[Fluid Clean] remove apis in fluid.layers.ops (#47867)

* remove apis in fluid.ops

* fix test_activation_nn_grad

* fix circle import error

* fix ops

* fix cos

* fix divide not inplace

* remove lazy-import part

python/paddle/distributed/fleet/meta_optimizers/localsgd_optimizer.py

@@ -449,8 +449,8 @@ class AdaptiveLocalSGDOptimizer(MetaOptimizerBase):
                 communicate()
                 self._generate_avg_loss(main_block, loss, avg_loss)
                 next_local_steps = layers.cast(
-                    layers.ceil(
-                        layers.sqrt(
+                    paddle.ceil(
+                        paddle.sqrt(
                             lr_0
                             * avg_loss
                             / (global_lr * loss_0)

python/paddle/distributed/fleet/meta_parallel/sharding/group_sharded_utils.py

@@ -68,7 +68,7 @@ class GroupShardedClipGrad:
                 merge_grad = layers.get_tensor_from_selected_rows(
                     layers.merge_selected_rows(g)
                 )
-            square = layers.square(merge_grad)
+            square = paddle.square(merge_grad)
             sum_square = layers.reduce_sum(square)
 
             if p.dtype == paddle.float16:
@@ -133,7 +133,7 @@ class GroupShardedClipGrad:
         with device_guard(dev_id, "gpu"):
             paddle.distributed.all_reduce(global_norm_var, group=self._group)
 
-        global_norm_var = layers.sqrt(global_norm_var)
+        global_norm_var = paddle.sqrt(global_norm_var)
         max_global_norm = layers.fill_constant(
             shape=[1], dtype=global_norm_var.dtype, value=self.clip_norm
         )

python/paddle/distributed/fleet/meta_parallel/sharding/sharding_utils.py

@@ -69,7 +69,7 @@ class ShardingClipGrad:
                 merge_grad = layers.get_tensor_from_selected_rows(
                     layers.merge_selected_rows(g)
                 )
-            square = layers.square(merge_grad)
+            square = paddle.square(merge_grad)
             sum_square = layers.reduce_sum(square)
 
             if p.dtype == paddle.float16:
@@ -131,7 +131,7 @@ class ShardingClipGrad:
         with device_guard(dev_id, "gpu"):
             paddle.distributed.all_reduce(global_norm_var, group=self._group)
 
-        global_norm_var = layers.sqrt(global_norm_var)
+        global_norm_var = paddle.sqrt(global_norm_var)
         max_global_norm = layers.fill_constant(
             shape=[1], dtype=global_norm_var.dtype, value=self.clip_norm
         )

python/paddle/distribution/categorical.py

@@ -17,7 +17,7 @@ import paddle
 from paddle.distribution import distribution
 from paddle.fluid.data_feeder import check_type, convert_dtype
 from paddle.fluid.framework import _non_static_mode
-from paddle.fluid.layers import ops, tensor
+from paddle.fluid.layers import tensor
 from paddle.tensor import multinomial
 
 
@@ -214,8 +214,8 @@ class Categorical(distribution.Distribution):
         other_logits = other.logits - paddle.max(
             other.logits, axis=-1, keepdim=True
         )
-        e_logits = ops.exp(logits)
-        other_e_logits = ops.exp(other_logits)
+        e_logits = paddle.exp(logits)
+        other_e_logits = paddle.exp(other_logits)
         z = paddle.sum(e_logits, axis=-1, keepdim=True)
         other_z = paddle.sum(other_e_logits, axis=-1, keepdim=True)
         prob = e_logits / z
@@ -255,7 +255,7 @@ class Categorical(distribution.Distribution):
         """
         name = self.name + '_entropy'
         logits = self.logits - paddle.max(self.logits, axis=-1, keepdim=True)
-        e_logits = ops.exp(logits)
+        e_logits = paddle.exp(logits)
         z = paddle.sum(e_logits, axis=-1, keepdim=True)
         prob = e_logits / z
 

python/paddle/distribution/normal.py

@@ -23,7 +23,6 @@ from paddle.fluid.layers import (
     elementwise_div,
     elementwise_sub,
     nn,
-    ops,
     tensor,
 )
 
@@ -288,7 +287,7 @@ class Normal(distribution.Distribution):
 
         var = self.scale * self.scale
         return elementwise_div(
-            ops.exp(
+            paddle.exp(
                 -1.0 * ((value - self.loc) * (value - self.loc)) / (2.0 * var)
             ),
             (math.sqrt(2 * math.pi) * self.scale),

python/paddle/fluid/clip.py

@@ -72,7 +72,7 @@ def _squared_l2_norm(x):
         or x.dtype == core.VarDesc.VarType.FP16
         or x.dtype == core.VarDesc.VarType.BF16
     ):
-        square = layers.square(x)
+        square = paddle.square(x)
         sum_square = layers.reduce_sum(square)
         return sum_square
 
@@ -540,7 +540,7 @@ class ClipGradByGlobalNorm(ClipGradBase):
             global_norm_var_fp64 = paddle.add_n(sum_square_list)
             global_norm_var.append(global_norm_var_fp64)
         global_norm_var = paddle.add_n(global_norm_var)
-        global_norm_var = layers.sqrt(global_norm_var)
+        global_norm_var = paddle.sqrt(global_norm_var)
         max_global_norm = layers.fill_constant(
             shape=[1], dtype=global_norm_var.dtype, value=self.clip_norm
         )
@@ -648,7 +648,7 @@ class ClipGradByGlobalNorm(ClipGradBase):
                     if len(global_norm_var) > 1
                     else global_norm_var[0]
                 )
-                global_norm_var = layers.sqrt(x=global_norm_var)
+                global_norm_var = paddle.sqrt(x=global_norm_var)
                 max_global_norm = layers.fill_constant(
                     shape=[1], dtype=global_norm_var.dtype, value=self.clip_norm
                 )
@@ -727,7 +727,7 @@ class ClipGradByGlobalNorm(ClipGradBase):
         group_scale_name = self.group_name + "_scale"
         if group_scale_name not in self.context:
             group_norm_var = layers.sums(input=self.context[self.group_name])
-            group_norm_var = layers.sqrt(x=group_norm_var)
+            group_norm_var = paddle.sqrt(x=group_norm_var)
             clip_var = self.context[self.group_name + "_clip"]
             group_scale_var = layers.elementwise_div(
                 x=clip_var,

python/paddle/fluid/contrib/layers/rnn_impl.py

@@ -14,6 +14,7 @@
 
 import copy
 
+import paddle
 from paddle.fluid import layers, unique_name
 from paddle.fluid.dygraph import Layer
 from paddle.fluid.dygraph.layer_object_helper import LayerObjectHelper
@@ -95,8 +96,8 @@ class BasicGRUUnit(Layer):
         self._hiden_size = hidden_size
         self._param_attr = param_attr
         self._bias_attr = bias_attr
-        self._gate_activation = gate_activation or layers.sigmoid
-        self._activation = activation or layers.tanh
+        self._gate_activation = gate_activation or paddle.nn.functional.sigmoid
+        self._activation = activation or paddle.tanh
         self._dtype = dtype
 
     def _build_once(self, input, pre_hidden):
@@ -845,8 +846,8 @@ class BasicLSTMUnit(Layer):
         self._hiden_size = hidden_size
         self._param_attr = param_attr
         self._bias_attr = bias_attr
-        self._gate_activation = gate_activation or layers.sigmoid
-        self._activation = activation or layers.tanh
+        self._gate_activation = gate_activation or paddle.nn.functional.sigmoid
+        self._activation = activation or paddle.tanh
         self._forget_bias = layers.fill_constant(
             [1], dtype=dtype, value=forget_bias
         )
@@ -879,10 +880,14 @@ class BasicLSTMUnit(Layer):
         new_cell = layers.elementwise_add(
             layers.elementwise_mul(
                 pre_cell,
-                layers.sigmoid(layers.elementwise_add(f, self._forget_bias)),
+                paddle.nn.functional.sigmoid(
+                    layers.elementwise_add(f, self._forget_bias)
+                ),
+            ),
+            layers.elementwise_mul(
+                paddle.nn.functional.sigmoid(i), paddle.tanh(j)
             ),
-            layers.elementwise_mul(layers.sigmoid(i), layers.tanh(j)),
         )
-        new_hidden = layers.tanh(new_cell) * layers.sigmoid(o)
+        new_hidden = paddle.tanh(new_cell) * paddle.nn.functional.sigmoid(o)
 
         return new_hidden, new_cell

python/paddle/fluid/contrib/slim/quantization/adaround.py

@@ -17,6 +17,7 @@ import time
 import sys
 import logging
 
+import paddle
 import paddle.fluid as fluid
 
 from ....log_helper import get_logger
@@ -41,7 +42,9 @@ ZETA = 1.1
 
 def compute_soft_rounding(alpha_v):
     return fluid.layers.clip(
-        fluid.layers.sigmoid(alpha_v) * (ZETA - GAMMA) + GAMMA, min=0, max=1
+        paddle.nn.functional.sigmoid(alpha_v) * (ZETA - GAMMA) + GAMMA,
+        min=0,
+        max=1,
     )
 
 
@@ -73,8 +76,7 @@ class AdaRoundLoss:
             # calculate regularization term - which ensures parameter to converge to exactly zeros and ones
             # at the end of optimization
             reg_term = fluid.layers.reduce_sum(
-                -fluid.layers.pow(fluid.layers.abs(2 * h_v - 1), factor=beta)
-                + 1
+                -fluid.layers.pow(paddle.abs(2 * h_v - 1), factor=beta) + 1
             )
 
             # calculate the rounding loss

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

@@ -82,7 +82,7 @@ def bow_net(
         input=data, is_sparse=is_sparse, size=[dict_dim, emb_dim]
     )
     bow = fluid.layers.sequence_pool(input=emb, pool_type='sum')
-    bow_tanh = fluid.layers.tanh(bow)
+    bow_tanh = paddle.tanh(bow)
     fc_1 = fluid.layers.fc(input=bow_tanh, size=hid_dim, act="tanh")
     fc_2 = fluid.layers.fc(input=fc_1, size=hid_dim2, act="tanh")
     prediction = fluid.layers.fc(input=[fc_2], size=class_dim, act="softmax")

python/paddle/fluid/dygraph/learning_rate_scheduler.py

@@ -270,12 +270,10 @@ class NaturalExpDecay(LearningRateDecay):
         self.staircase = staircase
 
     def step(self):
-        from .. import layers
-
         div_res = self.create_lr_var(self.step_num / self.decay_steps)
         if self.staircase:
-            div_res = layers.floor(div_res)
-        decayed_lr = self.learning_rate * layers.exp(
+            div_res = paddle.floor(div_res)
+        decayed_lr = self.learning_rate * paddle.exp(
             -1 * self.decay_rate * div_res
         )
 
@@ -356,11 +354,9 @@ class ExponentialDecay(LearningRateDecay):
         self.staircase = staircase
 
     def step(self):
-        from .. import layers
-
         div_res = self.create_lr_var(self.step_num / self.decay_steps)
         if self.staircase:
-            div_res = layers.floor(div_res)
+            div_res = paddle.floor(div_res)
 
         decayed_lr = self.learning_rate * (self.decay_rate**div_res)
 
@@ -437,11 +433,9 @@ class InverseTimeDecay(LearningRateDecay):
         self.staircase = staircase
 
     def step(self):
-        from .. import layers
-
         div_res = self.create_lr_var(self.step_num / self.decay_steps)
         if self.staircase:
-            div_res = layers.floor(div_res)
+            div_res = paddle.floor(div_res)
 
         decayed_lr = self.learning_rate / (1 + self.decay_rate * div_res)
 
@@ -524,12 +518,10 @@ class PolynomialDecay(LearningRateDecay):
         self.cycle = cycle
 
     def step(self):
-        from .. import layers
-
         tmp_step_num = self.step_num
         tmp_decay_steps = self.decay_steps
         if self.cycle:
-            div_res = layers.ceil(
+            div_res = paddle.ceil(
                 self.create_lr_var(tmp_step_num / float(self.decay_steps))
             )
 
@@ -601,15 +593,13 @@ class CosineDecay(LearningRateDecay):
         self.epochs = epochs
 
     def step(self):
-        from .. import layers
-
-        cur_epoch = layers.floor(
+        cur_epoch = paddle.floor(
             self.create_lr_var(self.step_num / self.step_each_epoch)
         )
         decayed_lr = (
             self.learning_rate
             * 0.5
-            * (layers.cos(cur_epoch * math.pi / self.epochs) + 1)
+            * (paddle.cos(cur_epoch * math.pi / self.epochs) + 1)
         )
         return decayed_lr
 

python/paddle/fluid/dygraph/rnn.py

@@ -12,10 +12,9 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import paddle
 from . import Layer
 from ..layers import (
-    sigmoid,
-    tanh,
     concat,
     fill_constant,
     matmul,
@@ -139,8 +138,8 @@ class LSTMCell(Layer):
         self._param_attr = param_attr
         self._bias_attr = bias_attr
         self._dtype = dtype
-        self._gate_activation = gate_activation or sigmoid
-        self._activation = activation or tanh
+        self._gate_activation = gate_activation or paddle.nn.functional.sigmoid
+        self._activation = activation or paddle.tanh
         self._use_cudnn_impl = use_cudnn_impl
 
         if self._use_cudnn_impl:
@@ -254,7 +253,9 @@ class LSTMCell(Layer):
                         elementwise_add(f, self._forget_bias)
                     ),
                 ),
-                elementwise_mul(sigmoid(i), tanh(j)),
+                elementwise_mul(
+                    paddle.nn.functional.sigmoid(i), paddle.tanh(j)
+                ),
             )
             new_hidden = self._activation(new_cell) * self._gate_activation(o)
 
@@ -357,8 +358,8 @@ class GRUCell(Layer):
         self._param_attr = param_attr
         self._bias_attr = bias_attr
         self._dtype = dtype
-        self._gate_activation = gate_activation or sigmoid
-        self._activation = activation or tanh
+        self._gate_activation = gate_activation or paddle.nn.functional.sigmoid
+        self._activation = activation or paddle.tanh
         self._use_cudnn_impl = use_cudnn_impl
 
         if self._use_cudnn_impl:

python/paddle/fluid/layers/__init__.py

@@ -12,8 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from . import ops
-from .ops import *
 from . import nn
 from .nn import *
 from . import io
@@ -43,7 +41,6 @@ __all__ += nn.__all__
 __all__ += io.__all__
 __all__ += tensor.__all__
 __all__ += control_flow.__all__
-__all__ += ops.__all__
 __all__ += device.__all__
 __all__ += detection.__all__
 __all__ += metric_op.__all__

python/paddle/fluid/layers/control_flow.py

@@ -14,7 +14,7 @@
 
 from ..wrapped_decorator import signature_safe_contextmanager
 
-from .layer_function_generator import autodoc, templatedoc
+from .layer_function_generator import templatedoc
 from .tensor import assign, cast, fill_constant
 from .. import core
 from ..framework import (

python/paddle/fluid/layers/detection.py

@@ -17,15 +17,13 @@ All layers just related to the detection neural network.
 
 import paddle
 
-from .layer_function_generator import generate_layer_fn
-from .layer_function_generator import autodoc, templatedoc
+from .layer_function_generator import templatedoc
 from ..layer_helper import LayerHelper
 from ..framework import Variable, _non_static_mode, static_only, in_dygraph_mode
 from .. import core
 from .loss import softmax_with_cross_entropy
 from . import tensor
 from . import nn
-from . import ops
 from ..data_feeder import check_variable_and_dtype, check_type, check_dtype
 import math
 import numpy as np

python/paddle/fluid/layers/distributions.py

@@ -14,7 +14,6 @@
 
 from . import control_flow
 from . import tensor
-from . import ops
 from . import nn
 import math
 import numpy as np
@@ -535,8 +534,8 @@ class Categorical(Distribution):
         other_logits = other.logits - nn.reduce_max(
             other.logits, dim=-1, keep_dim=True
         )
-        e_logits = ops.exp(logits)
-        other_e_logits = ops.exp(other_logits)
+        e_logits = paddle.exp(logits)
+        other_e_logits = paddle.exp(other_logits)
         z = nn.reduce_sum(e_logits, dim=-1, keep_dim=True)
         other_z = nn.reduce_sum(other_e_logits, dim=-1, keep_dim=True)
         prob = e_logits / z
@@ -556,7 +555,7 @@ class Categorical(Distribution):
 
         """
         logits = self.logits - nn.reduce_max(self.logits, dim=-1, keep_dim=True)
-        e_logits = ops.exp(logits)
+        e_logits = paddle.exp(logits)
         z = nn.reduce_sum(e_logits, dim=-1, keep_dim=True)
         prob = e_logits / z
         entropy = -1.0 * nn.reduce_sum(

python/paddle/fluid/layers/io.py

@@ -19,7 +19,6 @@ import threading
 
 from ..data_feeder import DataFeeder
 from .control_flow import BlockGuard
-from .layer_function_generator import templatedoc
 from .. import core
 from ..executor import global_scope
 from ..framework import (

python/paddle/fluid/layers/layer_function_generator.py

@@ -45,14 +45,11 @@ __all__ = [
 def _convert_(name):
     """
     Formatting.
-
     Args:
        name: The name/alias
-
     This function takes in a name and converts it to a standard format of
     group1_group2. Where as per the regular expression, group1 can have
     alphabets and numbers and group2 has capital alphabets.
-
     """
     s1 = re.sub('(.)([A-Z][a-z]+)', r'\1_\2', name)
     return re.sub('([a-z0-9])([A-Z])', r'\1_\2', s1).lower()
@@ -80,10 +77,8 @@ def _generate_doc_string_(
 ):
     """
     Generate docstring by OpProto
-
     Args:
         op_proto (framework_pb2.OpProto): a protobuf message typed OpProto
-
     Returns:
         str: the document string
     """
@@ -148,13 +143,10 @@ def _generate_doc_string_(
 
 def generate_layer_fn(op_type):
     """Register the Python layer for an Operator.
-
     Args:
        op_type: The name of the operator to be created.
-
     This function takes in the operator type (sigmoid, mean , average etc) and
     creates the operator functionality.
-
     """
     op_proto = OpProtoHolder.instance().get_op_proto(op_type)
     not_intermediate_outputs = [
@@ -271,13 +263,10 @@ def generate_layer_fn(op_type):
 
 def generate_activation_fn(op_type):
     """Register the Python layer for an Operator without Attribute.
-
     Args:
        op_type: The name of the operator to be created.
-
     This function takes in the operator type (sigmoid, exp , tanh etc) and
     creates the operator functionality.
-
     """
     op_proto = OpProtoHolder.instance().get_op_proto(op_type)
 
@@ -330,10 +319,8 @@ def generate_activation_fn(op_type):
 
 def generate_inplace_fn(inplace_op_type):
     """Register the Python layer for an Inplace Operator without Attribute.
-
     Args:
        inplace_op_type: The name of the inplace operator to be created.
-
     This function takes in the inplace operator type (exp_ , ceil_ etc) and
     creates the operator functionality.
     """
@@ -378,12 +365,10 @@ def templatedoc(op_type=None):
     """
     Decorator of layer function. It will use the docstring from the layer
     function as the template. The template arguments are:
-
     * ${comment}: The operator comment written in CPP.
     * ${{name}_comment}: The comment of ${name} written with AddAttr, AddOutput,
         and AddInput. The ${name} is Python snake style. i.e., xxx_xxx.
     * ${{name}_type}: The type of ${name}.
-
     Returns:
         Decorated function.
     """
@@ -438,7 +423,6 @@ def templatedoc(op_type=None):
 def add_sample_code(func, sample_code):
     """
     Append sample code for dynamically generated functions.
-
     Args:
        func: The function of the function to be append sample code to.
        sample_code: sample code session in rst format.

python/paddle/fluid/layers/learning_rate_scheduler.py

@@ -26,7 +26,6 @@ import numbers
 import paddle
 from . import control_flow
 from . import nn
-from . import ops
 from . import tensor
 from ..framework import default_main_program, Parameter, unique_name, name_scope
 from ..framework import Variable
@@ -171,7 +170,7 @@ def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False):
 
             div_res = global_step / decay_steps
             if staircase:
-                div_res = ops.floor(div_res)
+                div_res = paddle.floor(div_res)
             decayed_lr = learning_rate * (decay_rate**div_res)
 
             return decayed_lr
@@ -233,8 +232,8 @@ def natural_exp_decay(learning_rate, decay_steps, decay_rate, staircase=False):
 
             div_res = global_step / decay_steps
             if staircase:
-                div_res = ops.floor(div_res)
-            decayed_lr = learning_rate * ops.exp(-1 * decay_rate * div_res)
+                div_res = paddle.floor(div_res)
+            decayed_lr = learning_rate * paddle.exp(-1 * decay_rate * div_res)
 
             return decayed_lr
 
@@ -293,7 +292,7 @@ def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False):
 
             div_res = global_step / decay_steps
             if staircase:
-                div_res = ops.floor(div_res)
+                div_res = paddle.floor(div_res)
 
             decayed_lr = learning_rate / (1 + decay_rate * div_res)
 
@@ -347,7 +346,7 @@ def polynomial_decay(
             global_step = _decay_step_counter()
 
             if cycle:
-                div_res = ops.ceil(global_step / decay_steps)
+                div_res = paddle.ceil(global_step / decay_steps)
                 zero_var = tensor.fill_constant(
                     shape=[1], dtype='float32', value=0.0
                 )
@@ -497,11 +496,11 @@ def cosine_decay(learning_rate, step_each_epoch, epochs):
         else:
             global_step = _decay_step_counter()
 
-            cur_epoch = ops.floor(global_step / step_each_epoch)
+            cur_epoch = paddle.floor(global_step / step_each_epoch)
             decayed_lr = (
                 learning_rate
                 * 0.5
-                * (ops.cos(cur_epoch * math.pi / epochs) + 1)
+                * (paddle.cos(cur_epoch * math.pi / epochs) + 1)
             )
             return decayed_lr
 

python/paddle/fluid/layers/loss.py

@@ -1737,7 +1737,6 @@ def kldiv_loss(x, target, reduction='mean', name=None):
     return loss
 
 
-from .ops import square
 from .control_flow import equal
 
 

python/paddle/fluid/nets.py

@@ -12,6 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import paddle
 from . import layers
 from .data_feeder import check_variable_and_dtype, convert_dtype
 from ..utils import deprecated
@@ -387,7 +388,7 @@ def glu(input, dim=-1):
         input, 'input', ['float16', 'float32', 'float64'], "glu"
     )
     a, b = layers.split(input, num_or_sections=2, dim=dim)
-    act_b = layers.sigmoid(x=b)
+    act_b = paddle.nn.functional.sigmoid(x=b)
     out = layers.elementwise_mul(x=a, y=act_b)
     return out
 

python/paddle/fluid/optimizer.py

@@ -48,7 +48,6 @@ from .clip import (
 from .framework import program_guard
 from .initializer import Constant
 from .layer_helper import LayerHelper
-from .layers import ops
 from .dygraph import base as imperative_base
 from .dygraph import no_grad
 from .dygraph.learning_rate_scheduler import (
@@ -4457,7 +4456,7 @@ class ModelAverage(Optimizer):
         sum = layers.cast(
             x=sum, dtype='float32' if self._dtype is None else self._dtype
         )
-        ops._elementwise_div(x=sum, y=tmp, out=param)
+        paddle.assign(paddle.divide(sum, tmp), output=param)
 
     def _add_average_restore_op(self, block, param_grad):
         param = block._clone_variable(param_grad[0])

python/paddle/fluid/tests/book/notest_understand_sentiment.py

@@ -70,21 +70,21 @@ def dyn_rnn_lstm(
             gate1 = fluid.layers.fc(input=hidden, size=size, bias_attr=False)
             return gate0 + gate1
 
-        forget_gate = fluid.layers.sigmoid(
+        forget_gate = paddle.nn.functional.sigmoid(
             x=gate_common(word, prev_hidden, lstm_size)
         )
-        input_gate = fluid.layers.sigmoid(
+        input_gate = paddle.nn.functional.sigmoid(
             x=gate_common(word, prev_hidden, lstm_size)
         )
-        output_gate = fluid.layers.sigmoid(
+        output_gate = paddle.nn.functional.sigmoid(
             x=gate_common(word, prev_hidden, lstm_size)
         )
-        cell_gate = fluid.layers.sigmoid(
+        cell_gate = paddle.nn.functional.sigmoid(
             x=gate_common(word, prev_hidden, lstm_size)
         )
 
         cell = forget_gate * prev_cell + input_gate * cell_gate
-        hidden = output_gate * fluid.layers.tanh(x=cell)
+        hidden = output_gate * paddle.tanh(x=cell)
         rnn.update_memory(prev_cell, cell)
         rnn.update_memory(prev_hidden, hidden)
         rnn.output(hidden)

python/paddle/fluid/tests/book/test_rnn_encoder_decoder.py

@@ -70,10 +70,10 @@ def lstm_step(x_t, hidden_t_prev, cell_t_prev, size):
     def linear(inputs):
         return fluid.layers.fc(input=inputs, size=size, bias_attr=True)
 
-    forget_gate = fluid.layers.sigmoid(x=linear([hidden_t_prev, x_t]))
-    input_gate = fluid.layers.sigmoid(x=linear([hidden_t_prev, x_t]))
-    output_gate = fluid.layers.sigmoid(x=linear([hidden_t_prev, x_t]))
-    cell_tilde = fluid.layers.tanh(x=linear([hidden_t_prev, x_t]))
+    forget_gate = paddle.nn.functional.sigmoid(x=linear([hidden_t_prev, x_t]))
+    input_gate = paddle.nn.functional.sigmoid(x=linear([hidden_t_prev, x_t]))
+    output_gate = paddle.nn.functional.sigmoid(x=linear([hidden_t_prev, x_t]))
+    cell_tilde = paddle.tanh(x=linear([hidden_t_prev, x_t]))
 
     cell_t = fluid.layers.sums(
         input=[
@@ -83,7 +83,7 @@ def lstm_step(x_t, hidden_t_prev, cell_t_prev, size):
     )
 
     hidden_t = fluid.layers.elementwise_mul(
-        x=output_gate, y=fluid.layers.tanh(x=cell_t)
+        x=output_gate, y=paddle.tanh(x=cell_t)
     )
 
     return hidden_t, cell_t

python/paddle/fluid/tests/test_if_else_op.py

@@ -175,12 +175,12 @@ class TestIfElse(unittest.TestCase):
             ie = layers.IfElse(ifcond)
             with ie.true_block():
                 true_target = ie.input(src)
-                true_target = fluid.layers.exp(true_target)
+                true_target = paddle.exp(true_target)
                 ie.output(true_target)
 
             with ie.false_block():
                 false_target = ie.input(src)
-                false_target = fluid.layers.tanh(false_target)
+                false_target = paddle.tanh(false_target)
                 ie.output(false_target)
             if_out = ie()
             out = layers.reduce_sum(if_out[0])
@@ -244,7 +244,7 @@ class TestIfElseError(unittest.TestCase):
                 ie = layers.IfElse(ifcond)
                 with ie.true_block():
                     true_target = ie.input(src)
-                    true_target = fluid.layers.exp(true_target)
+                    true_target = paddle.exp(true_target)
                     ie.output([])
 
 

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

@@ -130,7 +130,7 @@ def train_network(
     q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
     # vsum
     q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-    q_ss = fluid.layers.softsign(q_sum)
+    q_ss = paddle.nn.functional.softsign(q_sum)
     # fc layer after conv
     q_fc = fluid.layers.fc(
         input=q_ss,
@@ -157,7 +157,7 @@ def train_network(
     pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
     # vsum
     pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-    pt_ss = fluid.layers.softsign(pt_sum)
+    pt_ss = paddle.nn.functional.softsign(pt_sum)
     # fc layer
     pt_fc = fluid.layers.fc(
         input=pt_ss,
@@ -181,7 +181,7 @@ def train_network(
     nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
     # vsum
     nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-    nt_ss = fluid.layers.softsign(nt_sum)
+    nt_ss = paddle.nn.functional.softsign(nt_sum)
     # fc layer
     nt_fc = fluid.layers.fc(
         input=nt_ss,

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

@@ -61,7 +61,7 @@ def dyfunc_with_if_else2(x, col=100):
         y = fluid.layers.relu(x)
     else:
         x_pow = fluid.layers.pow(x, 2)
-        y = fluid.layers.tanh(x_pow)
+        y = paddle.tanh(x_pow)
     return y
 
 
@@ -161,7 +161,7 @@ def nested_if_else(x_v):
             tmp = y * w
             y = fluid.layers.relu(tmp)
             if paddle.mean(y).numpy()[0] < batch_size:
-                y = fluid.layers.abs(y)
+                y = paddle.abs(y)
             else:
                 tmp = fluid.layers.fill_constant(
                     y.shape, dtype='float32', value=-1
@@ -276,7 +276,7 @@ class NetWithControlFlowIf(fluid.dygraph.Layer):
                     self.constant_vars['w'] = fluid.layers.fill_constant(
                         [hidden_dim], dtype='float32', value=9
                     )
-                    y = fluid.layers.abs(y)
+                    y = paddle.abs(y)
                 else:
                     tmp = fluid.layers.fill_constant(
                         y.shape, dtype='float32', value=-1

python/paddle/fluid/tests/unittests/dygraph_to_static/seq2seq_dygraph_model.py

@@ -49,8 +49,8 @@ class BasicLSTMUnit(Layer):
         self._hiden_size = hidden_size
         self._param_attr = param_attr
         self._bias_attr = bias_attr
-        self._gate_activation = gate_activation or layers.sigmoid
-        self._activation = activation or layers.tanh
+        self._gate_activation = gate_activation or paddle.nn.functional.sigmoid
+        self._activation = activation or paddle.tanh
         self._forget_bias = forget_bias
         self._dtype = dtype
         self._input_size = input_size
@@ -76,12 +76,14 @@ class BasicLSTMUnit(Layer):
         i, j, f, o = layers.split(gate_input, num_or_sections=4, dim=-1)
         new_cell = layers.elementwise_add(
             layers.elementwise_mul(
-                pre_cell, layers.sigmoid(f + self._forget_bias)
+                pre_cell, paddle.nn.functional.sigmoid(f + self._forget_bias)
+            ),
+            layers.elementwise_mul(
+                paddle.nn.functional.sigmoid(i), paddle.tanh(j)
             ),
-            layers.elementwise_mul(layers.sigmoid(i), layers.tanh(j)),
         )
 
-        new_hidden = layers.tanh(new_cell) * layers.sigmoid(o)
+        new_hidden = paddle.tanh(new_cell) * paddle.nn.functional.sigmoid(o)
 
         return new_hidden, new_cell
 

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

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 import paddle
-
 import paddle.fluid as fluid
 import paddle.fluid.param_attr as attr
 
@@ -232,7 +231,7 @@ class SoftsignLayer:
         """
         operation
         """
-        softsign = fluid.layers.softsign(input)
+        softsign = paddle.nn.functional.softsign(input)
         return softsign
 
 

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

@@ -89,28 +89,22 @@ class Cycle_Gan(fluid.dygraph.Layer):
         cyc_A = self.build_generator_resnet_9blocks_b(fake_B)
         cyc_B = self.build_generator_resnet_9blocks_a(fake_A)
 
-        diff_A = fluid.layers.abs(
-            fluid.layers.elementwise_sub(x=input_A, y=cyc_A)
-        )
-        diff_B = fluid.layers.abs(
-            fluid.layers.elementwise_sub(x=input_B, y=cyc_B)
-        )
+        diff_A = paddle.abs(fluid.layers.elementwise_sub(x=input_A, y=cyc_A))
+        diff_B = paddle.abs(fluid.layers.elementwise_sub(x=input_B, y=cyc_B))
         cyc_A_loss = fluid.layers.reduce_mean(diff_A) * lambda_A
         cyc_B_loss = fluid.layers.reduce_mean(diff_B) * lambda_B
         cyc_loss = cyc_A_loss + cyc_B_loss
 
         fake_rec_A = self.build_gen_discriminator_a(fake_B)
-        g_A_loss = fluid.layers.reduce_mean(fluid.layers.square(fake_rec_A - 1))
+        g_A_loss = paddle.mean(paddle.square(fake_rec_A - 1))
 
         fake_rec_B = self.build_gen_discriminator_b(fake_A)
-        g_B_loss = fluid.layers.reduce_mean(fluid.layers.square(fake_rec_B - 1))
+        g_B_loss = paddle.mean(paddle.square(fake_rec_B - 1))
         G = g_A_loss + g_B_loss
         idt_A = self.build_generator_resnet_9blocks_a(input_B)
         idt_loss_A = (
             fluid.layers.reduce_mean(
-                fluid.layers.abs(
-                    fluid.layers.elementwise_sub(x=input_B, y=idt_A)
-                )
+                paddle.abs(fluid.layers.elementwise_sub(x=input_B, y=idt_A))
             )
             * lambda_B
             * lambda_identity
@@ -119,9 +113,7 @@ class Cycle_Gan(fluid.dygraph.Layer):
         idt_B = self.build_generator_resnet_9blocks_b(input_A)
         idt_loss_B = (
             fluid.layers.reduce_mean(
-                fluid.layers.abs(
-                    fluid.layers.elementwise_sub(x=input_A, y=idt_B)
-                )
+                paddle.abs(fluid.layers.elementwise_sub(x=input_A, y=idt_B))
             )
             * lambda_A
             * lambda_identity
@@ -271,7 +263,7 @@ class build_generator_resnet_9blocks(fluid.dygraph.Layer):
         y = self.deconv1(y)
         y = fluid.layers.pad2d(y, [3, 3, 3, 3], mode="reflect")
         y = self.conv3(y)
-        y = fluid.layers.tanh(y)
+        y = paddle.tanh(y)
         return y
 
 
@@ -647,8 +639,7 @@ def train(args, to_static):
                     data_B, fake_pool_B
                 )
                 d_loss_A = (
-                    fluid.layers.square(fake_pool_rec_B)
-                    + fluid.layers.square(rec_B - 1)
+                    paddle.square(fake_pool_rec_B) + paddle.square(rec_B - 1)
                 ) / 2.0
                 d_loss_A = fluid.layers.reduce_mean(d_loss_A)
 
@@ -661,8 +652,7 @@ def train(args, to_static):
                     data_A, fake_pool_A
                 )
                 d_loss_B = (
-                    fluid.layers.square(fake_pool_rec_A)
-                    + fluid.layers.square(rec_A - 1)
+                    paddle.square(fake_pool_rec_A) + paddle.square(rec_A - 1)
                 ) / 2.0
                 d_loss_B = fluid.layers.reduce_mean(d_loss_B)
 

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

@@ -99,10 +99,10 @@ class SimpleLSTMRNN(fluid.Layer):
                 i, j, f, o = fluid.layers.split(
                     gate_input, num_or_sections=4, dim=-1
                 )
-                c = pre_cell * fluid.layers.sigmoid(f) + fluid.layers.sigmoid(
-                    i
-                ) * fluid.layers.tanh(j)
-                m = fluid.layers.tanh(c) * fluid.layers.sigmoid(o)
+                c = pre_cell * paddle.nn.functional.sigmoid(
+                    f
+                ) + paddle.nn.functional.sigmoid(i) * paddle.tanh(j)
+                m = paddle.tanh(c) * paddle.nn.functional.sigmoid(o)
                 hidden_array[k] = m
                 cell_array[k] = c
                 step_input = m

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

@@ -145,7 +145,7 @@ class BOW(fluid.dygraph.Layer):
         emb = emb * mask_emb
         emb = fluid.layers.reshape(emb, shape=[-1, self.seq_len, self.hid_dim])
         bow_1 = fluid.layers.reduce_sum(emb, dim=1)
-        bow_1 = fluid.layers.tanh(bow_1)
+        bow_1 = paddle.tanh(bow_1)
         fc_1 = self._fc1(bow_1)
         fc_2 = self._fc2(fc_1)
         prediction = self._fc_prediction(fc_2)
@@ -197,7 +197,7 @@ class GRU(fluid.dygraph.Layer):
         fc_1 = self._fc1(emb)
         gru_hidden = self._gru(fc_1)
         gru_hidden = fluid.layers.reduce_max(gru_hidden, dim=1)
-        tanh_1 = fluid.layers.tanh(gru_hidden)
+        tanh_1 = paddle.tanh(gru_hidden)
         fc_2 = self._fc2(tanh_1)
         prediction = self._fc_prediction(fc_2)
 
@@ -253,8 +253,8 @@ class BiGRU(fluid.dygraph.Layer):
         fc_1 = self._fc1(emb)
         gru_forward = self._gru_forward(fc_1)
         gru_backward = self._gru_backward(fc_1)
-        gru_forward_tanh = fluid.layers.tanh(gru_forward)
-        gru_backward_tanh = fluid.layers.tanh(gru_backward)
+        gru_forward_tanh = paddle.tanh(gru_forward)
+        gru_backward_tanh = paddle.tanh(gru_backward)
         encoded_vector = fluid.layers.concat(
             input=[gru_forward_tanh, gru_backward_tanh], axis=2
         )

python/paddle/fluid/tests/unittests/dygraph_to_static/test_word2vec.py

@@ -18,6 +18,7 @@ import numpy as np
 import paddle.fluid as fluid
 import unittest
 
+import paddle
 from paddle.fluid.dygraph.nn import Embedding
 from paddle.fluid.dygraph import ProgramTranslator
 from paddle.fluid.dygraph import declarative
@@ -260,7 +261,7 @@ class SkipGram(fluid.dygraph.Layer):
         )
         word_sim = fluid.layers.reduce_sum(word_sim, dim=-1)
 
-        pred = fluid.layers.sigmoid(word_sim)
+        pred = paddle.nn.functional.sigmoid(word_sim)
 
         loss = fluid.layers.sigmoid_cross_entropy_with_logits(word_sim, label)
         loss = fluid.layers.reduce_mean(loss)

python/paddle/fluid/tests/unittests/ipu/test_cumsum_op_ipu.py

@@ -51,7 +51,7 @@ class TestBase(IPUOpTest):
         x = paddle.static.data(
             name=self.feed_list[0], shape=self.feed_shape[0], dtype="float32"
         )
-        out = paddle.fluid.layers.cumsum(x, **self.attrs)
+        out = paddle.cumsum(x, **self.attrs)
         self.fetch_list = [out.name]
 
     def run_model(self, exec_mode):
@@ -90,7 +90,7 @@ class TestCase4(TestBase):
         x = paddle.static.data(
             name=self.feed_list[0], shape=self.feed_shape[0], dtype="int32"
         )
-        out = paddle.fluid.layers.cumsum(x, **self.attrs)
+        out = paddle.cumsum(x, **self.attrs)
         self.fetch_list = [out.name]
 
 
@@ -104,7 +104,7 @@ class TestCase5(TestBase):
         x = paddle.static.data(
             name=self.feed_list[0], shape=self.feed_shape[0], dtype="int64"
         )
-        out = paddle.fluid.layers.cumsum(x, **self.attrs)
+        out = paddle.cumsum(x, **self.attrs)
         self.fetch_list = [out.name]
 
 

python/paddle/fluid/tests/unittests/ipu/test_gelu_op_ipu.py

@@ -45,7 +45,7 @@ class TestBase(IPUOpTest):
         x = paddle.static.data(
             name=self.feed_list[0], shape=self.feed_shape[0], dtype='float32'
         )
-        out = paddle.fluid.layers.gelu(x, **self.attrs)
+        out = paddle.nn.functional.gelu(x, **self.attrs)
         self.fetch_list = [out.name]
 
     def run_model(self, exec_mode):

python/paddle/fluid/tests/unittests/ipu/test_unary_ops_ipu.py

@@ -29,7 +29,7 @@ class TestBase(IPUOpTest):
         self.set_feed_attr()
 
     def set_test_op(self):
-        self.op = paddle.fluid.layers.abs
+        self.op = paddle.abs
         self.op_attrs = {}
 
     def set_data_feed(self):
@@ -70,55 +70,55 @@ class TestAcos(TestBase):
         self.atol = 1e-6
 
     def set_test_op(self):
-        self.op = paddle.fluid.layers.acos
+        self.op = paddle.acos
         self.op_attrs = {}
 
 
 class TestAsin(TestAcos):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.asin
+        self.op = paddle.asin
         self.op_attrs = {}
 
 
 class TestSinh(TestAcos):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.sinh
+        self.op = paddle.sinh
         self.op_attrs = {}
 
 
 class TestAtan(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.atan
+        self.op = paddle.atan
         self.op_attrs = {}
 
 
 class TestCeil(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.ceil
+        self.op = paddle.ceil
         self.op_attrs = {}
 
 
 class TestCos(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.cos
+        self.op = paddle.cos
         self.op_attrs = {}
 
 
 class TestCosh(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.cosh
+        self.op = paddle.cosh
         self.op_attrs = {}
 
 
 class TestErf(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.erf
+        self.op = paddle.erf
         self.op_attrs = {}
 
 
 class TestExp(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.exp
+        self.op = paddle.exp
         self.op_attrs = {}
 
 
@@ -128,19 +128,19 @@ class TestFloor(TestBase):
         return False
 
     def set_test_op(self):
-        self.op = paddle.fluid.layers.floor
+        self.op = paddle.floor
         self.op_attrs = {}
 
 
 class TestLog(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.log
+        self.op = paddle.log
         self.op_attrs = {}
 
 
 class TestReciprocal(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.reciprocal
+        self.op = paddle.reciprocal
         self.op_attrs = {}
 
 
@@ -152,55 +152,55 @@ class TestRelu(TestBase):
 
 class TestRound(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.round
+        self.op = paddle.round
         self.op_attrs = {}
 
 
 class TestSigmoid(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.sigmoid
+        self.op = paddle.nn.functional.sigmoid
         self.op_attrs = {}
 
 
 class TestSign(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.sign
+        self.op = paddle.sign
         self.op_attrs = {}
 
 
 class TestSin(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.sin
+        self.op = paddle.sin
         self.op_attrs = {}
 
 
 class TestSoftplus(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.softplus
+        self.op = paddle.nn.functional.softplus
         self.op_attrs = {}
 
 
 class TestSoftsign(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.softsign
+        self.op = paddle.nn.functional.softsign
         self.op_attrs = {}
 
 
 class TestSqrt(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.sqrt
+        self.op = paddle.sqrt
         self.op_attrs = {}
 
 
 class TestTan(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.tan
+        self.op = paddle.tan
         self.op_attrs = {}
 
 
 class TestTanh(TestBase):
     def set_test_op(self):
-        self.op = paddle.fluid.layers.tanh
+        self.op = paddle.tanh
         self.op_attrs = {}
 
 

python/paddle/fluid/tests/unittests/ir/inference/test_mkldnn_elt_act_fuse_pass.py

@@ -75,7 +75,7 @@ class ElementwiseActivationMkldnnFusePassTest_Add_Tanh(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_add
-        self.act = fluid.layers.tanh
+        self.act = paddle.tanh
 
 
 class ElementwiseActivationMkldnnFusePassTest_Add_LeakyRelu(
@@ -108,7 +108,7 @@ class ElementwiseActivationMkldnnFusePassTest_Add_SQRT(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_add
-        self.act = fluid.layers.sqrt
+        self.act = paddle.sqrt
 
 
 class ElementwiseActivationMkldnnFusePassTest_Add_ABS(
@@ -116,7 +116,7 @@ class ElementwiseActivationMkldnnFusePassTest_Add_ABS(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_add
-        self.act = fluid.layers.abs
+        self.act = paddle.abs
 
 
 class ElementwiseActivationMkldnnFusePassTest_Add_Clip(
@@ -134,7 +134,7 @@ class ElementwiseActivationMkldnnFusePassTest_Add_Gelu(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_add
-        self.act = fluid.layers.gelu
+        self.act = paddle.nn.functional.gelu
 
 
 class ElementwiseActivationMkldnnFusePassTest_Add_Gelu_Tanh(
@@ -142,7 +142,7 @@ class ElementwiseActivationMkldnnFusePassTest_Add_Gelu_Tanh(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_add
-        self.act = fluid.layers.gelu
+        self.act = paddle.nn.functional.gelu
         self.act_alpha = True
 
 
@@ -159,7 +159,7 @@ class ElementwiseActivationMkldnnFusePassTest_Add_Sigmoid(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_add
-        self.act = fluid.layers.sigmoid
+        self.act = paddle.nn.functional.sigmoid
 
 
 class ElementwiseActivationMkldnnFusePassTest_Sub_Relu(
@@ -175,7 +175,7 @@ class ElementwiseActivationMkldnnFusePassTest_Sub_Tanh(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_sub
-        self.act = fluid.layers.tanh
+        self.act = paddle.tanh
 
 
 class ElementwiseActivationMkldnnFusePassTest_Sub_LeakyRelu(
@@ -208,7 +208,7 @@ class ElementwiseActivationMkldnnFusePassTest_Sub_ABS(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_sub
-        self.act = fluid.layers.abs
+        self.act = paddle.abs
 
 
 class ElementwiseActivationMkldnnFusePassTest_Sub_Clip(
@@ -226,7 +226,7 @@ class ElementwiseActivationMkldnnFusePassTest_Sub_Gelu(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_sub
-        self.act = fluid.layers.gelu
+        self.act = paddle.nn.functional.gelu
 
 
 class ElementwiseActivationMkldnnFusePassTest_Sub_Gelu_Tanh(
@@ -234,7 +234,7 @@ class ElementwiseActivationMkldnnFusePassTest_Sub_Gelu_Tanh(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_sub
-        self.act = fluid.layers.gelu
+        self.act = paddle.nn.functional.gelu
         self.act_alpha = True
 
 
@@ -251,7 +251,7 @@ class ElementwiseActivationMkldnnFusePassTest_Sub_Sigmoid(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_sub
-        self.act = fluid.layers.sigmoid
+        self.act = paddle.nn.functional.sigmoid
 
 
 class ElementwiseActivationMkldnnFusePassTest_Mul_Relu(
@@ -267,7 +267,7 @@ class ElementwiseActivationMkldnnFusePassTest_Mul_Tanh(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_mul
-        self.act = fluid.layers.tanh
+        self.act = paddle.tanh
 
 
 class ElementwiseActivationMkldnnFusePassTest_Mul_LeakyRelu(
@@ -300,7 +300,7 @@ class ElementwiseActivationMkldnnFusePassTest_Mul_SQRT(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_mul
-        self.act = fluid.layers.sqrt
+        self.act = paddle.sqrt
 
 
 class ElementwiseActivationMkldnnFusePassTest_Mul_ABS(
@@ -308,7 +308,7 @@ class ElementwiseActivationMkldnnFusePassTest_Mul_ABS(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_mul
-        self.act = fluid.layers.abs
+        self.act = paddle.abs
 
 
 class ElementwiseActivationMkldnnFusePassTest_Mul_Clip(
@@ -326,7 +326,7 @@ class ElementwiseActivationMkldnnFusePassTest_Mul_Gelu(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_mul
-        self.act = fluid.layers.gelu
+        self.act = paddle.nn.functional.gelu
 
 
 class ElementwiseActivationMkldnnFusePassTest_Mul_Gelu_Tanh(
@@ -334,7 +334,7 @@ class ElementwiseActivationMkldnnFusePassTest_Mul_Gelu_Tanh(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_mul
-        self.act = fluid.layers.gelu
+        self.act = paddle.nn.functional.gelu
         self.act_alpha = True
 
 
@@ -351,7 +351,7 @@ class ElementwiseActivationMkldnnFusePassTest_Mul_Sigmoid(
 ):
     def set_params(self):
         self.operand = fluid.layers.elementwise_mul
-        self.act = fluid.layers.sigmoid
+        self.act = paddle.nn.functional.sigmoid
 
 
 if __name__ == "__main__":

python/paddle/fluid/tests/unittests/ir/inference/test_trt_activation_pass.py

@@ -17,6 +17,7 @@ import shutil
 import unittest
 import numpy as np
 from inference_pass_test import InferencePassTest
+import paddle
 import paddle.fluid as fluid
 import paddle.fluid.core as core
 from paddle.fluid.core import PassVersionChecker
@@ -81,7 +82,7 @@ class TensorRTSubgraphPassSoftMaxTest(TensorRTSubgraphPassActivationTest):
 
 class TensorRTSubgraphPassSigmoidTest(TensorRTSubgraphPassActivationTest):
     def append_act(self, x):
-        return fluid.layers.sigmoid(x)
+        return paddle.nn.functional.sigmoid(x)
 
 
 class TensorRTSubgraphPassHardSwishTest(TensorRTSubgraphPassActivationTest):
@@ -108,7 +109,7 @@ class TensorRTSubgraphPassClipTest(TensorRTSubgraphPassActivationTest):
 
 class TensorRTSubgraphPassTanhTest(TensorRTSubgraphPassActivationTest):
     def append_act(self, x):
-        return fluid.layers.tanh(x)
+        return paddle.tanh(x)
 
 
 class TensorRTSubgraphPassSwishTest(TensorRTSubgraphPassActivationTest):
@@ -303,7 +304,7 @@ class TensorRTSubgraphPassPreluFp16DynamicSerializeTest(
 
 class TensorRTSubgraphPassGeluTest(TensorRTSubgraphPassActivationTest):
     def append_act(self, x):
-        return fluid.layers.gelu(x)
+        return paddle.nn.functional.gelu(x)
 
 
 class TensorRTSubgraphPassGeluDynamicTest(TensorRTSubgraphPassActivationTest):
@@ -322,7 +323,7 @@ class TensorRTSubgraphPassGeluDynamicTest(TensorRTSubgraphPassActivationTest):
         )
 
     def append_act(self, x):
-        return fluid.layers.gelu(x)
+        return paddle.nn.functional.gelu(x)
 
 
 class TensorRTSubgraphPassGeluFp16Test(TensorRTSubgraphPassActivationTest):
@@ -333,7 +334,7 @@ class TensorRTSubgraphPassGeluFp16Test(TensorRTSubgraphPassActivationTest):
         )
 
     def append_act(self, x):
-        return fluid.layers.gelu(x)
+        return paddle.nn.functional.gelu(x)
 
 
 class TensorRTSubgraphPassGeluFp16SerializeTest(
@@ -346,7 +347,7 @@ class TensorRTSubgraphPassGeluFp16SerializeTest(
         )
 
     def append_act(self, x):
-        return fluid.layers.gelu(x)
+        return paddle.nn.functional.gelu(x)
 
 
 class TensorRTSubgraphPassGeluFp16DynamicTest(
@@ -367,7 +368,7 @@ class TensorRTSubgraphPassGeluFp16DynamicTest(
         )
 
     def append_act(self, x):
-        return fluid.layers.gelu(x)
+        return paddle.nn.functional.gelu(x)
 
 
 class TensorRTSubgraphPassGeluFp16DynamicSerializeTest(
@@ -388,7 +389,7 @@ class TensorRTSubgraphPassGeluFp16DynamicSerializeTest(
         )
 
     def append_act(self, x):
-        return fluid.layers.gelu(x)
+        return paddle.nn.functional.gelu(x)
 
 
 if __name__ == "__main__":

python/paddle/fluid/tests/unittests/ir/test_ir_fusion_group_pass.py

@@ -15,6 +15,7 @@
 import unittest
 
 import numpy as np
+import paddle
 from pass_test import PassTest
 import paddle.fluid as fluid
 import paddle.fluid.layers as layers
@@ -85,10 +86,14 @@ class FusionGroupPassComplicatedTest(FusionGroupPassTest):
             one = layers.fill_constant(shape=[1], dtype=dtype, value=1.0)
             tmp_0 = one * self.feed_vars[0]
             # subgraph with 9 op nodes
-            tmp_1 = tmp_0 * layers.sigmoid(self.feed_vars[1]) + layers.sigmoid(
-                self.feed_vars[2]
-            ) * layers.tanh(self.feed_vars[3])
-            tmp_2 = layers.tanh(tmp_1) + layers.sigmoid(self.feed_vars[4])
+            tmp_1 = tmp_0 * paddle.nn.functional.sigmoid(
+                self.feed_vars[1]
+            ) + paddle.nn.functional.sigmoid(self.feed_vars[2]) * paddle.tanh(
+                self.feed_vars[3]
+            )
+            tmp_2 = paddle.tanh(tmp_1) + paddle.nn.functional.sigmoid(
+                self.feed_vars[4]
+            )
 
         self.append_gradients(tmp_2)
 
@@ -162,10 +167,10 @@ class FusionGroupPassSumTest(FusionGroupPassTest):
             tmp_0 = layers.sum(
                 [self.feed_vars[0], self.feed_vars[1], self.feed_vars[2]]
             )
-            tmp_1 = layers.sqrt(tmp_0)
+            tmp_1 = paddle.sqrt(tmp_0)
             tmp_2 = layers.mul(tmp_0, self.feed_vars[3])
             # subgraph with 2 op nodes
-            tmp_3 = layers.square(layers.sum([tmp_1, tmp_2]))
+            tmp_3 = paddle.square(layers.sum([tmp_1, tmp_2]))
 
         self.append_gradients(tmp_3)
 

python/paddle/fluid/tests/unittests/mlu/sync_batch_norm_op_mlu.py

@@ -97,7 +97,7 @@ class TestSyncBatchNormOpTraining(TestSyncBatchNormRunnerBase):
                 )
                 if self.bn_dtype == np.float16:
                     bn = fluid.layers.cast(bn, 'float32')
-                sigmoid = fluid.layers.sigmoid(bn)
+                sigmoid = paddle.nn.functional.sigmoid(bn)
                 out = fluid.layers.reduce_sum(sigmoid)
                 # if not sync_bn:
                 #     out = out / core.get_mlu_device_count()

python/paddle/fluid/tests/unittests/mlu/test_gelu_op_mlu.py

@@ -109,7 +109,7 @@ class TestGeluNet(unittest.TestCase):
             c = paddle.multiply(a, b)
 
             fc_1 = fluid.layers.fc(input=c, size=128)
-            fc_1_gelu = fluid.layers.gelu(fc_1)
+            fc_1_gelu = paddle.nn.functional.gelu(fc_1)
             prediction = fluid.layers.fc(input=fc_1_gelu, size=2, act='softmax')
 
             cost = fluid.layers.cross_entropy(input=prediction, label=label)

python/paddle/fluid/tests/unittests/npu/sync_batch_norm_op_npu.py

@@ -99,7 +99,7 @@ class TestSyncBatchNormOpTraining(TestSyncBatchNormRunnerBase):
                 )
                 # if self.dtype == np.float16:
                 #     bn = fluid.layers.cast(bn, 'float32')
-                sigmoid = fluid.layers.sigmoid(bn)
+                sigmoid = paddle.nn.functional.sigmoid(bn)
                 out = fluid.layers.reduce_sum(sigmoid)
                 # if not sync_bn:
                 #     out = out / core.get_npu_device_count()

python/paddle/fluid/tests/unittests/npu/test_gelu_op_npu.py

@@ -109,7 +109,7 @@ class TestGeluNet(unittest.TestCase):
             c = paddle.multiply(a, b)
 
             fc_1 = fluid.layers.fc(input=c, size=128)
-            fc_1_gelu = fluid.layers.gelu(fc_1)
+            fc_1_gelu = paddle.nn.functional.gelu(fc_1)
             prediction = fluid.layers.fc(input=fc_1_gelu, size=2, act='softmax')
 
             cost = fluid.layers.cross_entropy(input=prediction, label=label)

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

@@ -88,7 +88,7 @@ def bow_net(
         input=data, is_sparse=is_sparse, size=[dict_dim, emb_dim]
     )
     bow = fluid.layers.sequence_pool(input=emb, pool_type='sum')
-    bow_tanh = fluid.layers.tanh(bow)
+    bow_tanh = paddle.tanh(bow)
     fc_1 = fluid.layers.fc(input=bow_tanh, size=hid_dim, act="tanh")
     fc_2 = fluid.layers.fc(input=fc_1, size=hid_dim2, act="tanh")
     prediction = fluid.layers.fc(input=[fc_2], size=class_dim, act="softmax")

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

@@ -33,7 +33,7 @@ class TestSigmoidTripleGradCheck(unittest.TestCase):
         dtype = np.float64
         x = layers.data('x', shape, False, dtype=dtype)
         x.persistable = True
-        y = layers.sigmoid(x)
+        y = F.sigmoid(x)
         x_arr = np.random.random(shape).astype(dtype)
         x_arr[np.abs(x_arr) < 0.005] = 0.002
         gradient_checker.triple_grad_check(
@@ -51,7 +51,7 @@ class TestSigmoidTripleGradCheck(unittest.TestCase):
 
 class TestSigmoidDoubleGradCheck(unittest.TestCase):
     def sigmoid_wrapper(self, x):
-        return fluid.layers.sigmoid(x[0])
+        return F.sigmoid(x[0])
 
     @prog_scope()
     def func(self, place):
@@ -60,7 +60,7 @@ class TestSigmoidDoubleGradCheck(unittest.TestCase):
         dtype = np.float64
         x = layers.data('x', shape, False, dtype=dtype)
         x.persistable = True
-        y = layers.sigmoid(x)
+        y = F.sigmoid(x)
         x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
         x_arr[np.abs(x_arr) < 0.005] = 0.002
         gradient_checker.double_grad_check(
@@ -92,7 +92,7 @@ class TestTanhTripleGradCheck(unittest.TestCase):
         dtype = np.float64
         x = layers.data('x', shape, False, dtype=dtype)
         x.persistable = True
-        y = layers.tanh(x)
+        y = paddle.tanh(x)
         x_arr = np.random.random(shape).astype(dtype)
         x_arr[np.abs(x_arr) < 0.005] = 0.002
         gradient_checker.triple_grad_check(
@@ -322,7 +322,7 @@ class TestSqrtDoubleGradCheck(unittest.TestCase):
         x = layers.data('x', shape, False, dtype)
         x.persistable = True
 
-        y = layers.sqrt(x)
+        y = paddle.sqrt(x)
         x_arr = np.random.uniform(0.1, 1, shape).astype(dtype)
 
         gradient_checker.double_grad_check(
@@ -354,7 +354,7 @@ class TestRsqrtDoubleGradCheck(unittest.TestCase):
         x = layers.data('x', shape, False, dtype)
         x.persistable = True
 
-        y = layers.rsqrt(x)
+        y = paddle.rsqrt(x)
         x_arr = np.random.uniform(0.1, 1, shape).astype(dtype)
 
         gradient_checker.double_grad_check(
@@ -386,7 +386,7 @@ class TestSquareDoubleGradCheck(unittest.TestCase):
 
         x = layers.data('x', shape, False, dtype)
         x.persistable = True
-        y = layers.square(x)
+        y = paddle.square(x)
         x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
 
         gradient_checker.double_grad_check(
@@ -417,7 +417,7 @@ class TestAbsDoubleGradCheck(unittest.TestCase):
 
         x = layers.data('x', shape, False, dtype)
         x.persistable = True
-        y = layers.abs(x)
+        y = paddle.abs(x)
         x_arr = np.random.uniform(-1, 1, shape).astype(dtype)
         # Because we set delta = 0.005 in calculating numeric gradient,
         # if x is too small, the numeric gradient is inaccurate.
@@ -449,7 +449,7 @@ class TestLogDoubleGradCheck(unittest.TestCase):
 
         x = layers.data('x', shape, False, dtype)
         x.persistable = True
-        y = layers.log(x)
+        y = paddle.log(x)
 
         x_arr = np.random.uniform(0.1, 1, shape).astype(dtype)
 
@@ -608,7 +608,7 @@ class TestSinTripleGradCheck(unittest.TestCase):
         dtype = np.float64
         x = layers.data('x', shape, False, dtype=dtype)
         x.persistable = True
-        y = layers.sin(x)
+        y = paddle.sin(x)
         x_arr = np.random.random(shape).astype(dtype)
         x_arr[np.abs(x_arr) < 0.005] = 0.002
         gradient_checker.triple_grad_check(
@@ -733,7 +733,7 @@ class TestCosTripleGradCheck(unittest.TestCase):
         dtype = np.float64
         x = layers.data('x', shape, False, dtype=dtype)
         x.persistable = True
-        y = layers.cos(x)
+        y = paddle.cos(x)
         x_arr = np.random.random(shape).astype(dtype)
         x_arr[np.abs(x_arr) < 0.005] = 0.002
         gradient_checker.triple_grad_check(

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

@@ -33,17 +33,17 @@ class TestSqrtOpError(unittest.TestCase):
         with program_guard(Program(), Program()):
             # The input type of sqrt op must be Variable or numpy.ndarray.
             in1 = 1
-            self.assertRaises(TypeError, fluid.layers.sqrt, in1)
+            self.assertRaises(TypeError, paddle.sqrt, in1)
             # The input dtype of sqrt op must be float16, float32, float64.
             in2 = fluid.layers.data(
                 name='input2', shape=[12, 10], dtype="int32"
             )
-            self.assertRaises(TypeError, fluid.layers.sqrt, in2)
+            self.assertRaises(TypeError, paddle.sqrt, in2)
 
             in3 = fluid.layers.data(
                 name='input3', shape=[12, 10], dtype="float16"
             )
-            fluid.layers.sqrt(x=in3)
+            paddle.sqrt(x=in3)
 
 
 class TestActivation(OpTest):
@@ -390,16 +390,6 @@ class TestLogSigmoidAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with paddle.static.program_guard(paddle.static.Program()):
-            x = paddle.fluid.data('X', [11, 17])
-            out = paddle.fluid.layers.logsigmoid(x)
-            exe = paddle.static.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = np.log(1 / (1 + np.exp(-self.x_np)))
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -488,16 +478,6 @@ class TestTanhAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', [10, 12], self.dtype)
-            out = fluid.layers.tanh(x)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = np.tanh(self.x_np)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -593,7 +573,7 @@ class TestSinhAPI(unittest.TestCase):
         with fluid.dygraph.guard():
             np_x = np.array([0.1])
             x = fluid.dygraph.to_variable(np_x)
-            z = fluid.layers.sinh(x).numpy()
+            z = paddle.sinh(x).numpy()
             z_expected = np.sinh(np_x)
             np.testing.assert_allclose(z, z_expected, rtol=1e-05)
 
@@ -610,7 +590,7 @@ class TestSinhAPI(unittest.TestCase):
                 dtype="float32",
             )
 
-            pd_sinh_out = fluid.layers.sinh(data_x)
+            pd_sinh_out = paddle.sinh(data_x)
             exe = fluid.Executor(place=fluid.CPUPlace())
             exe.run(fluid.default_startup_program())
             (np_sinh_res,) = exe.run(
@@ -630,7 +610,7 @@ class TestSinhAPI(unittest.TestCase):
             )
             var = fluid.dygraph.to_variable(input_x)
             var.stop_gradient = False
-            loss = fluid.layers.sinh(var)
+            loss = paddle.sinh(var)
             loss.backward()
             grad_var = var.gradient()
             self.assertEqual(grad_var.shape, input_x.shape)
@@ -640,13 +620,13 @@ class TestSinhOpError(unittest.TestCase):
     def test_errors(self):
         with program_guard(Program()):
             # The input type must be Variable.
-            self.assertRaises(TypeError, fluid.layers.sinh, 1)
+            self.assertRaises(TypeError, paddle.sinh, 1)
             # The input dtype must be float16, float32, float64.
             x_int32 = fluid.data(name='x_int32', shape=[12, 10], dtype='int32')
-            self.assertRaises(TypeError, fluid.layers.sinh, x_int32)
+            self.assertRaises(TypeError, paddle.sinh, x_int32)
             # support the input dtype is float16
             x_fp16 = fluid.data(name='x_fp16', shape=[12, 10], dtype='float16')
-            fluid.layers.sinh(x_fp16)
+            paddle.sinh(x_fp16)
 
 
 class TestCosh(TestActivation):
@@ -678,7 +658,7 @@ class TestCoshAPI(unittest.TestCase):
         with fluid.dygraph.guard():
             np_x = np.array([0.1])
             x = fluid.dygraph.to_variable(np_x)
-            z = fluid.layers.cosh(x).numpy()
+            z = paddle.cosh(x).numpy()
             z_expected = np.cosh(np_x)
             np.testing.assert_allclose(z, z_expected, rtol=1e-05)
 
@@ -715,7 +695,7 @@ class TestCoshAPI(unittest.TestCase):
             )
             var = fluid.dygraph.to_variable(input_x)
             var.stop_gradient = False
-            loss = fluid.layers.cosh(var)
+            loss = paddle.cosh(var)
             loss.backward()
             grad_var = var.gradient()
             self.assertEqual(grad_var.shape, input_x.shape)
@@ -725,13 +705,13 @@ class TestCoshOpError(unittest.TestCase):
     def test_errors(self):
         with program_guard(Program()):
             # The input type must be Variable.
-            self.assertRaises(TypeError, fluid.layers.cosh, 1)
+            self.assertRaises(TypeError, paddle.cosh, 1)
             # The input dtype must be float16, float32, float64.
             x_int32 = fluid.data(name='x_int32', shape=[12, 10], dtype='int32')
-            self.assertRaises(TypeError, fluid.layers.cosh, x_int32)
+            self.assertRaises(TypeError, paddle.cosh, x_int32)
             # support the input dtype is float16
             x_fp16 = fluid.data(name='x_fp16', shape=[12, 10], dtype='float16')
-            fluid.layers.cosh(x_fp16)
+            paddle.cosh(x_fp16)
 
 
 def ref_tanhshrink(x):
@@ -798,16 +778,6 @@ class TestTanhshrinkAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', self.x_np.shape, self.x_np.dtype)
-            out = fluid.layers.tanh_shrink(x)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = ref_tanhshrink(self.x_np)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -914,16 +884,6 @@ class TestHardShrinkAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', [10, 12])
-            out = fluid.layers.hard_shrink(x)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = ref_hardshrink(self.x_np, 0.5)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -1080,16 +1040,6 @@ class TestSoftshrinkAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', self.x_np.shape, self.x_np.dtype)
-            out = fluid.layers.softshrink(x, self.threshold)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = ref_softshrink(self.x_np, self.threshold)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -1780,16 +1730,6 @@ class TestLeakyReluAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', [10, 12])
-            out = fluid.layers.leaky_relu(x, 0.01)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = ref_leaky_relu(self.x_np)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -3120,16 +3060,6 @@ class TestSoftplusAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', self.x_np.shape, self.x_np.dtype)
-            out = fluid.layers.softplus(x)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = ref_softplus(self.x_np)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -3215,16 +3145,6 @@ class TestSoftsignAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', self.x_np.shape, self.x_np.dtype)
-            out = fluid.layers.softsign(x)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = ref_softsign(self.x_np)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -3314,16 +3234,6 @@ class TestThresholdedReluAPI(unittest.TestCase):
             np.testing.assert_allclose(out_ref, r.numpy(), rtol=1e-05)
         paddle.enable_static()
 
-    def test_fluid_api(self):
-        paddle.enable_static()
-        with fluid.program_guard(fluid.Program()):
-            x = fluid.data('X', self.x_np.shape, self.x_np.dtype)
-            out = fluid.layers.thresholded_relu(x, self.threshold)
-            exe = fluid.Executor(self.place)
-            res = exe.run(feed={'X': self.x_np}, fetch_list=[out])
-        out_ref = ref_thresholded_relu(self.x_np, self.threshold)
-        np.testing.assert_allclose(out_ref, res[0], rtol=1e-05)
-
     def test_errors(self):
         paddle.enable_static()
         with paddle.static.program_guard(paddle.static.Program()):
@@ -3660,45 +3570,6 @@ class TestMishAPI(unittest.TestCase):
             F.mish(x_fp16)
 
 
-# ------------------ Test Error Activation----------------------
-def create_test_error_class(op_type):
-    class TestOpErrors(unittest.TestCase):
-        def test_errors(self):
-            with program_guard(Program(), Program()):
-                op = getattr(fluid.layers, op_type)
-                # The input dtype of op_type must be float32, float64.
-                in1 = fluid.layers.data(
-                    name='input2', shape=[12, 10], dtype="int32"
-                )
-                in2 = fluid.layers.data(
-                    name='input3', shape=[12, 10], dtype="int64"
-                )
-                self.assertRaises(TypeError, op, in1)
-                self.assertRaises(TypeError, op, in2)
-
-    cls_name = "{0}_{1}".format(op_type, "test_errors")
-    TestOpErrors.__name__ = cls_name
-    globals()[cls_name] = TestOpErrors
-
-
-create_test_error_class('acos')
-create_test_error_class('asin')
-create_test_error_class('atan')
-create_test_error_class('ceil')
-create_test_error_class('cos')
-create_test_error_class('floor')
-create_test_error_class('reciprocal')
-create_test_error_class('round')
-create_test_error_class('rsqrt')
-create_test_error_class('sin')
-create_test_error_class('sqrt')
-create_test_error_class('tanh')
-create_test_error_class('tan')
-create_test_error_class('acosh')
-create_test_error_class('asinh')
-create_test_error_class('atanh')
-
-
 # ------------------ Test Cudnn Activation----------------------
 def create_test_act_cudnn_class(parent, atol=1e-3, grad_atol=1e-3):
     @unittest.skipIf(

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

@@ -371,7 +371,7 @@ class BadInputTest(unittest.TestCase):
 
             def test_bad_x():
                 data = [1, 2, 4]
-                result = fluid.layers.cumsum(data, axis=0)
+                result = paddle.cumsum(data, axis=0)
 
             self.assertRaises(TypeError, test_bad_x)
 

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

@@ -87,7 +87,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -119,7 +119,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -150,7 +150,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps11.py

@@ -83,7 +83,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -111,7 +111,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -138,7 +138,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps12.py

@@ -86,7 +86,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -114,7 +114,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -141,7 +141,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps13.py

@@ -89,7 +89,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -119,7 +119,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -148,7 +148,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps2.py

@@ -88,7 +88,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         q_ss = fluid.layers.data_norm(input=q_ss)
         # fc layer after conv
         q_fc = fluid.layers.fc(
@@ -119,7 +119,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -148,7 +148,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps3.py

@@ -87,7 +87,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -119,7 +119,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -150,7 +150,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps4.py

@@ -85,7 +85,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -115,7 +115,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -144,7 +144,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps5.py

@@ -87,7 +87,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -119,7 +119,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -150,7 +150,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

python/paddle/fluid/tests/unittests/test_dist_fleet_ps6.py

@@ -85,7 +85,7 @@ class TestPSPassWithBow(unittest.TestCase):
         q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
-        q_ss = fluid.layers.softsign(q_sum)
+        q_ss = paddle.nn.functional.softsign(q_sum)
         # fc layer after conv
         q_fc = fluid.layers.fc(
             input=q_ss,
@@ -115,7 +115,7 @@ class TestPSPassWithBow(unittest.TestCase):
         pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
-        pt_ss = fluid.layers.softsign(pt_sum)
+        pt_ss = paddle.nn.functional.softsign(pt_sum)
         # fc layer
         pt_fc = fluid.layers.fc(
             input=pt_ss,
@@ -144,7 +144,7 @@ class TestPSPassWithBow(unittest.TestCase):
         nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
-        nt_ss = fluid.layers.softsign(nt_sum)
+        nt_ss = paddle.nn.functional.softsign(nt_sum)
         # fc layer
         nt_fc = fluid.layers.fc(
             input=nt_ss,

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

@@ -38,7 +38,7 @@ def gru_net(
     fc0 = fluid.layers.fc(input=emb, size=hid_dim * 3)
     gru_h = fluid.layers.dynamic_gru(input=fc0, size=hid_dim, is_reverse=False)
     gru_max = fluid.layers.sequence_pool(input=gru_h, pool_type='max')
-    gru_max_tanh = fluid.layers.tanh(gru_max)
+    gru_max_tanh = paddle.tanh(gru_max)
     fc1 = fluid.layers.fc(input=gru_max_tanh, size=hid_dim2, act='tanh')
     prediction = fluid.layers.fc(input=fc1, size=class_dim, act='softmax')
     cost = fluid.layers.cross_entropy(input=prediction, label=label)

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

@@ -40,7 +40,7 @@ def lstm_net(
         input=fc0, size=hid_dim * 4, is_reverse=False
     )
     lstm_max = fluid.layers.sequence_pool(input=lstm_h, pool_type='max')
-    lstm_max_tanh = fluid.layers.tanh(lstm_max)
+    lstm_max_tanh = paddle.tanh(lstm_max)
     fc1 = fluid.layers.fc(input=lstm_max_tanh, size=hid_dim2, act='tanh')
     prediction = fluid.layers.fc(input=fc1, size=class_dim, act='softmax')
     cost = fluid.layers.cross_entropy(input=prediction, label=label)

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

@@ -191,10 +191,10 @@ def lm_model(
                     ends=[hidden_size * 4],
                 )
 
-                c = pre_cell * layers.sigmoid(f) + layers.sigmoid(
-                    i
-                ) * layers.tanh(j)
-                m = layers.tanh(c) * layers.sigmoid(o)
+                c = pre_cell * paddle.nn.functional.sigmoid(
+                    f
+                ) + paddle.nn.functional.sigmoid(i) * paddle.tanh(j)
+                m = paddle.tanh(c) * paddle.nn.functional.sigmoid(o)
 
                 rnn.update_memory(pre_hidden, m)
                 rnn.update_memory(pre_cell, c)
@@ -299,10 +299,10 @@ def lm_model(
                 gate_input = layers.elementwise_add(gate_input, bias)
                 i, j, f, o = layers.split(gate_input, num_or_sections=4, dim=-1)
 
-                c = pre_cell * layers.sigmoid(f) + layers.sigmoid(
-                    i
-                ) * layers.tanh(j)
-                m = layers.tanh(c) * layers.sigmoid(o)
+                c = pre_cell * paddle.nn.functional.sigmoid(
+                    f
+                ) + paddle.nn.functional.sigmoid(i) * paddle.tanh(j)
+                m = paddle.tanh(c) * paddle.nn.functional.sigmoid(o)
 
                 hidden_array[k] = m
                 cell_array[k] = c

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

@@ -327,7 +327,9 @@ class EagerDeletionRecurrentOpTest2(EagerDeletionRecurrentOpTest1):
                 bias_attr=False,
             )
 
-            h = layers.sigmoid(x=layers.elementwise_add(x=temp_l, y=temp_r))
+            h = paddle.nn.functional.sigmoid(
+                x=layers.elementwise_add(x=temp_l, y=temp_r)
+            )
 
             rnn.update_memory(h_pre, h)
             rnn.output(h)

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

@@ -48,7 +48,7 @@ class TestErfLayer(unittest.TestCase):
         y_ref = erf(x)
         with dg.guard(place) as g:
             x_var = dg.to_variable(x)
-            y_var = fluid.layers.erf(x_var)
+            y_var = paddle.erf(x_var)
             y_test = y_var.numpy()
         np.testing.assert_allclose(y_ref, y_test, rtol=1e-05)
 

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

@@ -45,7 +45,7 @@ class TestGeluOp(unittest.TestCase):
         place = fluid.CPUPlace()
         with dg.guard(place) as g:
             x_var = dg.to_variable(x)
-            y_var = fluid.layers.gelu(x_var, approximate)
+            y_var = F.gelu(x_var, approximate)
             y_test = y_var.numpy()
         np.testing.assert_allclose(y_ref, y_test, rtol=1e-05, atol=1e-08)
 
@@ -56,7 +56,7 @@ class TestGeluOp(unittest.TestCase):
         place = fluid.CUDAPlace(0)
         with dg.guard(place) as g:
             x_var = dg.to_variable(x)
-            y_var = fluid.layers.gelu(x_var, approximate)
+            y_var = F.gelu(x_var, approximate)
             y_test = y_var.numpy()
         np.testing.assert_allclose(y_ref, y_test, rtol=1e-05, atol=1e-08)
 

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

@@ -35,7 +35,7 @@ def bow_net(
         input=data, is_sparse=True, size=[dict_dim, emb_dim]
     )
     bow = fluid.layers.sequence_pool(input=emb, pool_type='sum')
-    bow_tanh = fluid.layers.tanh(bow)
+    bow_tanh = paddle.tanh(bow)
     fc_1 = fluid.layers.fc(input=bow_tanh, size=hid_dim, act="tanh")
     fc_2 = fluid.layers.fc(input=fc_1, size=hid_dim2, act="tanh")
     prediction = fluid.layers.fc(input=[fc_2], size=class_dim, act="softmax")

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

@@ -914,7 +914,7 @@ class TestDygraphUtils(unittest.TestCase):
         with fluid.dygraph.guard():
             a = paddle.to_tensor(a_np)
             res1 = func(a, act="sigmoid", use_mkldnn=True, use_cudnn=True)
-            res2 = fluid.layers.sigmoid(a)
+            res2 = paddle.nn.functional.sigmoid(a)
             np.testing.assert_allclose(res1.numpy(), res2.numpy(), rtol=1e-05)
 
     def test_append_activation_in_dygraph2(self):
@@ -929,7 +929,7 @@ class TestDygraphUtils(unittest.TestCase):
         with fluid.dygraph.guard():
             a = paddle.to_tensor(a_np)
             res1 = func(a, act="sigmoid", use_cudnn=True)
-            res2 = fluid.layers.sigmoid(a)
+            res2 = paddle.nn.functional.sigmoid(a)
             np.testing.assert_array_equal(res1.numpy(), res2.numpy())
 
     def test_append_activation_in_dygraph3(self):

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

@@ -317,7 +317,7 @@ class SimpleAttention(fluid.dygraph.Layer):
         concated = fluid.layers.elementwise_add(
             encoder_proj, decoder_state_expand
         )
-        concated = fluid.layers.tanh(x=concated)
+        concated = paddle.tanh(x=concated)
         attention_weight = self.fc_2(concated)
 
         weights_reshape = fluid.layers.reshape(

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

@@ -115,10 +115,10 @@ class SimpleLSTMRNN(fluid.Layer):
                 i, j, f, o = fluid.layers.split(
                     gate_input, num_or_sections=4, dim=-1
                 )
-                c = pre_cell * fluid.layers.sigmoid(f) + fluid.layers.sigmoid(
-                    i
-                ) * fluid.layers.tanh(j)
-                m = fluid.layers.tanh(c) * fluid.layers.sigmoid(o)
+                c = pre_cell * paddle.nn.functional.sigmoid(
+                    f
+                ) + paddle.nn.functional.sigmoid(i) * paddle.tanh(j)
+                m = paddle.tanh(c) * paddle.nn.functional.sigmoid(o)
                 self.hidden_array[k] = m
                 self.cell_array[k] = c
                 self._input = m

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

@@ -110,10 +110,10 @@ class SimpleLSTMRNN(fluid.Layer):
                 i, j, f, o = fluid.layers.split(
                     gate_input, num_or_sections=4, dim=-1
                 )
-                c = pre_cell * fluid.layers.sigmoid(f) + fluid.layers.sigmoid(
-                    i
-                ) * fluid.layers.tanh(j)
-                m = fluid.layers.tanh(c) * fluid.layers.sigmoid(o)
+                c = pre_cell * paddle.nn.functional.sigmoid(
+                    f
+                ) + paddle.nn.functional.sigmoid(i) * paddle.tanh(j)
+                m = paddle.tanh(c) * paddle.nn.functional.sigmoid(o)
                 self.hidden_array[k] = m
                 self.cell_array[k] = c
                 self._input = m

python/paddle/fluid/tests/unittests/test_imperative_save_load_v2.py

@@ -112,10 +112,10 @@ class SimpleLSTMRNN(fluid.Layer):
                 i, j, f, o = fluid.layers.split(
                     gate_input, num_or_sections=4, dim=-1
                 )
-                c = pre_cell * fluid.layers.sigmoid(f) + fluid.layers.sigmoid(
-                    i
-                ) * fluid.layers.tanh(j)
-                m = fluid.layers.tanh(c) * fluid.layers.sigmoid(o)
+                c = pre_cell * paddle.nn.functional.sigmoid(
+                    f
+                ) + paddle.nn.functional.sigmoid(i) * paddle.tanh(j)
+                m = paddle.tanh(c) * paddle.nn.functional.sigmoid(o)
                 self.hidden_array[k] = m
                 self.cell_array[k] = c
                 self._input = m

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

@@ -322,7 +322,7 @@ class Generator(fluid.dygraph.Layer):
         res_block = self._res_block(conv0)
         deconv = self._deconv(res_block)
         conv1 = self._conv1(deconv)
-        out = fluid.layers.tanh(conv1)
+        out = paddle.tanh(conv1)
         return out
 
 
@@ -437,11 +437,9 @@ def gradient_penalty(f, real, fake, no_grad_set, cfg):
     )
 
     epsilon = 1e-16
-    norm = fluid.layers.sqrt(
-        fluid.layers.reduce_sum(fluid.layers.square(gradient), dim=1) + epsilon
-    )
+    norm = paddle.sqrt(paddle.sum(paddle.square(gradient), axis=1) + epsilon)
 
-    gp = fluid.layers.reduce_mean(fluid.layers.square(norm - 1.0))
+    gp = paddle.mean(paddle.square(norm - 1.0))
     return gp
 
 
@@ -451,7 +449,7 @@ def get_generator_loss(
     fake_img = generator(image_real, label_trg)
     rec_img = generator(fake_img, label_org)
     g_loss_rec = fluid.layers.reduce_mean(
-        fluid.layers.abs(fluid.layers.elementwise_sub(image_real, rec_img))
+        paddle.abs(paddle.subtract(image_real, rec_img))
     )
 
     pred_fake, cls_fake = discriminator(fake_img)

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

@@ -182,7 +182,7 @@ class TestDygraphTripleGrad(TestCase):
         numel = z_np.size
         z.stop_gradient = False
 
-        out = fluid.layers.sigmoid(paddle.matmul(x, y) + z)
+        out = paddle.nn.functional.sigmoid(paddle.matmul(x, y) + z)
         out_np = out.numpy()
 
         (dx_actual,) = self.grad([out], [x], create_graph=True)
@@ -278,7 +278,7 @@ class TestDygraphTripleGradBradcastCase(TestCase):
         numel = z_np.size
         z.stop_gradient = False
 
-        out = fluid.layers.sigmoid(paddle.matmul(x, y) + z)
+        out = paddle.nn.functional.sigmoid(paddle.matmul(x, y) + z)
         out_np = out.numpy()
 
         (dx_actual,) = self.grad([out], [x], create_graph=True)

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

@@ -87,7 +87,7 @@ class TestInplaceANBOpTraining(unittest.TestCase):
                 # a new Variable for fetch
                 bn = bn * 1.0
 
-                sigmoid = fluid.layers.sigmoid(bn)
+                sigmoid = paddle.nn.functional.sigmoid(bn)
                 out = fluid.layers.reduce_sum(sigmoid)
                 if not only_forward:
                     sgd_opt = fluid.optimizer.SGD(learning_rate=0.0)

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

@@ -41,7 +41,7 @@ def lstm_net(
         input=fc0, size=hid_dim * 4, is_reverse=False
     )
     lstm_max = fluid.layers.sequence_pool(input=lstm_h, pool_type='max')
-    lstm_max_tanh = fluid.layers.tanh(lstm_max)
+    lstm_max_tanh = paddle.tanh(lstm_max)
     fc1 = fluid.layers.fc(input=lstm_max_tanh, size=hid_dim2, act='tanh')
     prediction = fluid.layers.fc(input=fc1, size=class_dim, act='softmax')
     cost = fluid.layers.cross_entropy(input=prediction, label=label)

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

@@ -3680,126 +3680,6 @@ class TestBook(LayerTest):
             )
             return out
 
-    def make_sigmoid(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.sigmoid(input, name='sigmoid')
-            return out
-
-    def make_exp(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.exp(input, name='exp')
-            return out
-
-    def make_tanh(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.tanh(input, name='tanh')
-            return out
-
-    def make_tanh_shrink(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.tanh_shrink(input, name='tanh_shrink')
-            return out
-
-    def make_sqrt(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.sqrt(input, name='sqrt')
-            return out
-
-    def make_abs(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.abs(input, name='abs')
-            return out
-
-    def make_ceil(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.ceil(input, name='ceil')
-            return out
-
-    def make_floor(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.floor(input, name='floor')
-            return out
-
-    def make_cos(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.cos(input, name='cos')
-            return out
-
-    def make_sin(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.sin(input, name='sin')
-            return out
-
-    def make_round(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.round(input, name='round')
-            return out
-
-    def make_reciprocal(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.reciprocal(input, name='reciprocal')
-            return out
-
-    def make_square(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.square(input, name='square')
-            return out
-
-    def make_softplus(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.softplus(input, name='softplus')
-            return out
-
-    def make_softsign(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.softsign(input, name='softsign')
-            return out
-
     def make_mish(self):
         with program_guard(
             fluid.default_main_program(), fluid.default_startup_program()
@@ -3920,14 +3800,6 @@ class TestBook(LayerTest):
             out = layers.scale(input, scale=scale_var)
             return out
 
-    def make_softshrink(self):
-        with program_guard(
-            fluid.default_main_program(), fluid.default_startup_program()
-        ):
-            input = self._get_data(name="input", shape=[16], dtype="float32")
-            out = layers.softshrink(input, alpha=0.3)
-            return out
-
     def make_iou_similarity(self):
         with program_guard(
             fluid.default_main_program(), fluid.default_startup_program()

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

@@ -63,7 +63,7 @@ class TestLgammaOpApi(unittest.TestCase):
         shape = (1, 4)
         data = np.random.random(shape).astype(self.dtype) + 1
         data_ = paddle.to_tensor(data)
-        out = paddle.fluid.layers.lgamma(data_)
+        out = paddle.lgamma(data_)
         result = special.gammaln(data)
         np.testing.assert_allclose(result, out.numpy(), rtol=1e-05)
         paddle.enable_static()

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

@@ -50,7 +50,7 @@ def lstm_net(use_feed):
         input=fc0, size=hid_dim * 4, is_reverse=False
     )
     lstm_max = fluid.layers.sequence_pool(input=lstm_h, pool_type='max')
-    lstm_max_tanh = fluid.layers.tanh(lstm_max)
+    lstm_max_tanh = paddle.tanh(lstm_max)
     fc1 = fluid.layers.fc(input=lstm_max_tanh, size=hid_dim2, act='tanh')
     prediction = fluid.layers.fc(input=fc1, size=class_dim, act='softmax')
     cost = fluid.layers.cross_entropy(input=prediction, label=label)

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

@@ -81,7 +81,7 @@ def simple_fc_net(img, label, use_py_func_op):
             ),
         )
         if not use_py_func_op:
-            hidden = fluid.layers.tanh(hidden)
+            hidden = paddle.tanh(hidden)
         else:
             new_hidden = (
                 fluid.default_main_program()

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

@@ -316,7 +316,9 @@ class RecurrentOpTest2(RecurrentOpTest1):
                 bias_attr=False,
             )
 
-            h = layers.sigmoid(x=layers.elementwise_add(x=temp_l, y=temp_r))
+            h = paddle.nn.functional.sigmoid(
+                x=layers.elementwise_add(x=temp_l, y=temp_r)
+            )
 
             rnn.update_memory(h_pre, h)
             rnn.output(h)
@@ -710,7 +712,9 @@ class RecurrentOpStopGradientTest(RecurrentOpTest1):
                 bias_attr=False,
             )
 
-            h = layers.sigmoid(x=layers.elementwise_add(temp_l, temp_r))
+            h = paddle.nn.functional.sigmoid(
+                x=layers.elementwise_add(temp_l, temp_r)
+            )
 
             rnn.update_memory(h_pre, h)
             rnn.output(h)

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

@@ -135,7 +135,7 @@ def bow_net(
         input=data, is_sparse=is_sparse, size=[dict_dim, emb_dim]
     )
     bow = fluid.layers.sequence_pool(input=emb, pool_type='sum')
-    bow_tanh = fluid.layers.tanh(bow)
+    bow_tanh = paddle.tanh(bow)
     fc_1 = fluid.layers.fc(input=bow_tanh, size=hid_dim, act="tanh")
     fc_2 = fluid.layers.fc(input=fc_1, size=hid_dim2, act="tanh")
     prediction = fluid.layers.fc(input=[fc_2], size=class_dim, act="softmax")
@@ -225,7 +225,7 @@ class TestRegularizer(unittest.TestCase):
             param_list = fluid.default_main_program().block(0).all_parameters()
             para_sum = []
             for para in param_list:
-                para_mul = fluid.layers.square(x=para)
+                para_mul = paddle.square(x=para)
                 para_sum.append(fluid.layers.reduce_sum(input=para_mul))
             avg_cost_l2 += fluid.layers.sums(para_sum) * 0.5
 

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

@@ -41,7 +41,7 @@ def bow_net(
         input=data, is_sparse=is_sparse, size=[dict_dim, emb_dim]
     )
     bow = fluid.layers.sequence_pool(input=emb, pool_type='sum')
-    bow_tanh = fluid.layers.tanh(bow)
+    bow_tanh = paddle.tanh(bow)
     fc_1 = fluid.layers.fc(input=bow_tanh, size=hid_dim, act="tanh")
     fc_2 = fluid.layers.fc(input=fc_1, size=hid_dim2, act="tanh")
     prediction = fluid.layers.fc(input=[fc_2], size=class_dim, act="softmax")
@@ -133,7 +133,7 @@ class TestRegularizer(unittest.TestCase):
             param_list = fluid.default_main_program().block(0).all_parameters()
             para_sum = []
             for para in param_list:
-                para_mul = fluid.layers.square(x=para)
+                para_mul = paddle.square(x=para)
                 para_sum.append(fluid.layers.reduce_sum(input=para_mul))
             avg_cost_l2 += fluid.layers.sums(para_sum) * 0.5
 

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

@@ -30,7 +30,7 @@ class Generator(fluid.dygraph.Layer):
 
     def forward(self, x):
         x = self.conv1(x)
-        x = fluid.layers.tanh(x)
+        x = paddle.tanh(x)
         return x
 
 

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

@@ -122,10 +122,10 @@ class SimpleLSTMRNN(fluid.Layer):
                 i, j, f, o = fluid.layers.split(
                     gate_input, num_or_sections=4, dim=-1
                 )
-                c = pre_cell * fluid.layers.sigmoid(f) + fluid.layers.sigmoid(
-                    i
-                ) * fluid.layers.tanh(j)
-                m = fluid.layers.tanh(c) * fluid.layers.sigmoid(o)
+                c = pre_cell * paddle.nn.functional.sigmoid(
+                    f
+                ) + paddle.nn.functional.sigmoid(i) * paddle.tanh(j)
+                m = paddle.tanh(c) * paddle.nn.functional.sigmoid(o)
                 self.hidden_array[k] = m
                 self.cell_array[k] = c
                 self._input = m

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

@@ -94,7 +94,7 @@ class TestSyncBatchNormOpTraining(unittest.TestCase):
                     bn = fluid.layers.cast(bn, 'float32')
                 else:
                     bn = fluid.layers.cast(bn, 'float64')
-                sigmoid = fluid.layers.sigmoid(bn)
+                sigmoid = paddle.nn.functional.sigmoid(bn)
                 out = fluid.layers.reduce_sum(sigmoid)
                 if not sync_bn:
                     out = out / core.get_cuda_device_count()

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

@@ -59,7 +59,7 @@ def bow_net(
         input=data, is_sparse=is_sparse, size=[dict_dim, emb_dim]
     )
     bow = fluid.layers.sequence_pool(input=emb, pool_type='sum')
-    bow_tanh = fluid.layers.tanh(bow)
+    bow_tanh = paddle.tanh(bow)
     fc_1 = fluid.layers.fc(input=bow_tanh, size=hid_dim, act="tanh")
     fc_2 = fluid.layers.fc(input=fc_1, size=hid_dim2, act="tanh")
     prediction = fluid.layers.fc(input=[fc_2], size=class_dim, act="softmax")

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

@@ -15,6 +15,7 @@
 from functools import partial
 import numpy as np
 
+import paddle
 import paddle.fluid as fluid
 import paddle.fluid.layers as layers
 
@@ -156,7 +157,7 @@ def multi_head_attention(
         # So, here define the softmax for temporary solution.
 
         def __softmax(x, eps=1e-9):
-            exp_out = layers.exp(x=x)
+            exp_out = paddle.exp(x=x)
             sum_out = layers.reduce_sum(exp_out, dim=-1, keep_dim=False)
             return layers.elementwise_div(x=exp_out, y=sum_out, axis=0)
 

python/paddle/incubate/distributed/models/moe/grad_clip.py

@@ -209,7 +209,7 @@ class ClipGradForMOEByGlobalNorm(ClipGradBase):
             global_norm_var = global_norm_var_normal + global_norm_var_moe
 
         params_and_grads = []
-        global_norm_var = layers.sqrt(global_norm_var)
+        global_norm_var = paddle.sqrt(global_norm_var)
         max_global_norm = layers.fill_constant(
             shape=[1], dtype=global_norm_var.dtype, value=self.clip_norm
         )

python/paddle/incubate/optimizer/modelaverage.py

@@ -557,7 +557,7 @@ class ModelAverage(Optimizer):
         sum = layers.cast(
             x=sum, dtype='float32' if self._dtype is None else self._dtype
         )
-        layers.ops._elementwise_div(x=sum, y=tmp, out=param)
+        paddle.tensor.ops._elementwise_div(x=sum, y=tmp, out=param)
 
     def _add_average_restore_op(self, block, param):
         param = block._clone_variable(param)