polish the code

python/paddle/profiler/profiler.py

@@ -268,10 +268,10 @@ class Profiler:
         scheduler (Callable|tuple, optional): If it is a callable object, it takes a step number as parameter and return the corresponding :ref:`ProfilerState <api_paddle_profiler_ProfilerState>`. This callable object can be generated by :ref:`make_scheduler <api_paddle_profiler_make_scheduler>` function.
             If not provided (None), the default scheduler will keep tracing until the profiler exits. If it is a tuple, it has two values start_batch and end_batch,
             which means profiling range [start_batch, end_batch).
-        on_trace_ready (callable): callable object, takes the Profiler object as parameter, which provides a way for users to do post-processing.
-            This callable object will be called when ``scheduler`` returns ``ProfilerState.RECORD_AND_RETURN``.
-        timer_only (bool): If it is True, the cost of Dataloader and every step of the model will be count without profiling. Otherwise, the model will
-            be timed and profiled.
+        on_trace_ready (Callable, optional): Callable object, serves as callback function, and takes the Profiler object as parameter, which provides a way for users to do post-processing.
+            This callable object will be called when ``scheduler`` returns ``ProfilerState.RECORD_AND_RETURN``. The default value is :ref:`export_chrome_tracing <api_paddle_profiler_export_chrome_tracing>` (./profiler_log/).
+        timer_only (bool, optional): If it is True, the cost of Dataloader and every step of the model will be count without profiling. Otherwise, the model will
+            be timed and profiled. Default: False.
 
     Examples:
         1. profiling range [2, 5).
@@ -322,6 +322,7 @@ class Profiler:
         4. Use profiler to get throughput and cost of the model
 
             .. code-block:: python
+                :name: code-example-timer1
 
                 import paddle
                 import paddle.profiler as profiler
@@ -368,8 +369,19 @@ def forward(self, image, label=None):
                     if i % 10 == 0:
                         step_info = p.step_info(unit='images')
                         print("Iter {}: {}".format(i, step_info))
+                        # The average statistics for 10 steps between the last and this call will be
+                        # printed when the "step_info" is called at 10 iteration intervals.
+                        # The values you get may be different from the following.
+                        # Iter 0:  reader_cost: 0.51946 s batch_cost: 0.66077 s ips: 6.054 images/s
+                        # Iter 10:  reader_cost: 0.00014 s batch_cost: 0.00441 s ips: 907.009 images/s
                 p.stop()
-
+                # The performance summary will be automatically printed when the "stop" is called.
+                # Reader Ratio: 2.658%
+                # Time Unit: s, IPS Unit: images/s
+                # |                 |       avg       |       max       |       min       |
+                # |   reader_cost   |     0.00011     |     0.00013     |     0.00007     |
+                # |    batch_cost   |     0.00405     |     0.00434     |     0.00326     |
+                # |       ips       |    1086.42904   |    1227.30604   |    959.92796    |
     """
 
     def __init__(
@@ -455,6 +467,7 @@ def start(self):
                     #train()
                     prof.step()
                 prof.stop()
+
         '''
         # Timing only without profiling
         benchmark().begin()
@@ -519,7 +532,7 @@ def step(self, num_samples: Optional[int]=None):
         Signals the profiler that the next profiling step has started.
         Get the new ProfilerState and trigger corresponding action.
 
-        Parameters:
+        Args:
             num_samples (int|None, optional): Specifies the batch size of every step of the model
             that is used to compute throughput when timer_only is True. Default: None.
 
@@ -569,7 +582,7 @@ def step_info(self, unit=None):
         or others depends on the `unit`. When `num_samples` of `step()` is None, it is
         measured in `steps/s`.
 
-        Parameters:
+        Args:
             unit (string, optional): The unit of input data is only used When `num_samples`
             of `step()` is specified as a number. For example, when it is `images`, the unit
             of throughput is `images/s`. Default: None, the unit of throughput is `samples/s`.
@@ -578,6 +591,7 @@ def step_info(self, unit=None):
             string: A string representing the statistic.
         Examples:
             .. code-block:: python
+                :name: code-example-timer2
 
                 import paddle.profiler as profiler
                 prof = profiler.Profiler(timer_only=True)
@@ -586,8 +600,15 @@ def step_info(self, unit=None):
                     #train()
                     prof.step()
                     if iter % 10 == 0:
-                        print(prof.step_info())
+                        print("Iter {}: {}".format(iter, prof.step_info()))
+                        # The example does not call the DataLoader, so there is no "reader_cost".
+                        # Iter 0:  batch_cost: 0.00001 s ips: 86216.623 steps/s
+                        # Iter 10:  batch_cost: 0.00001 s ips: 103645.034 steps/s
                 prof.stop()
+                # Time Unit: s, IPS Unit: steps/s
+                # |                 |       avg       |       max       |       min       |
+                # |    batch_cost   |     0.00000     |     0.00002     |     0.00000     |
+                # |       ips       |   267846.19437  |   712030.38727  |   45134.16662   |
         """
         if unit is None:
             unit = 'samples'