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

* test=develop

* test=develop

Author: xsrobin

paddle/fluid/API.spec

@@ -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)

paddle/fluid/pybind/pybind.cc

@@ -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/average.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/backward.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 @@ def set_batch_size(self, batch_size):
         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 @@ def set_dense_slots(self, dense_slots_name):
         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 @@ def set_use_slots(self, use_slots_name):
         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 @@ def desc(self):
         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/data_feed_desc.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/executor.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 @@ def _optimized_guard(self, param_and_grads):
 
         Examples:
 
+            >>> import paddle.fluid as fluid
             >>> p, g = backward(...)
             >>> with program._optimized_guard([p,g]):
             >>>     p = p - 0.001 * g
@@ -2940,6 +2948,7 @@ def _lr_schedule_guard(self, is_with_opt=False):
 
         Examples:
 
+            >>> import paddle.fluid as fluid
             >>> p, g = backward(...)
             >>> with program.lr_schedule_guard():
             >>>     lr = lr * decay

python/paddle/fluid/framework.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/initializer.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/io.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)