[1, -1], [-1, -1]]).astype('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')
             loss = paddle.nn.functional.margin_ranking_loss(input, other, label)
             print(loss.numpy()) # [0.75]
     """
@@ -578,8 +574,8 @@ def l1_loss(input, label, reduction='mean', name=None):
             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_variable(input_data)
-            label = paddle.to_variable(label_data)
+            input = paddle.to_tensor(input_data)
+            label = paddle.to_tensor(label_data)
 
             l1_loss = paddle.nn.functional.l1_loss(input, label)
             print(l1_loss.numpy())
@@ -675,9 +671,9 @@ def nll_loss(input,
 
                 place = paddle.CPUPlace()
                 paddle.disable_static(place)
-                input = paddle.to_variable(input_np)
+                input = paddle.to_tensor(input_np)
                 log_out = log_softmax(input)
-                label = paddle.to_variable(label_np)
+                label = paddle.to_tensor(label_np)
                 result = nll_loss(log_out, label)
                 print(result.numpy()) # [1.0720209]
     """

python/paddle/nn/layer/distance.py

@@ -44,10 +44,10 @@ class PairwiseDistance(layers.Layer):
             For more information, please refer to :ref:`api_guide_Name`.
 
     Shape:
-        x: :math:`(N, D)` where `D` is the dimension of vector, available dtype
+        x: :math:`[N, D]` where `D` is the dimension of vector, available dtype
             is float32, float64.
-        y: :math:`(N, D)`, y have the same shape and dtype as x.
-        out: :math:`(N)`. If :attr:`keepdim` is ``True``, the out shape is :math:`(N, 1)`.
+        y: :math:`[N, D]`, y have the same shape and dtype as x.
+        out: :math:`[N]`. If :attr:`keepdim` is ``True``, the out shape is :math:`[N, 1]`.
             The same dtype as input tensor.
 
     Examples:
@@ -58,8 +58,8 @@ class PairwiseDistance(layers.Layer):
             paddle.disable_static()
             x_np = np.array([[1., 3.], [3., 5.]]).astype(np.float64)
             y_np = np.array([[5., 6.], [7., 8.]]).astype(np.float64)
-            x = paddle.to_variable(x_np)
-            y = paddle.to_variable(y_np)
+            x = paddle.to_tensor(x_np)
+            y = paddle.to_tensor(y_np)
             dist = paddle.nn.PairwiseDistance()
             distance = dist(x, y)
             print(distance.numpy()) # [5. 5.]

python/paddle/nn/layer/loss.py

@@ -376,8 +376,8 @@ class L1Loss(fluid.dygraph.Layer):
             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_variable(input_data)
-            label = paddle.to_variable(label_data)
+            input = paddle.to_tensor(input_data)
+            label = paddle.to_tensor(label_data)
 
             l1_loss = paddle.nn.loss.L1Loss()
             output = l1_loss(input, label)
@@ -455,7 +455,7 @@ class BCELoss(fluid.dygraph.Layer):
             For more information, please refer to :ref:`api_guide_Name`.
 
     Shape:
-        input (Tensor): 2-D tensor with shape: (N, *), N is batch_size, `*` means
+        input (Tensor): 2-D tensor with shape: [N, *], N is batch_size, `*` means
             number of additional dimensions. The input ``input`` should always
             be the output of sigmod.  Available dtype is float32, float64.
         label (Tensor): 2-D tensor with the same shape as ``input``. The target
@@ -476,12 +476,11 @@ class BCELoss(fluid.dygraph.Layer):
             label_data = np.array([1.0, 0.0, 1.0]).astype("float32")
 
             paddle.disable_static()
-            input = paddle.to_variable(input_data)
-            label = paddle.to_variable(label_data)
+            input = paddle.to_tensor(input_data)
+            label = paddle.to_tensor(label_data)
             bce_loss = paddle.nn.loss.BCELoss()
             output = bce_loss(input, label)
             print(output.numpy())  # [0.65537095]
-            paddle.enable_static()
 
     """
 
@@ -584,9 +583,9 @@ class NLLLoss(fluid.dygraph.Layer):
 
                 place = paddle.CPUPlace()
                 paddle.disable_static(place)
-                input = paddle.to_variable(input_np)
+                input = paddle.to_tensor(input_np)
                 log_out = log_softmax(input)
-                label = paddle.to_variable(label_np)
+                label = paddle.to_tensor(label_np)
                 result = nll_loss(log_out, label)
                 print(result.numpy()) # [1.0720209]
 
@@ -729,14 +728,12 @@ class MarginRankingLoss(fluid.dygraph.Layer):
 
         .. code-block:: python
 
-            import numpy as np
             import paddle
-
             paddle.disable_static()
 
-            input = paddle.to_variable(np.array([[1, 2], [3, 4]]).astype("float32"))
-            other = paddle.to_variable(np.array([[2, 1], [2, 4]]).astype("float32"))
-            label = paddle.to_variable(np.array([[1, -1], [-1, -1]]).astype("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)
             print(loss.numpy()) # [0.75]