cherry pick, fix dygraph api doc, test=release/1.5

BackwardStrategy
dygraph.nn
dygraph.checkpoint

paddle/fluid/API.spec

@@ -731,8 +731,8 @@ paddle.fluid.dygraph.Tracer.train_mode (ArgSpec(args=['self'], varargs=None, key
 paddle.fluid.dygraph.start_gperf_profiler (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.dygraph.stop_gperf_profiler (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.dygraph.prepare_context (ArgSpec(args=['strategy'], varargs=None, keywords=None, defaults=(None,)), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
-paddle.fluid.dygraph.save_persistables (ArgSpec(args=['model_dict', 'dirname', 'optimizers'], varargs=None, keywords=None, defaults=('save_dir', None)), ('document', 'bdeefe733228f5f2d4a8f8c61a5956cf'))
-paddle.fluid.dygraph.load_persistables (ArgSpec(args=['dirname'], varargs=None, keywords=None, defaults=('save_dir',)), ('document', 'fb79b050b5eb52fa9c5fdccefe521aa1'))
+paddle.fluid.dygraph.save_persistables (ArgSpec(args=['model_dict', 'dirname', 'optimizers'], varargs=None, keywords=None, defaults=('save_dir', None)), ('document', '7f526f879139a14cda8e0b5a9171f264'))
+paddle.fluid.dygraph.load_persistables (ArgSpec(args=['dirname'], varargs=None, keywords=None, defaults=('save_dir',)), ('document', '2574d50a7a9f89fb0d74ddf73d8128f0'))
 paddle.fluid.dygraph.NoamDecay.__init__ (ArgSpec(args=['self', 'd_model', 'warmup_steps', 'begin', 'step', 'dtype'], varargs=None, keywords=None, defaults=(1, 1, 'float32')), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.dygraph.NoamDecay.create_lr_var (ArgSpec(args=['self', 'lr'], varargs=None, keywords=None, defaults=None), ('document', '013bc233558149d0757b3df57845b866'))
 paddle.fluid.dygraph.NoamDecay.step (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))

paddle/fluid/pybind/imperative.cc

@@ -162,22 +162,23 @@ void BindImperative(pybind11::module *m_ptr) {
     1. :code:`sort_sum_gradient`, which will sum the gradient by the reverse order of trace.
 
     Examples:
-         .. code-block:: python
-
-           import numpy as np
-           import paddle.fluid as fluid
-           from paddle.fluid import FC
-
-           x = np.ones([2, 2], np.float32)
-           with fluid.dygraph.guard():
-               inputs2 = []
-               for _ in range(10):
-                   inputs2.append(fluid.dygraph.base.to_variable(x))
-               ret2 = fluid.layers.sums(inputs2)
-               loss2 = fluid.layers.reduce_sum(ret2)
-               backward_strategy = fluid.dygraph.BackwardStrategy()
-               backward_strategy.sort_sum_gradient = True
-               loss2.backward(backward_strategy)
+
+        .. code-block:: python
+
+          import numpy as np
+          import paddle.fluid as fluid
+          from paddle.fluid import FC
+
+          x = np.ones([2, 2], np.float32)
+          with fluid.dygraph.guard():
+              inputs2 = []
+              for _ in range(10):
+                  inputs2.append(fluid.dygraph.base.to_variable(x))
+              ret2 = fluid.layers.sums(inputs2)
+              loss2 = fluid.layers.reduce_sum(ret2)
+              backward_strategy = fluid.dygraph.BackwardStrategy()
+              backward_strategy.sort_sum_gradient = True
+              loss2.backward(backward_strategy)
       )DOC");
   backward_strategy.def(py::init())
       .def_property("sort_sum_gradient",

python/paddle/fluid/dygraph/checkpoint.py

@@ -43,35 +43,38 @@ def save_persistables(model_dict, dirname='save_dir', optimizers=None):
         optimizers(fluid.Optimizer|list(fluid.Optimizer)|None): The optimizers to be saved
 
     Returns:
+        None
 
     Examples:
+
         .. code-block:: python
-            ptb_model = PtbModel(
+
+          ptb_model = PtbModel(
                 hidden_size=hidden_size,
                 vocab_size=vocab_size,
                 num_layers=num_layers,
                 num_steps=num_steps,
                 init_scale=init_scale)
-            sgd = fluid.optimizer.SGD(learning_rate=0.01)
-            x_data = np.arange(12).reshape(4, 3).astype('int64')
-            y_data = np.arange(1, 13).reshape(4, 3).astype('int64')
-            x_data = x_data.reshape((-1, num_steps, 1))
-            y_data = y_data.reshape((-1, 1))
-            init_hidden_data = np.zeros(
+          sgd = fluid.optimizer.SGD(learning_rate=0.01)
+          x_data = np.arange(12).reshape(4, 3).astype('int64')
+          y_data = np.arange(1, 13).reshape(4, 3).astype('int64')
+          x_data = x_data.reshape((-1, num_steps, 1))
+          y_data = y_data.reshape((-1, 1))
+          init_hidden_data = np.zeros(
                 (num_layers, batch_size, hidden_size), dtype='float32')
-            init_cell_data = np.zeros(
+          init_cell_data = np.zeros(
                 (num_layers, batch_size, hidden_size), dtype='float32')
-            x = to_variable(x_data)
-            y = to_variable(y_data)
-            init_hidden = to_variable(init_hidden_data)
-            init_cell = to_variable(init_cell_data)
-            dy_loss, last_hidden, last_cell = ptb_model(x, y, init_hidden,
+          x = to_variable(x_data)
+          y = to_variable(y_data)
+          init_hidden = to_variable(init_hidden_data)
+          init_cell = to_variable(init_cell_data)
+          dy_loss, last_hidden, last_cell = ptb_model(x, y, init_hidden,
                                                         init_cell)
-            dy_loss.backward()
-            sgd.minimize(dy_loss)
-            ptb_model.clear_gradient()
-            param_path = "./my_paddle_model"
-            fluid.dygraph.save_persistables(ptb_model.state_dict(), dirname=param_path, sgd)
+          dy_loss.backward()
+          sgd.minimize(dy_loss)
+          ptb_model.clear_gradient()
+          param_path = "./my_paddle_model"
+          fluid.dygraph.save_persistables(ptb_model.state_dict(), dirname=param_path, sgd)
     """
     if isinstance(model_dict, collections.OrderedDict):
         _save_var_to_file(model_dict, optimizers, dirname, None)
@@ -95,13 +98,15 @@ def load_persistables(dirname='save_dir'):
         optimizer dict: The optimizer
 
     Examples:
-        .. code-block:: python
-            my_layer = layer(fluid.Layer)
-            param_path = "./my_paddle_model"
-            sgd = SGDOptimizer(learning_rate=1e-3)
-            param_dict, optimizer_dict = fluid.dygraph.load_persistables(my_layer.parameters(), param_path)
-            param_1 = param_dict['PtbModel_0.w_1']
-            sgd.load(optimizer_dict)
+
+         .. code-block:: python
+
+           my_layer = layer(fluid.Layer)
+           param_path = "./my_paddle_model"
+           sgd = SGDOptimizer(learning_rate=1e-3)
+           param_dict, optimizer_dict = fluid.dygraph.load_persistables(my_layer.parameters(), param_path)
+           param_1 = param_dict['PtbModel_0.w_1']
+           sgd.load(optimizer_dict)
 
         """
     return _load_var_from_file(dirname)