2.0rc api rename

python/paddle/__init__.py

@@ -221,7 +221,7 @@
 
 from .tensor.to_string import set_printoptions
 
-from .framework.random import manual_seed  #DEFINE_ALIAS
+from .framework.random import seed  #DEFINE_ALIAS
 from .framework.random import get_cuda_rng_state  #DEFINE_ALIAS
 from .framework.random import set_cuda_rng_state  #DEFINE_ALIAS
 from .framework import ParamAttr  #DEFINE_ALIAS

python/paddle/amp/auto_cast.py

@@ -37,7 +37,7 @@ def auto_cast(enable=True, custom_white_list=None, custom_black_list=None):
 
         import paddle
 
-        conv2d = paddle.nn.Conv2d(3, 2, 3, bias_attr=False)
+        conv2d = paddle.nn.Conv2D(3, 2, 3, bias_attr=False)
         data = paddle.rand([10, 3, 32, 32])
 
         with paddle.amp.auto_cast():

python/paddle/amp/grad_scaler.py

@@ -50,7 +50,7 @@ class GradScaler(AmpScaler):
 
         import paddle
 
-        model = paddle.nn.Conv2d(3, 2, 3, bias_attr=True)
+        model = paddle.nn.Conv2D(3, 2, 3, bias_attr=True)
         optimizer = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters())
         scaler = paddle.amp.GradScaler(init_loss_scaling=1024)
         data = paddle.rand([10, 3, 32, 32])
@@ -90,7 +90,7 @@ def scale(self, var):
 
             import paddle
 
-            model = paddle.nn.Conv2d(3, 2, 3, bias_attr=True)
+            model = paddle.nn.Conv2D(3, 2, 3, bias_attr=True)
             optimizer = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters())
             scaler = paddle.amp.GradScaler(init_loss_scaling=1024)
             data = paddle.rand([10, 3, 32, 32])
@@ -122,7 +122,7 @@ def minimize(self, optimizer, *args, **kwargs):
 
             import paddle
 
-            model = paddle.nn.Conv2d(3, 2, 3, bias_attr=True)
+            model = paddle.nn.Conv2D(3, 2, 3, bias_attr=True)
             optimizer = paddle.optimizer.SGD(learning_rate=0.01, parameters=model.parameters())
             scaler = paddle.amp.GradScaler(init_loss_scaling=1024)
             data = paddle.rand([10, 3, 32, 32])

python/paddle/distribution.py

@@ -670,13 +670,13 @@ class Categorical(Distribution):
             import paddle
             from paddle.distribution import Categorical
 
-            paddle.manual_seed(100) # on CPU device
+            paddle.seed(100) # on CPU device
             x = paddle.rand([6])
             print(x.numpy())
             # [0.5535528  0.20714243 0.01162981
             #  0.51577556 0.36369765 0.2609165 ]
 
-            paddle.manual_seed(200) # on CPU device
+            paddle.seed(200) # on CPU device
             y = paddle.rand([6])
             print(y.numpy())
             # [0.77663314 0.90824795 0.15685187
@@ -685,7 +685,7 @@ class Categorical(Distribution):
             cat = Categorical(x)
             cat2 = Categorical(y)
 
-            paddle.manual_seed(1000) # on CPU device
+            paddle.seed(1000) # on CPU device
             cat.sample([2,3])
             # [[0, 0, 5],
             #  [3, 4, 5]]
@@ -744,15 +744,15 @@ def sample(self, shape):
                 import paddle
                 from paddle.distribution import Categorical
 
-                paddle.manual_seed(100) # on CPU device
+                paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
                 print(x.numpy())
                 # [0.5535528  0.20714243 0.01162981
                 #  0.51577556 0.36369765 0.2609165 ]
 
                 cat = Categorical(x)
 
-                paddle.manual_seed(1000) # on CPU device
+                paddle.seed(1000) # on CPU device
                 cat.sample([2,3])
                 # [[0, 0, 5],
                 #  [3, 4, 5]]
@@ -791,13 +791,13 @@ def kl_divergence(self, other):
                 import paddle
                 from paddle.distribution import Categorical
 
-                paddle.manual_seed(100) # on CPU device
+                paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
                 print(x.numpy())
                 # [0.5535528  0.20714243 0.01162981
                 #  0.51577556 0.36369765 0.2609165 ]
 
-                paddle.manual_seed(200) # on CPU device
+                paddle.seed(200) # on CPU device
                 y = paddle.rand([6])
                 print(y.numpy())
                 # [0.77663314 0.90824795 0.15685187
@@ -842,7 +842,7 @@ def entropy(self):
                 import paddle
                 from paddle.distribution import Categorical
 
-                paddle.manual_seed(100) # on CPU device
+                paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
                 print(x.numpy())
                 # [0.5535528  0.20714243 0.01162981
@@ -887,7 +887,7 @@ def probs(self, value):
                 import paddle
                 from paddle.distribution import Categorical
 
-                paddle.manual_seed(100) # on CPU device
+                paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
                 print(x.numpy())
                 # [0.5535528  0.20714243 0.01162981
@@ -953,7 +953,7 @@ def log_prob(self, value):
                 import paddle
                 from paddle.distribution import Categorical
 
-                paddle.manual_seed(100) # on CPU device
+                paddle.seed(100) # on CPU device
                 x = paddle.rand([6])
                 print(x.numpy())
                 # [0.5535528  0.20714243 0.01162981

python/paddle/fluid/contrib/tests/test_weight_decay_extend.py

@@ -114,7 +114,7 @@ def run_program(self, place, feed_list):
         return param_sum
 
     def check_weight_decay(self, place, model):
-        paddle.manual_seed(1)
+        paddle.seed(1)
         paddle.framework.random._manual_program_seed(1)
         main_prog = fluid.framework.Program()
         startup_prog = fluid.framework.Program()
@@ -137,7 +137,7 @@ def check_weight_decay(self, place, model):
         return param_sum
 
     def check_weight_decay2(self, place, model):
-        paddle.manual_seed(1)
+        paddle.seed(1)
         paddle.framework.random._manual_program_seed(1)
         main_prog = fluid.framework.Program()
         startup_prog = fluid.framework.Program()

python/paddle/fluid/dygraph/layers.py

@@ -1058,7 +1058,7 @@ def __init__(self):
                         super(Mylayer, self).__init__()
                         self.linear1 = paddle.nn.Linear(10, 10)
                         self.linear2 = paddle.nn.Linear(5, 5)
-                        self.conv2d = paddle.nn.Conv2d(3, 2, 3)
+                        self.conv2d = paddle.nn.Conv2D(3, 2, 3)
                         self.embedding = paddle.nn.Embedding(128, 16)
                         self.h_0 = paddle.to_tensor(np.zeros([10, 10]).astype('float32'))
 

python/paddle/fluid/dygraph/nn.py

@@ -110,7 +110,7 @@ class Conv2D(layers.Layer):
         dilation (int or tuple, optional): The dilation size. If dilation is a tuple, it must
             contain two integers, (dilation_H, dilation_W). Otherwise, the
             dilation_H = dilation_W = dilation. Default: 1.
-        groups (int, optional): The groups number of the Conv2d Layer. According to grouped
+        groups (int, optional): The groups number of the Conv2D Layer. According to grouped
             convolution in Alex Krizhevsky's Deep CNN paper: when group=2,
             the first half of the filters is only connected to the first half
             of the input channels, while the second half of the filters is only
@@ -345,7 +345,7 @@ class Conv3D(layers.Layer):
         dilation (int|tuple, optional): The dilation size. If dilation is a tuple, it must
             contain three integers, (dilation_D, dilation_H, dilation_W). Otherwise, the
             dilation_D = dilation_H = dilation_W = dilation. The default value is 1.
-        groups (int, optional): The groups number of the Conv3d Layer. According to grouped
+        groups (int, optional): The groups number of the Conv3D Layer. According to grouped
             convolution in Alex Krizhevsky's Deep CNN paper: when group=2,
             the first half of the filters is only connected to the first half
             of the input channels, while the second half of the filters is only
@@ -574,7 +574,7 @@ class Conv3DTranspose(layers.Layer):
         dilation(int|tuple, optional): The dilation size. If dilation is a tuple, it must
             contain three integers, (dilation_D, dilation_H, dilation_W). Otherwise, the
             dilation_D = dilation_H = dilation_W = dilation. The default value is 1.
-        groups(int, optional): The groups number of the Conv3d transpose layer. Inspired by
+        groups(int, optional): The groups number of the Conv3D transpose layer. Inspired by
             grouped convolution in Alex Krizhevsky's Deep CNN paper, in which
             when group=2, the first half of the filters is only connected to the
             first half of the input channels, while the second half of the
@@ -2541,7 +2541,7 @@ class Conv2DTranspose(layers.Layer):
         dilation(int or tuple, optional): The dilation size. If dilation is a tuple, it must
             contain two integers, (dilation_H, dilation_W). Otherwise, the
             dilation_H = dilation_W = dilation. Default: 1.
-        groups(int, optional): The groups number of the Conv2d transpose layer. Inspired by
+        groups(int, optional): The groups number of the Conv2D transpose layer. Inspired by
             grouped convolution in Alex Krizhevsky's Deep CNN paper, in which
             when group=2, the first half of the filters is only connected to the
             first half of the input channels, while the second half of the

python/paddle/fluid/initializer.py

@@ -749,7 +749,7 @@ class BilinearInitializer(Initializer):
                                       regularizer=L2Decay(0.),
                                       initializer=nn.initializer.Bilinear())
             data = paddle.rand([B, 3, H, W], dtype='float32')
-            conv_up = nn.ConvTranspose2d(3,
+            conv_up = nn.Conv2DTranspose(3,
                                          out_channels=C,
                                          kernel_size=2 * factor - factor % 2,
                                          padding=int(

python/paddle/fluid/nets.py

@@ -43,7 +43,7 @@ def simple_img_conv_pool(input,
                          act=None,
                          use_cudnn=True):
     """
-	:api_attr: Static Graph
+	:api_attr: Static Graph
 
     The simple_img_conv_pool api is composed of :ref:`api_fluid_layers_conv2d` and :ref:`api_fluid_layers_pool2d` .
 
@@ -106,6 +106,8 @@ def simple_img_conv_pool(input,
         .. code-block:: python
 
             import paddle.fluid as fluid
+            import paddle
+            paddle.enable_static()
             img = fluid.data(name='img', shape=[100, 1, 28, 28], dtype='float32')
             conv_pool = fluid.nets.simple_img_conv_pool(input=img,
                                                         filter_size=5,
@@ -151,37 +153,37 @@ def img_conv_group(input,
                    pool_type="max",
                    use_cudnn=True):
     """
-	:api_attr: Static Graph
+	:api_attr: Static Graph
 
     The Image Convolution Group is composed of Convolution2d, BatchNorm, DropOut,
-    and Pool2d. According to the input arguments, img_conv_group will do serials of
+    and Pool2D. According to the input arguments, img_conv_group will do serials of
     computation for Input using Convolution2d, BatchNorm, DropOut, and pass the last
-    result to Pool2d.
+    result to Pool2D.
 
     Args:
         input (Variable): The input is 4-D Tensor with shape [N, C, H, W], the data type of input is float32 or float64.
         conv_num_filter(list|tuple): Indicates the numbers of filter of this group.
-        pool_size (int|list|tuple): The pooling size of Pool2d Layer. If pool_size
+        pool_size (int|list|tuple): The pooling size of Pool2D Layer. If pool_size
             is a list or tuple, it must contain two integers, (pool_size_height, pool_size_width).
             Otherwise, the pool_size_height = pool_size_width = pool_size.
-        conv_padding (int|list|tuple): The padding size of the Conv2d Layer. If padding is
+        conv_padding (int|list|tuple): The padding size of the Conv2D Layer. If padding is
             a list or tuple, its length must be equal to the length of conv_num_filter.
-            Otherwise the conv_padding of all Conv2d Layers are the same. Default 1.
+            Otherwise the conv_padding of all Conv2D Layers are the same. Default 1.
         conv_filter_size (int|list|tuple): The filter size. If filter_size is a list or
             tuple, its length must be equal to the length of conv_num_filter.
-            Otherwise the conv_filter_size of all Conv2d Layers are the same. Default 3.
-        conv_act (str): Activation type for Conv2d Layer that is not followed by BatchNorm.
+            Otherwise the conv_filter_size of all Conv2D Layers are the same. Default 3.
+        conv_act (str): Activation type for Conv2D Layer that is not followed by BatchNorm.
             Default: None.
-        param_attr (ParamAttr): The parameters to the Conv2d Layer. Default: None
-        conv_with_batchnorm (bool|list): Indicates whether to use BatchNorm after Conv2d Layer.
+        param_attr (ParamAttr): The parameters to the Conv2D Layer. Default: None
+        conv_with_batchnorm (bool|list): Indicates whether to use BatchNorm after Conv2D Layer.
             If conv_with_batchnorm is a list, its length must be equal to the length of
             conv_num_filter. Otherwise, conv_with_batchnorm indicates whether all the
-            Conv2d Layer follows a BatchNorm. Default False.
+            Conv2D Layer follows a BatchNorm. Default False.
         conv_batchnorm_drop_rate (float|list): Indicates the drop_rate of Dropout Layer
             after BatchNorm. If conv_batchnorm_drop_rate is a list, its length must be
             equal to the length of conv_num_filter. Otherwise, drop_rate of all Dropout
             Layers is conv_batchnorm_drop_rate. Default 0.0.
-        pool_stride (int|list|tuple): The pooling stride of Pool2d layer. If pool_stride
+        pool_stride (int|list|tuple): The pooling stride of Pool2D layer. If pool_stride
             is a list or tuple, it must contain two integers, (pooling_stride_H,
             pooling_stride_W). Otherwise, the pooling_stride_H = pooling_stride_W = pool_stride.
             Default 1.
@@ -192,12 +194,15 @@ def img_conv_group(input,
 
     Return:
         A Variable holding Tensor representing the final result after serial computation using Convolution2d,
-        BatchNorm, DropOut, and Pool2d, whose data type is the same with input.
+        BatchNorm, DropOut, and Pool2D, whose data type is the same with input.
 
     Examples:
         .. code-block:: python
 
             import paddle.fluid as fluid
+            import paddle
+            paddle.enable_static()
+
             img = fluid.data(name='img', shape=[None, 1, 28, 28], dtype='float32')
             conv_pool = fluid.nets.img_conv_group(input=img,
                                                   conv_padding=1,
@@ -261,7 +266,7 @@ def sequence_conv_pool(input,
                        pool_type="max",
                        bias_attr=None):
     """
-	:api_attr: Static Graph
+	:api_attr: Static Graph
 
     **This api takes input as an LoDTensor. If input is a Tensor, please use** 
     :ref:`api_fluid_nets_simple_img_conv_pool` **instead**
@@ -300,6 +305,8 @@ def sequence_conv_pool(input,
         .. code-block:: python
 
             import paddle.fluid as fluid
+            import paddle
+            paddle.enable_static()
             input_dim = 100 #len(word_dict)
             emb_dim = 128
             hid_dim = 512
@@ -327,7 +334,7 @@ def sequence_conv_pool(input,
 
 def glu(input, dim=-1):
     """
-	:api_attr: Static Graph
+	:api_attr: Static Graph
 
     The Gated Linear Units(GLU) composed by :ref:`api_fluid_layers_split` , 
     :ref:`api_fluid_layers_sigmoid`  and :ref:`api_fluid_layers_elementwise_mul` . 
@@ -356,6 +363,9 @@ def glu(input, dim=-1):
         .. code-block:: python
 
             import paddle.fluid as fluid
+            import paddle
+            paddle.enable_static()
+
             data = fluid.data(
                 name="words", shape=[-1, 6, 3, 9], dtype="float32")
             # shape of output: [-1, 3, 3, 9]
@@ -375,7 +385,7 @@ def scaled_dot_product_attention(queries,
                                  num_heads=1,
                                  dropout_rate=0.):
     """
-	:api_attr: Static Graph
+	:api_attr: Static Graph
 
     This interface Multi-Head Attention using scaled dot product.
     Attention mechanism can be seen as mapping a query and a set of key-value
@@ -435,7 +445,9 @@ def scaled_dot_product_attention(queries,
         .. code-block:: python
 
             import paddle.fluid as fluid
-
+            import paddle
+            paddle.enable_static()
+
             queries = fluid.data(name="queries", shape=[3, 5, 9], dtype="float32")
             keys = fluid.data(name="keys", shape=[3, 6, 9], dtype="float32")
             values = fluid.data(name="values", shape=[3, 6, 10], dtype="float32")

python/paddle/fluid/tests/unittests/dygraph_to_static/test_bmn.py

@@ -564,7 +564,7 @@ def train_bmn(args, place, to_static):
     loss_data = []
 
     with fluid.dygraph.guard(place):
-        paddle.manual_seed(SEED)
+        paddle.seed(SEED)
         paddle.framework.random._manual_program_seed(SEED)
         global local_random
         local_random = np.random.RandomState(SEED)

python/paddle/fluid/tests/unittests/dygraph_to_static/test_lac.py

@@ -450,7 +450,7 @@ def do_train(args, to_static):
     place = fluid.CUDAPlace(0) if fluid.is_compiled_with_cuda(
     ) else fluid.CPUPlace()
     with fluid.dygraph.guard(place):
-        paddle.manual_seed(SEED)
+        paddle.seed(SEED)
         paddle.framework.random._manual_program_seed(SEED)
 
         reader = get_random_input_data(args.batch_size, args.vocab_size,

python/paddle/fluid/tests/unittests/dygraph_to_static/test_mobile_net.py

@@ -451,7 +451,7 @@ def train_mobilenet(args, to_static):
     with fluid.dygraph.guard(args.place):
 
         np.random.seed(SEED)
-        paddle.manual_seed(SEED)
+        paddle.seed(SEED)
         paddle.framework.random._manual_program_seed(SEED)
 
         if args.model == "MobileNetV1":

python/paddle/fluid/tests/unittests/dygraph_to_static/test_ptb_lm.py

@@ -218,7 +218,7 @@ def train(place):
     batch_num = 200
 
     with fluid.dygraph.guard(place):
-        paddle.manual_seed(SEED)
+        paddle.seed(SEED)
         paddle.framework.random._manual_program_seed(SEED)
         ptb_model = PtbModel(
             hidden_size=hidden_size,

python/paddle/fluid/tests/unittests/dygraph_to_static/test_ptb_lm_v2.py

@@ -210,7 +210,7 @@ def train(place):
     batch_num = 200
 
     paddle.disable_static(place)
-    paddle.manual_seed(SEED)
+    paddle.seed(SEED)
     paddle.framework.random._manual_program_seed(SEED)
     ptb_model = PtbModel(
         hidden_size=hidden_size,

python/paddle/fluid/tests/unittests/dygraph_to_static/test_reinforcement_learning.py

@@ -65,7 +65,7 @@ def train(args, place, to_static):
     env.seed(SEED)
 
     with fluid.dygraph.guard(place):
-        paddle.manual_seed(SEED)
+        paddle.seed(SEED)
         paddle.framework.random._manual_program_seed(SEED)
         local_random = np.random.RandomState(SEED)