Merge pull request #11491 from kuke/fix_docs

Fix some problems in api reference

doc/fluid/api/gen_doc.sh

 #!/bin/bash
-python gen_doc.py layers --submodules control_flow device io nn ops tensor detection learning_rate_scheduler > layers.rst
+python gen_doc.py layers --submodules control_flow device io nn ops tensor detection learning_rate_scheduler metric > layers.rst
 
 for module in data_feeder clip metrics executor initializer io nets optimizer param_attr profiler regularizer
 do

doc/fluid/api/initializer.rst

@@ -33,6 +33,13 @@ Xavier
     :members:
     :noindex:
 
+Bilinear
+--------
+
+..  autoclass:: paddle.fluid.initializer.Bilinear
+    :members:
+    :noindex:
+
 force_init_on_cpu
 -----------------
 
@@ -73,3 +80,10 @@ XavierInitializer
     :members:
     :noindex:
 
+BilinearInitializer
+-------------------
+
+..  autoclass:: paddle.fluid.initializer.BilinearInitializer
+    :members:
+    :noindex:
+

doc/fluid/api/io.rst

@@ -59,3 +59,39 @@ get_inference_program
 ..  autofunction:: paddle.fluid.io.get_inference_program
     :noindex:
 
+save_checkpoint
+---------------
+
+..  autofunction:: paddle.fluid.io.save_checkpoint
+    :noindex:
+
+load_checkpoint
+---------------
+
+..  autofunction:: paddle.fluid.io.load_checkpoint
+    :noindex:
+
+clean_checkpoint
+----------------
+
+..  autofunction:: paddle.fluid.io.clean_checkpoint
+    :noindex:
+
+load_persist_vars_without_grad
+------------------------------
+
+..  autofunction:: paddle.fluid.io.load_persist_vars_without_grad
+    :noindex:
+
+save_persist_vars_without_grad
+------------------------------
+
+..  autofunction:: paddle.fluid.io.save_persist_vars_without_grad
+    :noindex:
+
+get_latest_checkpoint_serial
+----------------------------
+
+..  autofunction:: paddle.fluid.io.get_latest_checkpoint_serial
+    :noindex:
+

doc/fluid/api/layers.rst

@@ -181,6 +181,12 @@ Print
 ..  autofunction:: paddle.fluid.layers.Print
     :noindex:
 
+is_empty
+--------
+
+..  autofunction:: paddle.fluid.layers.is_empty
+    :noindex:
+
 device
 ======
 
@@ -219,6 +225,12 @@ Send
 ..  autofunction:: paddle.fluid.layers.Send
     :noindex:
 
+Recv
+----
+
+..  autofunction:: paddle.fluid.layers.Recv
+    :noindex:
+
 open_recordio_file
 ------------------
 
@@ -255,6 +267,25 @@ double_buffer
 ..  autofunction:: paddle.fluid.layers.double_buffer
     :noindex:
 
+random_data_generator
+---------------------
+
+..  autofunction:: paddle.fluid.layers.random_data_generator
+    :noindex:
+
+Preprocessor
+------------
+
+..  autoclass:: paddle.fluid.layers.Preprocessor
+    :members:
+    :noindex:
+
+load
+----
+
+..  autofunction:: paddle.fluid.layers.load
+    :noindex:
+
 nn
 ==
 
@@ -399,10 +430,9 @@ conv2d_transpose
 conv3d_transpose
 ----------------
 
-..  autofunction:: paddle.fluid.layers.conv2d_transpose
+..  autofunction:: paddle.fluid.layers.conv3d_transpose
     :noindex:
 
-
 sequence_expand
 ---------------
 
@@ -613,6 +643,48 @@ roi_pool
 ..  autofunction:: paddle.fluid.layers.roi_pool
     :noindex:
 
+dice_loss
+---------
+
+..  autofunction:: paddle.fluid.layers.dice_loss
+    :noindex:
+
+image_resize
+------------
+
+..  autofunction:: paddle.fluid.layers.image_resize
+    :noindex:
+
+image_resize_short
+------------------
+
+..  autofunction:: paddle.fluid.layers.image_resize_short
+    :noindex:
+
+resize_bilinear
+---------------
+
+..  autofunction:: paddle.fluid.layers.resize_bilinear
+    :noindex:
+
+gather
+------
+
+..  autofunction:: paddle.fluid.layers.gather
+    :noindex:
+
+random_crop
+-----------
+
+..  autofunction:: paddle.fluid.layers.random_crop
+    :noindex:
+
+mean_iou
+--------
+
+..  autofunction:: paddle.fluid.layers.mean_iou
+    :noindex:
+
 ops
 ===
 
@@ -718,12 +790,6 @@ logical_not
 ..  autofunction:: paddle.fluid.layers.logical_not
     :noindex:
 
-uniform_random
---------------
-
-..  autofunction:: paddle.fluid.layers.uniform_random
-    :noindex:
-
 uniform_random_batch_size_like
 ------------------------------
 
@@ -742,12 +808,6 @@ gaussian_random_batch_size_like
 ..  autofunction:: paddle.fluid.layers.gaussian_random_batch_size_like
     :noindex:
 
-cumsum
-------
-
-..  autofunction:: paddle.fluid.layers.cumsum
-    :noindex:
-
 scatter
 -------
 
@@ -760,6 +820,30 @@ sum
 ..  autofunction:: paddle.fluid.layers.sum
     :noindex:
 
+slice
+-----
+
+..  autofunction:: paddle.fluid.layers.slice
+    :noindex:
+
+polygon_box_transform
+---------------------
+
+..  autofunction:: paddle.fluid.layers.polygon_box_transform
+    :noindex:
+
+shape
+-----
+
+..  autofunction:: paddle.fluid.layers.shape
+    :noindex:
+
+maxout
+------
+
+..  autofunction:: paddle.fluid.layers.maxout
+    :noindex:
+
 sigmoid
 -------
 
@@ -916,18 +1000,6 @@ stanh
 ..  autofunction:: paddle.fluid.layers.stanh
     :noindex:
 
-hard_shrink
------------
-
-..  autofunction:: paddle.fluid.layers.hard_shrink
-    :noindex:
-
-thresholded_relu
-----------------
-
-..  autofunction:: paddle.fluid.layers.thresholded_relu
-    :noindex:
-
 hard_sigmoid
 ------------
 
@@ -940,6 +1012,30 @@ swish
 ..  autofunction:: paddle.fluid.layers.swish
     :noindex:
 
+uniform_random
+--------------
+
+..  autofunction:: paddle.fluid.layers.uniform_random
+    :noindex:
+
+hard_shrink
+-----------
+
+..  autofunction:: paddle.fluid.layers.hard_shrink
+    :noindex:
+
+cumsum
+------
+
+..  autofunction:: paddle.fluid.layers.cumsum
+    :noindex:
+
+thresholded_relu
+----------------
+
+..  autofunction:: paddle.fluid.layers.thresholded_relu
+    :noindex:
+
 tensor
 ======
 
@@ -997,6 +1093,18 @@ fill_constant
 ..  autofunction:: paddle.fluid.layers.fill_constant
     :noindex:
 
+argmin
+------
+
+..  autofunction:: paddle.fluid.layers.argmin
+    :noindex:
+
+argmax
+------
+
+..  autofunction:: paddle.fluid.layers.argmax
+    :noindex:
+
 ones
 ----
 
@@ -1012,6 +1120,12 @@ zeros
 detection
 =========
 
+prior_box
+---------
+
+..  autofunction:: paddle.fluid.layers.prior_box
+    :noindex:
+
 multi_box_head
 --------------
 
@@ -1099,3 +1213,18 @@ noam_decay
 ..  autofunction:: paddle.fluid.layers.noam_decay
     :noindex:
 
+metric
+======
+
+accuracy
+--------
+
+..  autofunction:: paddle.fluid.layers.accuracy
+    :noindex:
+
+auc
+---
+
+..  autofunction:: paddle.fluid.layers.auc
+    :noindex:
+

doc/fluid/api/optimizer.rst

@@ -89,6 +89,13 @@ DecayedAdagradOptimizer
     :members:
     :noindex:
 
+RMSPropOptimizer
+----------------
+
+..  autoclass:: paddle.fluid.optimizer.RMSPropOptimizer
+    :members:
+    :noindex:
+
 Adadelta
 --------
 

doc/fluid/api/profiler.rst

@@ -23,3 +23,15 @@ profiler
 ..  autofunction:: paddle.fluid.profiler.profiler
     :noindex:
 
+start_profiler
+--------------
+
+..  autofunction:: paddle.fluid.profiler.start_profiler
+    :noindex:
+
+stop_profiler
+-------------
+
+..  autofunction:: paddle.fluid.profiler.stop_profiler
+    :noindex:
+

paddle/fluid/operators/activation_op.cc

@@ -27,7 +27,7 @@ namespace operators {
       AddInput("X", "Input of " #OP_NAME " operator");                \
       AddOutput("Out", "Output of " #OP_NAME " operator").Reuse("X"); \
       AddAttr<bool>("use_mkldnn",                                     \
-                    "(bool, default false) Only used in mkldnn kernel") \
+                    "(default false) Only used in mkldnn kernel")     \
           .SetDefault(false);                                         \
       AddComment(OP_COMMENT);                                         \
     }                                                                 \
@@ -196,7 +196,7 @@ $out = [x]$
 __attribute__((unused)) constexpr char ReciprocalDoc[] = R"DOC(
 Reciprocal Activation Operator.
 
-$$out = \frac{1}{x}$$
+$$out = \\frac{1}{x}$$
 
 )DOC";
 

paddle/fluid/operators/nce_op.cc

@@ -128,8 +128,10 @@ class NCEOpMaker : public framework::OpProtoAndCheckerMaker {
                               "user should avoid setting this attribute.")
         .SetDefault({});
     AddComment(R"DOC(
-Compute and return the noise-contrastive estimation training loss.
-See [Noise-contrastive estimation: A new estimation principle for unnormalized statistical models](http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf).
+Compute and return the noise-contrastive estimation training loss. See 
+`Noise-contrastive estimation: A new estimation principle for unnormalized 
+statistical models 
+ <http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf>`_.
 By default this operator uses a uniform distribution for sampling.
 )DOC");
   }

python/paddle/fluid/layers/detection.py

@@ -97,7 +97,9 @@ def detection_output(loc,
         nms_eta(float): The parameter for adaptive NMS.
 
     Returns:
-        Variable: The detection outputs is a LoDTensor with shape [No, 6].
+        Variable: 
+        
+            The detection outputs is a LoDTensor with shape [No, 6].
             Each row has six values: [label, confidence, xmin, ymin, xmax, ymax].
             `No` is the total number of detections in this mini-batch. For each
             instance, the offsets in first dimension are called LoD, the offset
@@ -296,8 +298,6 @@ def target_assign(input,
                   mismatch_value=None,
                   name=None):
     """
-    **Target assigner operator**
-
     This operator can be, for given the target bounding boxes or labels,
     to assign classification and regression targets to each prediction as well as
     weights to prediction. The weights is used to specify which prediction would
@@ -311,6 +311,8 @@ def target_assign(input,
 
     1. Assigning all outpts based on `match_indices`:
 
+    .. code-block:: text
+
         If id = match_indices[i][j] > 0,
 
             out[i][j][0 : K] = X[lod[i] + id][j % P][0 : K]
@@ -326,6 +328,8 @@ def target_assign(input,
     Assumed that the row offset for each instance in `neg_indices` is called neg_lod,
     for i-th instance and each `id` of neg_indices in this instance:
     
+    .. code-block:: text
+
         out[i][id][0 : K] = {mismatch_value, mismatch_value, ...}
         out_weight[i][id] = 1.0
 
@@ -341,10 +345,23 @@ def target_assign(input,
        mismatch_value (float32): Fill this value to the mismatched location.
 
     Returns:
-       out (Variable): The output is a 3D Tensor with shape [N, P, K],
-           N and P is the same as they are in `neg_indices`, K is the
-           same as it in input of X. If `match_indices[i][j]`.
-       out_weight (Variable): The weight for output with the shape of [N, P, 1].
+        tuple: 
+        
+               A tuple(out, out_weight) is returned. out is a 3D Tensor with 
+               shape [N, P, K], N and P is the same as they are in 
+               `neg_indices`, K is the same as it in input of X. If 
+               `match_indices[i][j]`. out_weight is the weight for output with 
+               the shape of [N, P, 1].
+
+    Examples:
+
+        .. code-block:: python
+
+            matched_indices, matched_dist = fluid.layers.bipartite_match(iou)
+            gt = layers.data(
+                        name='gt', shape=[1, 1], dtype='int32', lod_level=1)
+            trg, trg_weight = layers.target_assign(
+                            gt, matched_indices, mismatch_value=0)
     """
     helper = LayerHelper('target_assign', **locals())
     out = helper.create_tmp_variable(dtype=input.dtype)

python/paddle/fluid/layers/metric.py

@@ -53,6 +53,43 @@ def accuracy(input, label, k=1, correct=None, total=None):
 
 
 def auc(input, label, curve='ROC', num_thresholds=200):
+    """
+    **Area Under the Curve (AUC) Layer**
+
+    This implementation computes the AUC according to forward output and label.
+    It is used very widely in binary classification evaluation. 
+
+    Note: If input label contains values other than 0 and 1, it will be cast 
+    to `bool`. Find the relevant definitions `here <https://en.wikipedia.org\
+    /wiki/Receiver_operating_characteristic#Area_under_the_curve>`_.
+
+    There are two types of possible curves:
+
+        1. ROC: Receiver operating characteristic;
+        2. PR: Precision Recall
+
+    Args:
+        input(Variable): A floating-point 2D Variable, values are in the range 
+                         [0, 1]. Each row is sorted in descending order. This 
+                         input should be the output of topk. Typically, this 
+                         Variable indicates the probability of each label.
+        label(Variable): A 2D int Variable indicating the label of the training 
+                         data. The height is batch size and width is always 1.
+        curve(str): Curve type, can be 'ROC' or 'PR'. Default 'ROC'.
+        num_thresholds(int): The number of thresholds to use when discretizing 
+                             the roc curve. Default 200.
+
+    Returns:
+        Variable: A scalar representing the current AUC.
+
+    Examples:
+        .. code-block:: python
+        
+            # network is a binary classification model and label the ground truth
+            prediction = network(image, is_infer=True)
+            auc_out=fluid.layers.auc(input=prediction, label=label)
+    """
+
     warnings.warn(
         "This interface not recommended, fluid.layers.auc compute the auc at every minibatch, \
         but can not aggregate them and get the pass AUC, because pass \

python/paddle/fluid/layers/nn.py

@@ -2748,23 +2748,24 @@ def reduce_sum(input, dim=None, keep_dim=False, name=None):
 
 def reduce_mean(input, dim=None, keep_dim=False, name=None):
     """
-    Computes the mean of tensor elements over the given dimension.
+    Computes the mean of the input tensor's elements along the given dimension.
 
     Args:
         input (Variable): The input variable which is a Tensor or LoDTensor.
-        dim (list|int|None): The dimensions along which the mean is computed. If
-            :attr:`None`, compute the mean over all elements of :attr:`input`
-            and return a Tensor variable with a single element, otherwise
+        dim (list|int|None): The dimension along which the mean is computed. If
+            `None`, compute the mean over all elements of :attr:`input`
+            and return a variable with a single element, otherwise it
             must be in the range :math:`[-rank(input), rank(input))`. If
-            :math:`dim[i] < 0`, the dimension to reduce is :math:`rank + dim[i]`.
+            :math:`dim[i] < 0`, the dimension to reduce is 
+            :math:`rank(input) + dim[i]`.
         keep_dim (bool): Whether to reserve the reduced dimension in the
             output Tensor. The result tensor will have one fewer dimension
             than the :attr:`input` unless :attr:`keep_dim` is true.
-        name(str|None): A name for this layer(optional). If set None, the layer
+        name(str|None): A name for this layer(optional). If set `None`, the layer
                        will be named automatically.
 
     Returns:
-        Variable: The reduced Tensor variable.
+        Variable: The reduced mean Variable.
 
     Examples:
         .. code-block:: python
@@ -3517,13 +3518,41 @@ def nce(input,
         input (Variable): input variable.
         label (Variable): label.
         num_total_classes (int):${num_total_classes_comment}
-        sample_weight (int): ${sample_weight_comment}
+        sample_weight (Variable|None): A Variable of shape [batch_size, 1] 
+            storing a weight for each sample. The default weight for each 
+            sample is 1.0.
         param_attr (ParamAttr|None): attributes for parameter
         bias_attr (ParamAttr|None): attributes for bias
         num_neg_samples (int): ${num_neg_samples_comment}
     
     Returns:
-        Variable: output of nce layer.
+        Variable: The output nce loss.
+
+    Examples:
+        .. code-block:: python
+
+            window_size = 5
+            words = []
+            for i in xrange(window_size):
+                words.append(layers.data(
+                    name='word_{0}'.format(i), shape=[1], dtype='int64'))
+
+            dict_size = 10000
+            label_word = int(window_size / 2) + 1
+
+            embs = []
+            for i in xrange(window_size):
+                if i == label_word:
+                    continue
+
+                emb = layers.embedding(input=words[i], size=[dict_size, 32],
+                                       param_attr='emb.w', is_sparse=True)
+                embs.append(emb)
+
+            embs = layers.concat(input=embs, axis=1)
+            loss = layers.nce(input=embs, label=words[label_word],
+                          num_total_classes=dict_size, param_attr='nce.w',
+                          bias_attr='nce.b')
     """
     helper = LayerHelper('nce', **locals())
     assert isinstance(input, Variable)
@@ -3881,31 +3910,30 @@ def softmax_with_cross_entropy(logits, label, soft_label=False):
 
 def smooth_l1(x, y, inside_weight=None, outside_weight=None, sigma=None):
     """
-    **Smooth L1 Loss Operator. **
-
-    This operator computes the smooth L1 loss for X and Y.
-    The operator takes the first dimension of X and Y as batch size.
+    This layer computes the smooth L1 loss for Variable :attr:`x` and :attr:`y`.
+    It takes the first dimension of :attr:`x` and :attr:`y` as batch size.
     For each instance, it computes the smooth L1 loss element by element first
-    and then sums all the losses. So the shape of Out is [batch_size, 1].
+    and then sums all the losses. So the shape of ouput Variable is 
+    [batch_size, 1].
 
     Args:
         x (Variable): A tensor with rank at least 2. The input value of smooth
             L1 loss op with shape [batch_size, dim1, ..., dimN].
         y (Variable): A tensor with rank at least 2. The target value of smooth
-            L1 loss op with same shape as x.
+            L1 loss op with same shape as :attr:`x`.
         inside_weight (Variable|None):  A tensor with rank at least 2. This
-            input is optional and should have same shape with x. If provided,
-            the result of (x - y) will be multiplied by this tensor element by
-            element.
+            input is optional and should have same shape with :attr:`x`. If 
+            provided, the result of (:attr:`x` - :attr:`y`) will be multiplied 
+            by this tensor element by element.
         outside_weight (Variable|None): A tensor with rank at least 2. This
-            input is optional and should have same shape with x. If provided,
-            the out smooth L1 loss will be multiplied by this tensor element
-            by element.
-        sigma (float|None): Hyper parameter of smooth L1 loss op. A float scalar
-            with default value 1.0.
+            input is optional and should have same shape with :attr:`x`. If 
+            provided, the out smooth L1 loss will be multiplied by this tensor 
+            element by element.
+        sigma (float|None): Hyper parameter of smooth L1 loss layer. A float 
+           scalar with default value 1.0.
+
     Returns:
-        Variable: A tensor with rank be 2. The output smooth L1 loss with
-            shape [batch_size, 1].
+        Variable: The output smooth L1 loss with shape [batch_size, 1].
 
     Examples:
         .. code-block:: python
@@ -3916,6 +3944,7 @@ def smooth_l1(x, y, inside_weight=None, outside_weight=None, sigma=None):
             fc = fluid.layers.fc(input=data, size=100)
             out = fluid.layers.smooth_l1(x=fc, y=label)
     """
+
     helper = LayerHelper('smooth_l1_loss', **locals())
     diff = helper.create_tmp_variable(dtype=x.dtype)
     loss = helper.create_tmp_variable(dtype=x.dtype)
@@ -3935,32 +3964,20 @@ def smooth_l1(x, y, inside_weight=None, outside_weight=None, sigma=None):
 
 def one_hot(input, depth):
     """
-    One Hot Operator. This operator creates the one-hot representations for input
-    index values. The following example will help to explain the function of this
-    operator.
+    This layer creates the one-hot representations for input indices.
 
     Args:
-        input(variable):  A Tensor/LodTensor of indices, last dimension must be 1.
-        depth(scalar): an interger defining the depth of the one hot dimension.
+        input(Variable): Input indices, last dimension must be 1.
+        depth(scalar): An interger defining the depth of the one-hot dimension.
 
     Returns:
-         The one-hot tensor or LodTensor, same as input.
+        Variable: The one-hot representations of input.
 
     Examples:
         .. code-block:: python
         
-        X is a LoDTensor:
-          X.lod = [[0, 1, 4]]
-          X.shape = [4, 1]
-          X.data = [[1], [1], [3], [0]]
-        set depth = 4
-        Out is a LoDTensor:
-          Out.lod = [[0, 1, 4]]
-          Out.shape = [4, 4]
-          Out.data = [[0., 1., 0., 0.],
-                      [0., 1., 0., 0.],
-                      [0., 0., 0., 1.],
-                      [1., 0., 0., 0.]]
+            label = layers.data(name="label", shape=[1], dtype="float32")
+            one_hot_label = layers.one_hot(input=label, depth=10)
     """
     helper = LayerHelper("one_hot", **locals())
     one_hot_out = helper.create_tmp_variable(dtype='float32')
@@ -4104,12 +4121,12 @@ def reshape(x, shape, actual_shape=None, act=None, inplace=True, name=None):
 
 def lod_reset(x, y=None, target_lod=None):
     """
-    LoD Reset Operator. Set LoD of **x** to a new one specified by **y** or
-    **target_lod**. When **y** provided, **y.lod** would be considered as target
-    LoD first, otherwise **y.data** would be considered as target LoD. If **y**
-    is not provided, target LoD should be specified by **target_lod**.
-    If target LoD is specified by **Y.data** or **target_lod**, only one level
-    LoD is supported.
+    Set LoD of :attr:`x` to a new one specified by :attr:`y` or
+    :attr:`target_lod`. When :attr:`y` provided, :attr:`y.lod` would be 
+    considered as target LoD first, otherwise :attr:`y.data` would be 
+    considered as target LoD. If :attr:`y` is not provided, target LoD should 
+    be specified by :attr:`target_lod`. If target LoD is specified by 
+    :attr:`Y.data` or :attr:`target_lod`, only one level LoD is supported.
 
     .. code-block:: text
 
@@ -4162,15 +4179,16 @@ def lod_reset(x, y=None, target_lod=None):
 
     Args:
         x (Variable): Input variable which could be a Tensor or LodTensor.
-        y (Variable|None): If provided, output's LoD would be derived from y.
+        y (Variable|None): If provided, output's LoD would be derived 
+                           from :attr:`y`.
         target_lod (list|tuple|None): One level LoD which should be considered
-                                      as target LoD when y not provided.
+                                      as target LoD when :attr:`y` not provided.
 
     Returns:
-        Variable: Output variable with LoD specified by this operator.
+        Variable: Output variable with LoD specified by this layer.
 
     Raises:
-        ValueError: If y and target_lod are both None.
+        ValueError: If :attr:`y` and :attr:`target_lod` are both None.
 
     Examples:
         .. code-block:: python
@@ -4674,10 +4692,6 @@ def random_crop(x, shape, seed=None):
     """
     ${comment}
 
-    Examples:
-        >>> img = fluid.layers.data("img", [3, 256, 256])
-        >>> cropped_img = fluid.layers.random_crop(img, shape=[3, 224, 224])
-
     Args:
         x(${x_type}): ${x_comment}
         shape(${shape_type}): ${shape_comment}
@@ -4687,6 +4701,9 @@ def random_crop(x, shape, seed=None):
     Returns:
         ${out_comment}
     
+    Examples:
+        >>> img = fluid.layers.data("img", [3, 256, 256])
+        >>> cropped_img = fluid.layers.random_crop(img, shape=[3, 224, 224])
     """
     helper = LayerHelper("random_crop", **locals())
     dtype = helper.input_dtype()

python/paddle/fluid/layers/tensor.py

@@ -111,8 +111,21 @@ def create_global_var(shape,
 
 def cast(x, dtype):
     """
-    This function takes in the input with input_dtype
-    and casts it to the output_dtype as the output.
+    This layer takes in the Variable :attr:`x` with :attr:`x.dtype` and casts 
+    it to the output with :attr:`dtype`.
+
+    Args:
+        x (Variable): The input Variable for casting.
+        dtype(np.dtype|core.VarDesc.VarType|str): Data type of the output Variable.
+
+    Returns:
+        Variable: The output Variable after casting.
+
+    Examples:
+        .. code-block:: python
+             
+            data = fluid.layers.data(name='x', shape=[13], dtype='float32')
+            result = fluid.layers.cast(x=data, dtype='float64')
     """
     helper = LayerHelper('cast', **locals())
     out = helper.create_tmp_variable(dtype=dtype)