Add examples for AdamaxOptimizer (#17381)

test=develop

python/paddle/fluid/optimizer.py

@@ -1251,6 +1251,33 @@ class AdamaxOptimizer(Optimizer):
     However, it is added here for numerical stability to prevent the
     division by 0 error.
 
+    Examples:
+        .. code-block:: python
+
+          import paddle.fluid as fluid
+          import numpy
+
+          # First create the Executor.
+          place = fluid.CPUPlace() # fluid.CUDAPlace(0)
+          exe = fluid.Executor(place)
+
+          train_program = fluid.Program()
+          startup_program = fluid.Program()
+          with fluid.program_guard(train_program, startup_program):
+              data = fluid.layers.data(name='X', shape=[1], dtype='float32')
+              hidden = fluid.layers.fc(input=data, size=10)
+              loss = fluid.layers.mean(hidden)
+              adam = fluid.optimizer.Adamax(learning_rate=0.2)
+              adam.minimize(loss)
+
+          # Run the startup program once and only once.
+          exe.run(startup_program)
+
+          x = numpy.random.random(size=(10, 1)).astype('float32')
+          outs = exe.run(program=train_program,
+                        feed={'X': x},
+                         fetch_list=[loss.name])
+
     Args:
         learning_rate (float|Variable): the learning rate used to update parameters. \
         Can be a float value or a Variable with one float value as data element.
@@ -1261,12 +1288,6 @@ class AdamaxOptimizer(Optimizer):
                         fluid.regularizer.L2DecayRegularizer.
         name: A optional name prefix.
 
-    Examples:
-        .. code-block:: python
-
-            optimizer = fluid.optimizer.Adamax(learning_rate=0.2)
-            optimizer.minimize(cost)
-
     Notes:
        Currently, AdamaxOptimizer doesn't support sparse parameter optimization.
     """