Cherrypick add import to examples lack of it (#18440)

* test=develop

* test=develop

paddle/fluid/pybind/pybind.cc

@@ -625,6 +625,7 @@ All parameter, weight, gradient are variables in Paddle.
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           # create tensor from a scope and set value to it.
           param = scope.var('Param').get_tensor()
           param_array = np.full((height, row_numel), 5.0).astype("float32")
@@ -781,6 +782,7 @@ All parameter, weight, gradient are variables in Paddle.
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           gpu_place = fluid.CUDAPlace(0)
 
         )DOC")
@@ -839,6 +841,7 @@ All parameter, weight, gradient are variables in Paddle.
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           cpu_place = fluid.CPUPlace()
 
         )DOC")
@@ -858,6 +861,7 @@ All parameter, weight, gradient are variables in Paddle.
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           place = fluid.CUDAPinnedPlace()
 
         )DOC")
@@ -1156,6 +1160,7 @@ All parameter, weight, gradient are variables in Paddle.
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           x = fluid.layers.data(name='x', shape=[13], dtype='float32')
           y = fluid.layers.data(name='y', shape=[1], dtype='float32')
           y_predict = fluid.layers.fc(input=x, size=1, act=None)

python/paddle/fluid/average.py

@@ -49,6 +49,7 @@ class WeightedAverage(object):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             avg = fluid.average.WeightedAverage()
             avg.add(value=2.0, weight=1)
             avg.add(value=4.0, weight=2)

python/paddle/fluid/backward.py

@@ -489,6 +489,7 @@ def append_backward(loss, parameter_list=None, no_grad_set=None,
 
             # network configuration code
             # loss from ...
+            import paddle.fluid as fluid
             x = fluid.layers.data(name='x', shape=[13], dtype='float32')
             y = fluid.layers.data(name='y', shape=[1], dtype='float32')
 

python/paddle/fluid/data_feed_desc.py

@@ -31,6 +31,7 @@ class DataFeedDesc(object):
 
     .. code-block:: python
 
+      import paddle.fluid as fluid
       f = open("data.proto", "w")
       print >> f, 'name: "MultiSlotDataFeed"'
       print >> f, 'batch_size: 2'
@@ -61,6 +62,7 @@ class DataFeedDesc(object):
 
     .. code-block:: python
 
+      import paddle.fluid as fluid
       data_feed = fluid.DataFeedDesc('data.proto')
       data_feed.set_batch_size(128)
       data_feed.set_dense_slots('wd')  # The slot named 'wd' will be dense
@@ -95,6 +97,7 @@ class DataFeedDesc(object):
         Example:
             .. code-block:: python
 
+              import paddle.fluid as fluid
               f = open("data.proto", "w")
               print >> f, 'name: "MultiSlotDataFeed"'
               print >> f, 'batch_size: 2'
@@ -131,6 +134,7 @@ class DataFeedDesc(object):
         Example:
             .. code-block:: python
 
+              import paddle.fluid as fluid
               f = open("data.proto", "w")
               print >> f, 'name: "MultiSlotDataFeed"'
               print >> f, 'batch_size: 2'
@@ -175,6 +179,7 @@ class DataFeedDesc(object):
         Example:
             .. code-block:: python
 
+              import paddle.fluid as fluid
               f = open("data.proto", "w")
               print >> f, 'name: "MultiSlotDataFeed"'
               print >> f, 'batch_size: 2'
@@ -217,6 +222,7 @@ class DataFeedDesc(object):
         Example:
             .. code-block:: python
 
+              import paddle.fluid as fluid
               f = open("data.proto", "w")
               print >> f, 'name: "MultiSlotDataFeed"'
               print >> f, 'batch_size: 2'

python/paddle/fluid/executor.py

@@ -72,6 +72,7 @@ def scope_guard(scope):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import numpy
 
             new_scope = fluid.Scope()

python/paddle/fluid/framework.py

@@ -67,6 +67,7 @@ def in_dygraph_mode():
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             if fluid.in_dygraph_mode():
                 pass
 
@@ -143,6 +144,7 @@ def cuda_places(device_ids=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             cuda_places = fluid.cuda_places()
 
     """
@@ -173,6 +175,7 @@ def cpu_places(device_count=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             cpu_places = fluid.cpu_places()
     """
 
@@ -199,6 +202,7 @@ def cuda_pinned_places(device_count=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             cuda_pinned_places_cpu_num = fluid.cuda_pinned_places()
             # or
             cuda_pinned_places = fluid.cuda_pinned_places(1)
@@ -251,6 +255,7 @@ def name_scope(prefix=None):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           with fluid.name_scope("s1"):
               a = fluid.layers.data(name='data', shape=[1], dtype='int32')
               b = a + 1
@@ -412,6 +417,7 @@ class Variable(object):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             cur_program = Program()
             cur_block = cur_program.current_block()
             new_variable = cur_block.create_var(name="X",
@@ -1011,6 +1017,7 @@ class Operator(object):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             cur_program = Program()
             cur_block = cur_program.current_block()
             # var1 += var2 + var3
@@ -2907,6 +2914,7 @@ class Program(object):
 
         Examples:
 
+            >>> import paddle.fluid as fluid
             >>> p, g = backward(...)
             >>> with program._optimized_guard([p,g]):
             >>>     p = p - 0.001 * g
@@ -2940,6 +2948,7 @@ class Program(object):
 
         Examples:
 
+            >>> import paddle.fluid as fluid
             >>> p, g = backward(...)
             >>> with program.lr_schedule_guard():
             >>>     lr = lr * decay

python/paddle/fluid/initializer.py

@@ -42,7 +42,8 @@ def force_init_on_cpu():
 
         .. code-block:: python
 
-	    if fluid.initializer.force_init_on_cpu():
+	    import paddle.fluid as fluid
+        if fluid.initializer.force_init_on_cpu():
     		step = fluid.layers.create_global_var(
         	    shape=[2,3], value=1.0, dtype='float32')
 
@@ -58,7 +59,8 @@ def init_on_cpu():
     Examples:
         .. code-block:: python
 
-	    with fluid.initializer.init_on_cpu():
+	    import paddle.fluid as fluid
+        with fluid.initializer.init_on_cpu():
     		step = fluid.layers.create_global_var(
         	    shape=[2,3], value=1.0, dtype='float32')
 
@@ -133,7 +135,8 @@ class ConstantInitializer(Initializer):
     Examples:
         .. code-block:: python
 
-    	    x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
+    	    import paddle.fluid as fluid
+            x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
 	    fc = fluid.layers.fc(input=x, size=10,
     		param_attr=fluid.initializer.Constant(value=2.0))
 
@@ -292,7 +295,8 @@ class NormalInitializer(Initializer):
     Examples:
         .. code-block:: python
 
-	    x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
+	    import paddle.fluid as fluid
+        x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
 	    fc = fluid.layers.fc(input=x, size=10,
     		param_attr=fluid.initializer.Normal(loc=0.0, scale=2.0))
 
@@ -608,7 +612,8 @@ class MSRAInitializer(Initializer):
     Examples:
         .. code-block:: python
 		
-	    x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
+	    import paddle.fluid as fluid
+        x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
 	    fc = fluid.layers.fc(input=x, size=10,
     		param_attr=fluid.initializer.MSRA(uniform=False))
 
@@ -710,7 +715,8 @@ class BilinearInitializer(Initializer):
 
         .. code-block:: python
 
-	    factor = 2
+	    import paddle.fluid as fluid
+        factor = 2
 	    C = 2
 	    w_attr = fluid.initializer.ParamAttr(
 		learning_rate=0., 
@@ -836,6 +842,7 @@ class NumpyArrayInitializer(Initializer):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             x = fluid.layers.data(name="x", shape=[5], dtype='float32')
             fc = fluid.layers.fc(input=x, size=10,
                 param_attr=fluid.initializer.NumpyArrayInitializer(numpy.array([1,2])))

python/paddle/fluid/io.py

@@ -54,6 +54,7 @@ def is_parameter(var):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             param = fluid.default_main_program().global_block().var('fc.w')
             res = fluid.io.is_parameter(param)
     """
@@ -74,6 +75,7 @@ def is_persistable(var):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             param = fluid.default_main_program().global_block().var('fc.b')
             res = fluid.io.is_persistable(param)
     """
@@ -301,6 +303,7 @@ def _save_distributed_persistables(executor, dirname, main_program):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             exe = fluid.Executor(fluid.CPUPlace())
             param_path = "./my_paddle_model"
             t = distribute_transpiler.DistributeTranspiler()
@@ -681,6 +684,7 @@ def load_params(executor, dirname, main_program=None, filename=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             exe = fluid.Executor(fluid.CPUPlace())
             param_path = "./my_paddle_model"
             prog = fluid.default_main_program()
@@ -723,6 +727,7 @@ def load_persistables(executor, dirname, main_program=None, filename=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             exe = fluid.Executor(fluid.CPUPlace())
             param_path = "./my_paddle_model"
             prog = fluid.default_main_program()
@@ -760,6 +765,7 @@ def _load_distributed_persistables(executor, dirname, main_program=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             exe = fluid.Executor(fluid.CPUPlace())
             param_path = "./my_paddle_model"
             t = distribute_transpiler.DistributeTranspiler()
@@ -1230,6 +1236,7 @@ def get_parameter_value(para, executor):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             exe = fluid.Executor(fluid.CPUPlace())
             param = fluid.default_main_program().global_block().var('fc.w')
             p = fluid.io.get_parameter_value(param, exe)
@@ -1267,6 +1274,7 @@ def get_parameter_value_by_name(name, executor, program=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             exe = fluid.Executor(fluid.CPUPlace())
             p = fluid.io.get_parameter_value('fc.w', exe)
     """

python/paddle/fluid/layers/control_flow.py

@@ -58,6 +58,7 @@ def split_lod_tensor(input, mask, level=0):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           x = fluid.layers.data(name='x', shape=[1])
           x.persistable = True
 
@@ -107,6 +108,7 @@ def merge_lod_tensor(in_true, in_false, x, mask, level=0):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           x = layers.data(
                       name='x', shape=[1], dtype='float32', stop_gradient=False)
           y = layers.data(
@@ -756,6 +758,7 @@ def lod_rank_table(x, level=0):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             x = fluid.layers.data(name='x', shape=[10],
                                   dtype='float32', lod_level=1)
             out = layers.lod_rank_table(x=x, level=0)
@@ -822,6 +825,7 @@ def lod_tensor_to_array(x, table):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           x = fluid.layers.data(name='x', shape=[10])
           table = fluid.layers.lod_rank_table(x, level=0)
           array = fluid.layers.lod_tensor_to_array(x, table)
@@ -855,6 +859,7 @@ def array_to_lod_tensor(x, table):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           x = fluid.layers.data(name='x', shape=[10])
           table = fluid.layers.lod_rank_table(x, level=0)
           array = fluid.layers.lod_tensor_to_array(x, table)
@@ -964,6 +969,7 @@ def create_array(dtype):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           data = fluid.layers.create_array(dtype='float32')
 
     """
@@ -991,6 +997,7 @@ def less_than(x, y, force_cpu=None, cond=None):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           label = fluid.layers.data(name='y', shape=[1], dtype='int64')
           limit = fluid.layers.fill_constant(shape=[1], dtype='int64', value=5)
           cond = fluid.layers.less_than(x=label, y=limit)
@@ -1339,6 +1346,7 @@ class ConditionalBlock(object):
     Examples:
         .. code-block:: python
 
+             import paddle.fluid as fluid
              cond = layers.less_than(x=label, y=limit)
              true_image, false_image = layers.split_lod_tensor(
                  input=image, mask=cond)

python/paddle/fluid/layers/detection.py

@@ -682,6 +682,7 @@ def box_coder(prior_box,
  
         .. code-block:: python
  
+            import paddle.fluid as fluid
             prior_box = fluid.layers.data(name='prior_box', 
                                           shape=[512, 4], 
                                           dtype='float32',
@@ -813,6 +814,7 @@ def yolov3_loss(x,
     Examples:
       .. code-block:: python
 
+          import paddle.fluid as fluid
           x = fluid.layers.data(name='x', shape=[255, 13, 13], dtype='float32')
           gt_box = fluid.layers.data(name='gt_box', shape=[6, 4], dtype='float32')
           gt_label = fluid.layers.data(name='gt_label', shape=[6], dtype='int32')
@@ -1002,6 +1004,8 @@ def detection_map(detect_res,
     Examples:
           .. code-block:: python
 
+            import paddle.fluid as fluid
+            from fluid.layers import detection
             detect_res = fluid.layers.data(
                 name='detect_res',
                 shape=[10, 6],
@@ -1119,6 +1123,7 @@ def bipartite_match(dist_matrix,
 
     Examples:
 
+        >>> import paddle.fluid as fluid
         >>> x = fluid.layers.data(name='x', shape=[4], dtype='float32')
         >>> y = fluid.layers.data(name='y', shape=[4], dtype='float32')
         >>> iou = fluid.layers.iou_similarity(x=x, y=y)
@@ -1340,6 +1345,7 @@ def ssd_loss(location,
         type of `max_negative`.
 
     Examples:
+        >>> import paddle.fluid as fluid
         >>> pb = fluid.layers.data(
         >>>                   name='prior_box',
         >>>                   shape=[10, 4],
@@ -1542,6 +1548,7 @@ def prior_box(input,
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             input = fluid.layers.data(name="input", shape=[3,6,9])
             images = fluid.layers.data(name="images", shape=[3,9,12])
             box, var = fluid.layers.prior_box(
@@ -1668,6 +1675,7 @@ def density_prior_box(input,
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             input = fluid.layers.data(name="input", shape=[3,6,9])
             images = fluid.layers.data(name="images", shape=[3,9,12])
             box, var = fluid.layers.density_prior_box(
@@ -2019,6 +2027,7 @@ def anchor_generator(input,
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             conv1 = fluid.layers.data(name='conv1', shape=[48, 16, 16], dtype='float32')
             anchor, var = fluid.layers.anchor_generator(
                 input=conv1,
@@ -2526,6 +2535,7 @@ def box_clip(input, im_info, name=None):
     Examples:
         .. code-block:: python
         
+            import paddle.fluid as fluid
             boxes = fluid.layers.data(
                 name='boxes', shape=[8, 4], dtype='float32', lod_level=1)
             im_info = fluid.layers.data(name='im_info', shape=[3])
@@ -2730,6 +2740,7 @@ def multiclass_nms(bboxes,
         .. code-block:: python
 
 
+            import paddle.fluid as fluid
             boxes = fluid.layers.data(name='bboxes', shape=[81, 4],
                                       dtype='float32', lod_level=1)
             scores = fluid.layers.data(name='scores', shape=[81],
@@ -2808,6 +2819,7 @@ def distribute_fpn_proposals(fpn_rois,
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             fpn_rois = fluid.layers.data(
                 name='data', shape=[4], dtype='float32', lod_level=1)
             multi_rois, restore_ind = fluid.layers.distribute_fpn_proposals(
@@ -2866,6 +2878,7 @@ def box_decoder_and_assign(prior_box,
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             pb = fluid.layers.data(
                 name='prior_box', shape=[4], dtype='float32')
             pbv = fluid.layers.data(
@@ -2932,6 +2945,7 @@ def collect_fpn_proposals(multi_rois,
     Examples:
         .. code-block:: python
            
+            import paddle.fluid as fluid
             multi_rois = []
             multi_scores = []
             for i in range(4):

python/paddle/fluid/layers/io.py

@@ -84,6 +84,7 @@ def data(name,
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           data = fluid.layers.data(name='x', shape=[784], dtype='float32')
     """
     helper = LayerHelper('data', **locals())
@@ -147,6 +148,7 @@ class ListenAndServ(object):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             with fluid.program_guard(main):
                 serv = layers.ListenAndServ(
                     "127.0.0.1:6170", ["X"], optimizer_mode=False)
@@ -449,6 +451,7 @@ def random_data_generator(low, high, shapes, lod_levels, for_parallel=True):
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             reader = fluid.layers.random_data_generator(
                                              low=0.0,
                                              high=1.0,
@@ -1004,6 +1007,7 @@ def shuffle(reader, buffer_size):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             raw_reader = fluid.layers.io.open_files(filenames=['./data1.recordio',
                                                            './data2.recordio'],
                                                     shapes=[(3,224,224), (1,)],
@@ -1035,6 +1039,7 @@ def batch(reader, batch_size):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             raw_reader = fluid.layers.io.open_files(filenames=['./data1.recordio',
                                                            './data2.recordio'],
                                                     shapes=[(3,224,224), (1,)],

python/paddle/fluid/layers/layer_function_generator.py

@@ -253,6 +253,7 @@ def generate_activation_fn(op_type):
 Examples:
     .. code-block:: python
 
+        import paddle.fluid as fluid
         data = fluid.layers.data(name="input", shape=[32, 784])
         result = fluid.layers.%s(data)
 """ % op_type

python/paddle/fluid/layers/learning_rate_scheduler.py

@@ -54,6 +54,7 @@ def noam_decay(d_model, warmup_steps):
 
     .. code-block:: python
       
+      import padde.fluid as fluid
       import numpy as np
       # set hyper parameters
       d_model = 2
@@ -415,7 +416,8 @@ def cosine_decay(learning_rate, step_each_epoch, epochs):
     Examples:
 	.. code-block:: python
 
-  	    base_lr = 0.1
+  	    import paddle.fluid as fluid
+        base_lr = 0.1
 	    lr = fluid.layers.cosine_decay(
 	    learning_rate = base_lr, step_each_epoch=10000, epochs=120)
     """
@@ -457,6 +459,7 @@ def linear_lr_warmup(learning_rate, warmup_steps, start_lr, end_lr):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             boundaries = [100, 200]
             lr_steps = [0.1, 0.01, 0.001]
             warmup_steps = 50 

python/paddle/fluid/layers/ops.py

@@ -114,6 +114,7 @@ def hard_shrink(x, threshold=None):
 hard_shrink.__doc__ = _hard_shrink_.__doc__ + """
 Examples:
 
+    >>> import paddle.fluid as fluid
     >>> data = fluid.layers.data(name="input", shape=[784])
     >>> result = fluid.layers.hard_shrink(x=data, threshold=0.3)
 """
@@ -135,6 +136,7 @@ def cumsum(x, axis=None, exclusive=None, reverse=None):
 cumsum.__doc__ = _cum_sum_.__doc__ + """
 Examples:
 
+    >>> import paddle.fluid as fluid
     >>> data = fluid.layers.data(name="input", shape=[32, 784])
     >>> result = fluid.layers.cumsum(data, axis=0)
 """
@@ -157,6 +159,7 @@ def thresholded_relu(x, threshold=None):
 thresholded_relu.__doc__ = _thresholded_relu_.__doc__ + """
 Examples:
 
+    >>> import paddle.fluid as fluid
     >>> data = fluid.layers.data(name="input", shape=[1])
     >>> result = fluid.layers.thresholded_relu(data, threshold=0.4)
 """

python/paddle/fluid/layers/tensor.py

@@ -49,6 +49,7 @@ def create_tensor(dtype, name=None, persistable=False):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           tensor = fluid.layers.create_tensor(dtype='float32')
     """
     helper = LayerHelper("create_tensor", **locals())
@@ -85,6 +86,7 @@ def create_parameter(shape,
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import paddle.fluid.layers as layers
             W = layers.create_parameter(shape=[784, 200], dtype='float32')
     """
@@ -123,6 +125,7 @@ def create_global_var(shape,
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import paddle.fluid.layers as layers
             var = layers.create_global_var(shape=[2,3], value=1.0, dtype='float32',
                                           persistable=True, force_cpu=True, name='new_var')
@@ -157,6 +160,7 @@ def cast(x, dtype):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             data = fluid.layers.data(name='x', shape=[13], dtype='float32')
             result = fluid.layers.cast(x=data, dtype='float64')
     """
@@ -190,6 +194,7 @@ def concat(input, axis=0, name=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             a = fluid.layers.data(name='a', shape=[2, 13], dtype='float32')
             b = fluid.layers.data(name='b', shape=[2, 3], dtype='float32')
             c = fluid.layers.data(name='c', shape=[2, 2], dtype='float32')
@@ -482,6 +487,7 @@ def argmin(x, axis=0):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             x = fluid.layers.data(name="x", shape=[3, 4], dtype="float32")
             out = fluid.layers.argmin(x, axis=0)
             out = fluid.layers.argmin(x, axis=-1)
@@ -514,6 +520,7 @@ def argmax(x, axis=0):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             x = fluid.layers.data(name="x", shape=[3, 4], dtype="float32")
             out = fluid.layers.argmax(x, axis=0)
             out = fluid.layers.argmax(x, axis=-1)
@@ -565,6 +572,7 @@ def argsort(input, axis=-1, name=None):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             x = fluid.layers.data(name="x", shape=[3, 4], dtype="float32")
             out, indices = fluid.layers.argsort(input=x, axis=0)
     """
@@ -712,6 +720,7 @@ def save_combine(x, file_path, overwrite=True):
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             v1 = fluid.layers.data(name="data",
                                    shape=(4, 6),
                                    dtype="float32")
@@ -808,6 +817,7 @@ def isfinite(x):
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             var = fluid.layers.data(name="data",
                                     shape=(4, 6),
                                     dtype="float32")
@@ -843,6 +853,7 @@ def range(start, end, step, dtype):
 
         .. code-block:: python
 
+             import paddle.fluid as fluid
              data = fluid.layers.range(0, 10, 2, 'int32')
 
     """
@@ -884,6 +895,7 @@ def linspace(start, stop, num, dtype):
     Examples:
         .. code-block:: python
 
+             import paddle.fluid as fluid
              data = fluid.layers.linspace(0, 10, 5, 'float32') # [0.0,  2.5,  5.0,  7.5, 10.0]
              data = fluid.layers.linspace(0, 10, 1, 'float32') # [0.0]
 
@@ -925,6 +937,7 @@ def zeros_like(x, out=None):
     Examples:
         .. code-block:: python
 
+          import paddle.fluid as fluid
           x = fluid.layers.data(name='x', dtype='float32', shape=[3], append_batch_size=False)
           data = fluid.layers.zeros_like(x) # [0.0, 0.0, 0.0]
 

python/paddle/fluid/metrics.py

@@ -153,6 +153,7 @@ class CompositeMetric(MetricBase):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import numpy as np
             preds = [[0.1], [0.7], [0.8], [0.9], [0.2],
                      [0.2], [0.3], [0.5], [0.8], [0.6]]
@@ -225,6 +226,7 @@ class Precision(MetricBase):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import numpy as np
 
             metric = fluid.metrics.Precision()
@@ -286,6 +288,7 @@ class Recall(MetricBase):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import numpy as np
 
             metric = fluid.metrics.Recall()
@@ -345,6 +348,7 @@ class Accuracy(MetricBase):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             #suppose we have batch_size = 128
             batch_size=128
             accuracy_manager = fluid.metrics.Accuracy()
@@ -415,6 +419,7 @@ class ChunkEvaluator(MetricBase):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             # init the chunck-level evaluation manager
             metric = fluid.metrics.ChunkEvaluator()
 
@@ -504,6 +509,7 @@ class EditDistance(MetricBase):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import numpy as np
 
             # suppose that batch_size is 128
@@ -604,6 +610,7 @@ class Auc(MetricBase):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import numpy as np
             # init the auc metric
             auc_metric = fluid.metrics.Auc("ROC")
@@ -728,6 +735,7 @@ class DetectionMAP(object):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import paddle.fluid.layers as layers
 
             batch_size = -1 # can be any size

python/paddle/fluid/nets.py

@@ -190,6 +190,7 @@ def img_conv_group(input,
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             img = fluid.layers.data(name='img', shape=[1, 28, 28], dtype='float32')
             conv_pool = fluid.nets.img_conv_group(input=img,
                                                   conv_padding=1,
@@ -328,6 +329,7 @@ def glu(input, dim=-1):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             data = fluid.layers.data(
                 name="words", shape=[-1, 6, 3, 9], dtype="float32")
             # shape of output: [-1, 3, 3, 9]

python/paddle/fluid/optimizer.py

@@ -510,6 +510,7 @@ class Optimizer(object):
         Examples:
             .. code-block:: python
 
+                import paddle.fluid as fluid
                 loss = network()
                 optimizer = fluid.optimizer.SGD(learning_rate=0.1)
                 params_grads = optimizer.backward(loss)
@@ -827,6 +828,7 @@ class DGCMomentumOptimizer(MomentumOptimizer):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             optimizer = fluid.optimizer.DGCMomentumOptimizer(
                         learning_rate=0.0001,
                         momentum=0.9,
@@ -1685,6 +1687,7 @@ class AdadeltaOptimizer(Optimizer):
     Examples:
         .. code-block:: python
 
+            import paddle.fluid as fluid
             optimizer = fluid.optimizer.Adadelta(
                 learning_rate=0.0003, epsilon=1.0e-6, rho=0.95)
             _, params_grads = optimizer.minimize(cost)
@@ -2676,7 +2679,8 @@ class PipelineOptimizer(object):
 
     Examples:
         .. code-block:: python
-
+        
+            import paddle.fluid as fluid
             import paddle.fluid.layers as layers
 
             x = fluid.layers.data(name='x', shape=[1], dtype='int64', lod_level=0)

python/paddle/fluid/profiler.py

@@ -113,6 +113,7 @@ def reset_profiler():
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import paddle.fluid.profiler as profiler
             with profiler.profiler('CPU', 'total', '/tmp/profile'):
                 for iter in range(10):
@@ -141,6 +142,7 @@ def start_profiler(state):
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import paddle.fluid.profiler as profiler
 
             profiler.start_profiler('GPU')
@@ -190,6 +192,7 @@ def stop_profiler(sorted_key=None, profile_path='/tmp/profile'):
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import paddle.fluid.profiler as profiler
 
             profiler.start_profiler('GPU')
@@ -257,6 +260,7 @@ def profiler(state, sorted_key=None, profile_path='/tmp/profile'):
 
         .. code-block:: python
 
+            import paddle.fluid as fluid
             import paddle.fluid.profiler as profiler
             import numpy as np