Fix/program doc (#17908)

* test=develop, add some comments for Program.clone

* test=develop, add API.spec

* test=develop, refine comments

* refine Program doc and clone doc

* test=develop, refine doc

paddle/fluid/API.spec

 paddle.fluid.Program.__init__ (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.Program.block (ArgSpec(args=['self', 'index'], varargs=None, keywords=None, defaults=None), ('document', '86cd9499e226be661a3d686260ee1150'))
-paddle.fluid.Program.clone (ArgSpec(args=['self', 'for_test'], varargs=None, keywords=None, defaults=(False,)), ('document', '17d059efb24c81dde6166c6b0b93e9d0'))
+paddle.fluid.Program.clone (ArgSpec(args=['self', 'for_test'], varargs=None, keywords=None, defaults=(False,)), ('document', 'a65221387f84c74eee5130d7678ca900'))
 paddle.fluid.Program.current_block (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', 'd601c7719e425e3d9cf862ea4ad194ca'))
 paddle.fluid.Program.global_block (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', 'd64ea1dc96e9f674499ea3006d470aa4'))
 paddle.fluid.Program.list_vars (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '32c14b0f12baae4b352200fa09b5e789'))

python/paddle/fluid/framework.py

@@ -376,7 +376,7 @@ class Variable(object):
     two variables in different blocks could have the same name.
 
     There are many kinds of variables. Each kind of them has its own attributes
-    and usages. Please reference the framework.proto for details.
+    and usages. Please refer to the framework.proto for details.
 
     Most of a Variable's member variables can be setted to be None. It mean
     it is not available or will be specified later.
@@ -2771,9 +2771,18 @@ class Program(object):
     create c++ Program. A program is a self-contained programing
     language like container. It has at least one Block, when the
     control flow op like conditional_block, while_op is included,
-    it will contains nested block.
+    it will contain nested block.
     Please reference the framework.proto for details.
 
+    A set of Program usually contains startup program and main program.
+    A startup program is set to contain some initial work , and the main
+    program will contain the network structure and vars for train.
+
+    A set of Program can be used for test or train, in train program ,
+    Paddle will contain all content to build a train network,  in test
+    program Paddle will prune some content which is irrelevant to test, eg.
+    backward ops and vars.
+
     Notes: we have default_startup_program and default_main_program
     by default, a pair of them will shared the parameters.
     The default_startup_program only run once to initialize parameters,
@@ -3106,6 +3115,9 @@ class Program(object):
 
                     train_program = fluid.Program()
                     startup_program = fluid.Program()
+
+                    # startup_program is used to do some parameter init work,
+                    # and main program is used to hold the network
                     with fluid.program_guard(train_program, startup_program):
                         with fluid.unique_name.guard():
                             img = fluid.layers.data(name='image', shape=[784])
@@ -3117,6 +3129,15 @@ class Program(object):
                             avg_loss = fluid.layers.mean(loss)
                             test_program = train_program.clone(for_test=False)
                     print_prog(test_program)
+
+                    # Due to parameter sharing usage for train and test, so we need to use startup program of train
+                    # instead of using test startup program, while nothing is in test's startup program
+
+                    # In Paddle Fluid we will share weights by using the same Variable name. In train and test program
+                    # all parameters will have the same name and this can make train and test program sharing parameters,
+                    # that's why we need to use startup program of train. And for startup program of test, it has nothing,
+                    # since it is a new program.
+
                     with fluid.program_guard(train_program, startup_program):
                         with fluid.unique_name.guard():
                             sgd = fluid.optimizer.SGD(learning_rate=1e-3)