replace the AdagradOptimizer 、adamaxOptimizer、AdadeltaOptimizer、RMSPr…

…opOptimizer、LambOptimizer and Momentum (#54152)

* replace the AdadeltaOptimizer with Adadelta

* replace the RMSPropOptimizer with RMSProp

* replace the LambOptimizer with lamb

* replace the momentum in contrib/optimizer.py with Momentum in python/paddle/optimizer/momentum.py

* fix bug

* fix bug

* fix bug

* fix bug of Lamp

* fix bug of Lamp

* fix bug of import

* replace the AdamaxOptimizer with Admax and change the optimizer base for AdagradOptimizer

* fix bug

* fix bug

* Update optimizer.py

* fix bug

* fix bug

python/paddle/distributed/fleet/meta_optimizers/lamb_optimizer.py

@@ -13,8 +13,8 @@
 
 import logging
 
+import paddle
 from paddle.fluid.optimizer import AdamOptimizer
-from paddle.fluid.optimizer import LambOptimizer as LAMB
 
 from .meta_optimizer_base import MetaOptimizerBase
 
@@ -55,14 +55,13 @@ def exclude_fn(param):
 
             _exclude_from_weight_decay_fn = exclude_fn
 
-        self.lamb_opt = LAMB(
+        self.lamb_opt = paddle.optimizer.Lamb(
             learning_rate=opt._learning_rate,
             lamb_weight_decay=configs['lamb_weight_decay'],
             beta1=opt._beta1,
             beta2=opt._beta2,
             epsilon=opt._epsilon,
-            parameter_list=opt._parameter_list,
-            regularization=opt.regularization,
+            parameters=opt._parameter_list,
             grad_clip=opt._grad_clip,
             exclude_from_weight_decay_fn=_exclude_from_weight_decay_fn,
             name=opt._name,
@@ -111,7 +110,7 @@ def apply_gradients(self, params_grads):
         return self.lamb_opt.apply_gradients(params_grads=params_grads)
 
     def apply_optimize(self, loss, startup_program, params_grads):
-        return self.lamb_opt.apply_optimize(
+        return self.lamb_opt._apply_optimize(
             loss, startup_program=startup_program, params_grads=params_grads
         )
 

python/paddle/fluid/__init__.py

@@ -53,7 +53,6 @@
 from .initializer import set_global_initializer
 from . import layers
 from . import dygraph
-from . import contrib
 from . import optimizer
 from . import backward
 from .backward import gradients
@@ -105,7 +104,6 @@
         'io',
         'initializer',
         'layers',
-        'contrib',
         'dygraph',
         'enable_dygraph',
         'disable_dygraph',