Merge pull request #13556 from panyx0718/doc

clean a few more kwargs

paddle/fluid/API.spec

@@ -41,7 +41,7 @@ paddle.fluid.DistributeTranspiler.transpile ArgSpec(args=['self', 'trainer_id',
 paddle.fluid.memory_optimize ArgSpec(args=['input_program', 'skip_opt_set', 'print_log', 'level'], varargs=None, keywords=None, defaults=(None, False, 0))
 paddle.fluid.release_memory ArgSpec(args=['input_program', 'skip_opt_set'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.DistributeTranspilerConfig.__init__ 
-paddle.fluid.ParallelExecutor.__init__ ArgSpec(args=['self', 'use_cuda', 'loss_name', 'main_program', 'share_vars_from', 'exec_strategy', 'build_strategy', 'num_trainers', 'trainer_id', 'scope'], varargs=None, keywords='kwargs', defaults=(None, None, None, None, None, 1, 0, None))
+paddle.fluid.ParallelExecutor.__init__ ArgSpec(args=['self', 'use_cuda', 'loss_name', 'main_program', 'share_vars_from', 'exec_strategy', 'build_strategy', 'num_trainers', 'trainer_id', 'scope'], varargs=None, keywords=None, defaults=(None, None, None, None, None, 1, 0, None))
 paddle.fluid.ParallelExecutor.run ArgSpec(args=['self', 'fetch_list', 'feed', 'feed_dict', 'return_numpy'], varargs=None, keywords=None, defaults=(None, None, True))
 paddle.fluid.ExecutionStrategy.__init__ __init__(self: paddle.fluid.core.ExecutionStrategy) -> None
 paddle.fluid.BuildStrategy.GradientScaleStrategy.__init__ __init__(self: paddle.fluid.core.GradientScaleStrategy, arg0: int) -> None
@@ -374,7 +374,7 @@ paddle.fluid.CPUPlace.__init__ __init__(self: paddle.fluid.core.CPUPlace) -> Non
 paddle.fluid.CUDAPlace.__init__ __init__(self: paddle.fluid.core.CUDAPlace, arg0: int) -> None
 paddle.fluid.CUDAPinnedPlace.__init__ __init__(self: paddle.fluid.core.CUDAPinnedPlace) -> None
 paddle.fluid.ParamAttr.__init__ ArgSpec(args=['self', 'name', 'initializer', 'learning_rate', 'regularizer', 'trainable', 'gradient_clip', 'do_model_average'], varargs=None, keywords=None, defaults=(None, None, 1.0, None, True, None, False))
-paddle.fluid.WeightNormParamAttr.__init__ ArgSpec(args=['self', 'dim'], varargs=None, keywords='kwargs', defaults=(None,))
+paddle.fluid.WeightNormParamAttr.__init__ ArgSpec(args=['self', 'dim', 'name', 'initializer', 'learning_rate', 'regularizer', 'trainable', 'gradient_clip', 'do_model_average'], varargs=None, keywords=None, defaults=(None, None, None, 1.0, None, True, None, False))
 paddle.fluid.DataFeeder.__init__ ArgSpec(args=['self', 'feed_list', 'place', 'program'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.DataFeeder.decorate_reader ArgSpec(args=['self', 'reader', 'multi_devices', 'num_places', 'drop_last'], varargs=None, keywords=None, defaults=(None, True))
 paddle.fluid.DataFeeder.feed ArgSpec(args=['self', 'iterable'], varargs=None, keywords=None, defaults=None)

python/paddle/fluid/parallel_executor.py

@@ -74,28 +74,7 @@ class ParallelExecutor(object):
                  build_strategy=None,
                  num_trainers=1,
                  trainer_id=0,
-                 scope=None,
-                 **kwargs):
-        if len(kwargs) != 0:
-            err_msg = ""
-            for key in kwargs:
-                if key in dir(ExecutionStrategy):
-                    err_msg += \
-                        "Setting {0} by constructor is deprecated. Use " \
-                        "strategy=ExecutionStrategy(); strategy.{0}=xxx; " \
-                        "pe=ParallelExecutor(exec_strategy=strategy) " \
-                        "instead.\n ".format(key)
-                elif key in dir(BuildStrategy):
-                    err_msg += \
-                        "Setting {0} by constructor is deprecated. Use " \
-                        "strategy=BuildStrategy(); See help(" \
-                        "paddle.fluid.ParallelExecutor.BuildStrategy) \n".format(
-                            key)
-                else:
-                    err_msg += "Setting {0} by constructor is deprecated. Use strategy.\n".format(
-                        key)
-            raise ValueError(err_msg)
-
+                 scope=None):
         self._places = []
         self._act_places = []
         if use_cuda:

python/paddle/fluid/param_attr.py

@@ -185,7 +185,17 @@ class WeightNormParamAttr(ParamAttr):
 
     Args:
         dim(list): The parameter's name. Default None.
-        kwargs: Any field in ParamAttr. Default None.
+        name(str): The parameter's name. Default None.
+        initializer(Initializer): The method to initial this parameter. Default None.
+        learning_rate(float): The parameter's learning rate. The learning rate when
+            optimize is :math:`global\_lr * parameter\_lr * scheduler\_factor`.
+            Default 1.0.
+        regularizer(WeightDecayRegularizer): Regularization factor. Default None.
+        trainable(bool): Whether this parameter is trainable. Default True.
+        gradient_clip(BaseGradientClipAttr): The method to clip this parameter's
+            gradient. Default None.
+        do_model_average(bool): Whether this parameter should do model average.
+            Default False.
 
     Examples:
         .. code-block:: python
@@ -204,6 +214,21 @@ class WeightNormParamAttr(ParamAttr):
     # these paramters for inference.
     params_with_weight_norm = []
 
-    def __init__(self, dim=None, **kwargs):
-        super(WeightNormParamAttr, self).__init__(**kwargs)
+    def __init__(self,
+                 dim=None,
+                 name=None,
+                 initializer=None,
+                 learning_rate=1.0,
+                 regularizer=None,
+                 trainable=True,
+                 gradient_clip=None,
+                 do_model_average=False):
+        super(WeightNormParamAttr, self).__init__(
+            name=name,
+            initializer=initializer,
+            learning_rate=learning_rate,
+            regularizer=regularizer,
+            trainable=trainable,
+            gradient_clip=gradient_clip,
+            do_model_average=do_model_average)
         self.dim = dim