Release 2.0rc cherry pick api rename #28108 (#28184)

* rename count_include_pad-->exclusive  return_indices-->return_mask

* remove track_running_stats

* fix typo.

* rename xxxd-->xxxxD

* solve conflicts

python/paddle/fluid/tests/unittests/parallel_dygraph_sync_batch_norm.py

@@ -63,10 +63,7 @@ class TestLayer(fluid.dygraph.Layer):
             bias_attr=False)
 
         self._sync_batch_norm2 = SyncBatchNorm(
-            num_filters,
+            num_filters, weight_attr=False, bias_attr=False)
-            weight_attr=False,
-            bias_attr=False,
-            track_running_stats=False)
 
     def forward(self, inputs):
         y = self._conv(inputs)

python/paddle/fluid/tests/unittests/test_adaptive_max_pool2d.py

@@ -150,7 +150,7 @@ class TestAdaptiveMaxPool2DAPI(unittest.TestCase):
             x = paddle.to_tensor(self.x_np)
 
             out_1 = paddle.nn.functional.adaptive_max_pool2d(
-                x=x, return_indices=False, output_size=[3, 3])
+                x=x, return_mask=False, output_size=[3, 3])
 
             out_2 = paddle.nn.functional.adaptive_max_pool2d(x=x, output_size=5)
 

python/paddle/fluid/tests/unittests/test_pool1d_api.py

@@ -148,11 +148,7 @@ class TestPool1D_API(unittest.TestCase):
             input_np = np.random.random([2, 3, 32]).astype("float32")
             input = fluid.dygraph.to_variable(input_np)
             result = F.avg_pool1d(
-                input,
+                input, kernel_size=2, stride=2, padding=[1], exclusive=True)
-                kernel_size=2,
-                stride=2,
-                padding=[1],
-                count_include_pad=True)
 
             result_np = avg_pool1D_forward_naive(
                 input_np, ksize=[2], strides=[2], paddings=[1], exclusive=False)
@@ -160,7 +156,8 @@ class TestPool1D_API(unittest.TestCase):
             self.assertTrue(np.allclose(result.numpy(), result_np))
 
             avg_pool1d_dg = paddle.nn.AvgPool1D(
-                kernel_size=2, stride=None, padding=1, count_include_pad=True)
+                kernel_size=2, stride=None, padding=1, exclusive=True)
+
             result = avg_pool1d_dg(input)
             self.assertTrue(np.allclose(result.numpy(), result_np))
 
@@ -200,7 +197,7 @@ class TestPool1D_API(unittest.TestCase):
             input_np = np.random.random([2, 3, 32]).astype("float32")
             input = fluid.dygraph.to_variable(input_np)
             result, index = F.max_pool1d(
-                input, kernel_size=2, stride=2, padding=0, return_indices=True)
+                input, kernel_size=2, stride=2, padding=0, return_mask=True)
 
             result_np = max_pool1D_forward_naive(
                 input_np, ksize=[2], strides=[2], paddings=[0])

python/paddle/fluid/tests/unittests/test_pool2d_api.py

@@ -134,7 +134,7 @@ class TestPool2D_API(unittest.TestCase):
             input_np = np.random.random([2, 3, 32, 32]).astype("float32")
             input = fluid.dygraph.to_variable(input_np)
             result = max_pool2d(
-                input, kernel_size=2, stride=2, padding=0, return_indices=False)
+                input, kernel_size=2, stride=2, padding=0, return_mask=False)
 
             result_np = pool2D_forward_naive(
                 input_np,
@@ -159,7 +159,7 @@ class TestPool2D_API(unittest.TestCase):
                 kernel_size=2,
                 stride=2,
                 padding=0,
-                return_indices=False,
+                return_mask=False,
                 data_format="NHWC")
 
             result_np = pool2D_forward_naive(
@@ -222,7 +222,7 @@ class TestPool2D_API(unittest.TestCase):
                 kernel_size=2,
                 stride=None,
                 padding="SAME",
-                return_indices=True)
+                return_mask=True)
 
             result_np = pool2D_forward_naive(
                 input_np,
@@ -269,7 +269,7 @@ class TestPool2D_API(unittest.TestCase):
                 kernel_size=2,
                 stride=2,
                 padding=padding,
-                return_indices=False)
+                return_mask=False)
 
             result_np = pool2D_forward_naive(
                 input_np,
@@ -490,7 +490,7 @@ class TestPool2DError_API(unittest.TestCase):
                     padding=0,
                     ceil_mode=False,
                     data_format='NHWC',
-                    return_indices=True)
+                    return_mask=True)
 
         self.assertRaises(ValueError, run9)
 

python/paddle/fluid/tests/unittests/test_pool3d_api.py

@@ -83,7 +83,7 @@ class TestPool3D_API(unittest.TestCase):
                 stride=2,
                 padding=1,
                 ceil_mode=False,
-                count_include_pad=True)
+                exclusive=True)
 
             result_np = avg_pool3D_forward_naive(
                 input_np,
@@ -100,7 +100,7 @@ class TestPool3D_API(unittest.TestCase):
                 stride=None,
                 padding=1,
                 ceil_mode=False,
-                count_include_pad=True)
+                exclusive=True)
             result = avg_pool3d_dg(input)
             self.assertTrue(np.allclose(result.numpy(), result_np))
 
@@ -175,7 +175,7 @@ class TestPool3D_API(unittest.TestCase):
                 stride=2,
                 padding=0,
                 data_format="NDHWC",
-                return_indices=False)
+                return_mask=False)
 
             result_np = pool3D_forward_naive(
                 input_np,
@@ -239,7 +239,7 @@ class TestPool3D_API(unittest.TestCase):
                 kernel_size=2,
                 stride=None,
                 padding="SAME",
-                return_indices=True)
+                return_mask=True)
 
             result_np = pool3D_forward_naive(
                 input_np,
@@ -467,7 +467,7 @@ class TestPool3DError_API(unittest.TestCase):
                     stride=2,
                     padding=0,
                     data_format='NDHWC',
-                    return_indices=True)
+                    return_mask=True)
 
         self.assertRaises(ValueError, run10)
 

python/paddle/nn/layer/norm.py

@@ -73,7 +73,6 @@ class _InstanceNormBase(layers.Layer):
                  momentum=0.9,
                  weight_attr=None,
                  bias_attr=None,
-                 track_running_stats=False,
                  data_format="NCHW",
                  name=None):
         super(_InstanceNormBase, self).__init__()
@@ -135,9 +134,6 @@ class InstanceNorm1D(_InstanceNormBase):
         epsilon(float, optional): A value added to the denominator for
             numerical stability. Default is 1e-5.
         momentum(float, optional): The value used for the moving_mean and moving_var computation. Default: 0.9.
-        track_running_stats(bool, optional): Whether to use global mean and
-            variance. In train mode, when setting track_running_stats True, the global mean
-            and variance are also used during train period. Default: False.
         weight_attr(ParamAttr|bool, optional): The parameter attribute for Parameter `scale`
              of instance_norm. If it is set to None or one attribute of ParamAttr, instance_norm
 	     will create ParamAttr as weight_attr, the name of scale can be set in ParamAttr.
@@ -159,9 +155,6 @@ class InstanceNorm1D(_InstanceNormBase):
     Returns:
         None.
 
-    **Note**:
-        Momentum and track_running_stats is not effective. The next version will fix the problem .
-
 
     Examples:
 
@@ -214,9 +207,6 @@ class InstanceNorm2D(_InstanceNormBase):
         epsilon(float, optional): A value added to the denominator for
             numerical stability. Default is 1e-5.
         momentum(float, optional): The value used for the moving_mean and moving_var computation. Default: 0.9.
-        track_running_stats(bool, optional): Whether to use global mean and
-            variance. In train mode, when setting track_running_stats True, the global mean
-            and variance are also used during train period. Default: False.
         weight_attr(ParamAttr|bool, optional): The parameter attribute for Parameter `scale`
              of instance_norm. If it is set to None or one attribute of ParamAttr, instance_norm
 	     will create ParamAttr as weight_attr, the name of scale can be set in ParamAttr.
@@ -237,8 +227,6 @@ class InstanceNorm2D(_InstanceNormBase):
     Returns:
         None.
 
-    **Note**:
-        Momentum and track_running_stats is not effective. The next version will fix the problem .
 
     Examples:
 
@@ -290,9 +278,6 @@ class InstanceNorm3D(_InstanceNormBase):
         epsilon(float, optional): A value added to the denominator for
             numerical stability. Default is 1e-5.
         momentum(float, optional): The value used for the moving_mean and moving_var computation. Default: 0.9.
-        track_running_stats(bool, optional): Whether to use global mean and
-            variance. In train mode, when setting track_running_stats True, the global mean
-            and variance are also used during train period. Default: False.
         weight_attr(ParamAttr|bool, optional): The parameter attribute for Parameter `scale`
              of instance_norm. If it is set to None or one attribute of ParamAttr, instance_norm
 	     will create ParamAttr as weight_attr, the name of scale can be set in ParamAttr.
@@ -313,8 +298,6 @@ class InstanceNorm3D(_InstanceNormBase):
     Returns:
         None.
 
-    **Note**:
-        Momentum and track_running_stats is not effective. The next version will fix the problem .
 
     Examples:
 
@@ -570,7 +553,6 @@ class _BatchNormBase(layers.Layer):
                  weight_attr=None,
                  bias_attr=None,
                  data_format='NCHW',
-                 track_running_stats=True,
                  name=None):
         super(_BatchNormBase, self).__init__()
         self._num_features = num_features
@@ -636,7 +618,6 @@ class _BatchNormBase(layers.Layer):
         self._momentum = momentum
         self._epsilon = epsilon
         self._fuse_with_relu = False
-        self._track_running_stats = track_running_stats
         self._name = name
 
     def _check_input_dim(self, input):
@@ -651,11 +632,7 @@ class _BatchNormBase(layers.Layer):
 
         self._check_input_dim(input)
 
-        if not self.training and not self._track_running_stats:
+        if self.training:
-            raise ValueError(
-                'When inference, expected track_running_stats is True.')
-
-        if self.training and not self._track_running_stats:
             warnings.warn(
                 "When training, we now always track global mean and variance.")
 
@@ -720,9 +697,6 @@ class BatchNorm1D(_BatchNormBase):
             will create ParamAttr as bias_attr. If it is set to Fasle, the weight is not learnable.
             If the Initializer of the bias_attr is not set, the bias is initialized zero. Default: None.
         data_format(str, optional): Specify the input data format, may be "NC", "NCL" or "NLC". Defalut "NCL".
-        track_running_stats(bool, optional): Whether to use global mean and variance. In train period, 
-            True will track global mean and variance used for inference. When inference, track_running_stats must be 
-            True. Default: True.
         name(str, optional): Name for the BatchNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 
     Shape:
@@ -733,9 +707,6 @@ class BatchNorm1D(_BatchNormBase):
     Returns:
         None.
     
-    **Note**:
-        Now track_running_stats is actucal always true. The next version will fix the problem .
-    
 
     Examples:
         .. code-block:: python
@@ -817,9 +788,6 @@ class BatchNorm2D(_BatchNormBase):
             will create ParamAttr as bias_attr. If it is set to Fasle, the weight is not learnable.
             If the Initializer of the bias_attr is not set, the bias is initialized zero. Default: None.
         data_format(str, optional): Specify the input data format, the data format can be "NCHW" or "NHWC". Default: NCHW.
-        track_running_stats(bool, optional): Whether to use global mean and variance. In train period, 
-            True will track global mean and variance used for inference. When inference, track_running_stats must be 
-            True. Default: True.
         name(str, optional): Name for the BatchNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 
     Shape:
@@ -830,9 +798,6 @@ class BatchNorm2D(_BatchNormBase):
     Returns:
         None
 
-    **Note**:
-        Now track_running_stats is actucal always true. The next version will fix the problem .
-
     Examples:
         .. code-block:: python
 
@@ -912,9 +877,6 @@ class BatchNorm3D(_BatchNormBase):
             will create ParamAttr as bias_attr. If it is set to Fasle, the weight is not learnable.
             If the Initializer of the bias_attr is not set, the bias is initialized zero. Default: None.
         data_format(str, optional): Specify the input data format, the data format can be "NCDHW" or "NDHWC. Default: NCDHW.
-        track_running_stats(bool, optional): Whether to use global mean and variance. In train period, 
-            True will track global mean and variance used for inference. When inference, track_running_stats must be 
-            True. Default: True.
         name(str, optional): Name for the BatchNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 
     Shape:
@@ -925,9 +887,6 @@ class BatchNorm3D(_BatchNormBase):
     Returns:
         None
 
-    **Note**:
-        Now track_running_stats is actucal always true. The next version will fix the problem .
-
     Examples:
         .. code-block:: python
 
@@ -1024,8 +983,6 @@ class SyncBatchNorm(_BatchNormBase):
              will create ParamAttr as bias_attr. If the Initializer of the bias_attr
              is not set, the bias is initialized zero. If it is set to False, this layer will not 
              have trainable bias parameter. Default: None.
-        track_running_stats(bool, optional): Whether to compute global stats, which including running mean and 
-             running variance. Default: True.
 
     Shapes:
         input: Tensor that the dimension from 2 to 5.
@@ -1055,11 +1012,10 @@ class SyncBatchNorm(_BatchNormBase):
                  weight_attr=None,
                  bias_attr=None,
                  data_format='NCHW',
-                 track_running_stats=True,
                  name=None):
         super(SyncBatchNorm,
               self).__init__(num_features, momentum, epsilon, weight_attr,
-                             bias_attr, data_format, track_running_stats, name)
+                             bias_attr, data_format, name)
 
     def forward(self, x):
         # create output
@@ -1147,10 +1103,10 @@ class SyncBatchNorm(_BatchNormBase):
         """
         layer_output = layer
         if isinstance(layer, _BatchNormBase):
-            layer_output = SyncBatchNorm(
+            layer_output = SyncBatchNorm(layer._num_features, layer._momentum,
-                layer._num_features, layer._momentum, layer._epsilon,
+                                         layer._epsilon, layer._weight_attr,
-                layer._weight_attr, layer._bias_attr, layer._data_format,
+                                         layer._bias_attr, layer._data_format,
-                layer._track_running_stats, layer._name)
+                                         layer._name)
 
             if layer._weight_attr != False and layer._bias_attr != False:
                 with no_grad():