Add deprecated memory optimize doc (#20111)

* add deprecated memory optimize doc, test=develop, test=document_fix

* merge develop to solve conflict, test=develop, test=document_fix

paddle/fluid/API.spec

@@ -42,8 +42,8 @@ paddle.fluid.DistributeTranspiler.get_pserver_programs (ArgSpec(args=['self', 'e
 paddle.fluid.DistributeTranspiler.get_startup_program (ArgSpec(args=['self', 'endpoint', 'pserver_program', 'startup_program'], varargs=None, keywords=None, defaults=(None, None)), ('document', '90a40b80e0106f69262cc08b861c3e39'))
 paddle.fluid.DistributeTranspiler.get_trainer_program (ArgSpec(args=['self', 'wait_port'], varargs=None, keywords=None, defaults=(True,)), ('document', '0e47f020304e2b824e87ff03475c17cd'))
 paddle.fluid.DistributeTranspiler.transpile (ArgSpec(args=['self', 'trainer_id', 'program', 'pservers', 'trainers', 'sync_mode', 'startup_program', 'current_endpoint'], varargs=None, keywords=None, defaults=(None, '127.0.0.1:6174', 1, True, None, '127.0.0.1:6174')), ('document', '418c7e8b268e9be4104f2809e654c2f7'))
-paddle.fluid.memory_optimize (ArgSpec(args=['input_program', 'skip_opt_set', 'print_log', 'level', 'skip_grads'], varargs=None, keywords=None, defaults=(None, False, 0, True)), ('document', '2348247f684bfd5bb9466470f35be064'))
-paddle.fluid.release_memory (ArgSpec(args=['input_program', 'skip_opt_set'], varargs=None, keywords=None, defaults=(None,)), ('document', 'd38c5b8b2b2e0bb19bcf1b581a80a7e4'))
+paddle.fluid.memory_optimize (ArgSpec(args=['input_program', 'skip_opt_set', 'print_log', 'level', 'skip_grads'], varargs=None, keywords=None, defaults=(None, False, 0, True)), ('document', '2be29dc8ecdec9baa7728fb0c7f80e24'))
+paddle.fluid.release_memory (ArgSpec(args=['input_program', 'skip_opt_set'], varargs=None, keywords=None, defaults=(None,)), ('document', '2be29dc8ecdec9baa7728fb0c7f80e24'))
 paddle.fluid.DistributeTranspilerConfig ('paddle.fluid.transpiler.distribute_transpiler.DistributeTranspilerConfig', ('document', 'beac6f89fe97eb8c66a25de5a09c56d2'))
 paddle.fluid.DistributeTranspilerConfig.__init__ (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.ParallelExecutor ('paddle.fluid.parallel_executor.ParallelExecutor', ('document', '2b4d2e859f2e0c6161f4fed995f7956d'))
@@ -891,8 +891,8 @@ paddle.fluid.transpiler.DistributeTranspiler.get_pserver_programs (ArgSpec(args=
 paddle.fluid.transpiler.DistributeTranspiler.get_startup_program (ArgSpec(args=['self', 'endpoint', 'pserver_program', 'startup_program'], varargs=None, keywords=None, defaults=(None, None)), ('document', '90a40b80e0106f69262cc08b861c3e39'))
 paddle.fluid.transpiler.DistributeTranspiler.get_trainer_program (ArgSpec(args=['self', 'wait_port'], varargs=None, keywords=None, defaults=(True,)), ('document', '0e47f020304e2b824e87ff03475c17cd'))
 paddle.fluid.transpiler.DistributeTranspiler.transpile (ArgSpec(args=['self', 'trainer_id', 'program', 'pservers', 'trainers', 'sync_mode', 'startup_program', 'current_endpoint'], varargs=None, keywords=None, defaults=(None, '127.0.0.1:6174', 1, True, None, '127.0.0.1:6174')), ('document', '418c7e8b268e9be4104f2809e654c2f7'))
-paddle.fluid.transpiler.memory_optimize (ArgSpec(args=['input_program', 'skip_opt_set', 'print_log', 'level', 'skip_grads'], varargs=None, keywords=None, defaults=(None, False, 0, True)), ('document', '2348247f684bfd5bb9466470f35be064'))
-paddle.fluid.transpiler.release_memory (ArgSpec(args=['input_program', 'skip_opt_set'], varargs=None, keywords=None, defaults=(None,)), ('document', 'd38c5b8b2b2e0bb19bcf1b581a80a7e4'))
+paddle.fluid.transpiler.memory_optimize (ArgSpec(args=['input_program', 'skip_opt_set', 'print_log', 'level', 'skip_grads'], varargs=None, keywords=None, defaults=(None, False, 0, True)), ('document', '2be29dc8ecdec9baa7728fb0c7f80e24'))
+paddle.fluid.transpiler.release_memory (ArgSpec(args=['input_program', 'skip_opt_set'], varargs=None, keywords=None, defaults=(None,)), ('document', '2be29dc8ecdec9baa7728fb0c7f80e24'))
 paddle.fluid.transpiler.HashName ('paddle.fluid.transpiler.ps_dispatcher.HashName', ('document', '8190ddc66ee412441f5d97fd3f702bdd'))
 paddle.fluid.transpiler.HashName.__init__ (ArgSpec(args=['self', 'pserver_endpoints'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.transpiler.HashName.dispatch (ArgSpec(args=['self', 'varlist'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))

python/paddle/fluid/transpiler/memory_optimization_transpiler.py

@@ -21,56 +21,8 @@ def memory_optimize(input_program,
                     level=0,
                     skip_grads=True):
     """
-    | Legacy memory optimization strategy, reduce total memory consumption by reuse variable memory between different operators.
-    | Simple sample to explain the algorithm:
-    
-        ..  code-block:: python
-        
-            c = a + b  # assume this is the last time a is used
-            d = b * c
-         
-    | since **a** will not be used anymore after **"c = a + b"**, and the size of **a** and **d** are the same, 
-      we can use variable **a** to replace variable **d**, so actually we can optimize the above code to below:
-
-        ..  code-block:: python
-        
-            c = a + b
-            a = b * c 
-          
-    
-    | Please notice that, in this legacy design, we are using variable **a** to replace **d** directly, which means 
-      after you call this API, some variables may disappear, and some variables may hold unexpected values, like 
-      the above case, actually **a** holds the value of **d** after execution. 
-    
-    | So to protect important variables from being reused/removed in the optimization, we provide skip_opt_set 
-      to allow you specify a variable whitelist. 
-      The variables in the skip_opt_set will not be affected by memory_optimize API.
-    
-    Note: 
-        | **This API is deprecated, please avoid to use it in your new code.**
-        | Does not support operators which will create sub-block like While, IfElse etc.
-    
-    Args:
-        input_program(str): Input Program
-        skip_opt_set(set): vars wil be skipped in memory optimze
-        print_log(bool): whether to print debug log.
-        level(int): 0 or 1, 0 means we replace a with b only when a.size == b.size, 1 means we can replace a with b if a.size <= b.size
-    Returns:
-        None
-
-    Examples:
-        .. code-block:: python
-
-            import paddle.fluid as fluid
-            main_prog = fluid.Program()
-            startup_prog = fluid.Program()
-
-            place = fluid.CPUPlace()
-            exe = fluid.Executor(place)
-
-            exe.run(startup_prog)
-            fluid.memory_optimize(main_prog)
-
+    This API is deprecated since 1.6. Please do not use it. The better
+    memory optimization strategies are enabled by default.
     """
     logging.warn(
         'Caution! paddle.fluid.memory_optimize() is deprecated '
@@ -89,29 +41,8 @@ def memory_optimize(input_program,
 
 def release_memory(input_program, skip_opt_set=None):
     """
-    Modify the input program and insert :code:`delete_op` to early drop not used
-    variables. The modification will be performed inplace.
-
-    Notes: This is an experimental API and could be removed in next few
-    releases. Users should not use this API.
-
-    Args:
-        input_program(Program): The program will be inserted :code:`delete_op`.
-        skip_opt_set(set): vars wil be skipped in memory optimze
-    Returns:
-        None
-
-    Examples:
-        .. code-block:: python
-
-            import paddle.fluid as fluid
-
-            # build network
-            # ...
-            
-            # deprecated API
-            fluid.release_memory(fluid.default_main_program())
-    
+    This API is deprecated since 1.6. Please do not use it. The better
+    memory optimization strategies are enabled by default.
     """
     logging.warn('paddle.fluid.release_memory() is deprecated, it would not'
                  ' take any memory release on your program')