Change reduce mean (#27997)

* change paddle.fluid.layers.reduce_mean to paddle.mean

* change paddle.fluid.layers.reduce_mean to paddle.mean

python/paddle/amp/grad_scaler.py

@@ -56,7 +56,7 @@ class GradScaler(AmpScaler):
         data = paddle.rand([10, 3, 32, 32])
         with paddle.amp.auto_cast():
             conv = model(data)
-            loss = paddle.fluid.layers.reduce_mean(conv) 
+            loss = paddle.mean(conv)
             scaled = scaler.scale(loss)  # scale the loss 
             scaled.backward()            # do backward
             scaler.minimize(optimizer, scaled)  # update parameters     
@@ -96,7 +96,7 @@ class GradScaler(AmpScaler):
             data = paddle.rand([10, 3, 32, 32])
             with paddle.amp.auto_cast():
                 conv = model(data)
-                loss = paddle.fluid.layers.reduce_mean(conv) 
+                loss = paddle.mean(conv)
                 scaled = scaler.scale(loss)  # scale the loss 
                 scaled.backward()            # do backward
                 scaler.minimize(optimizer, scaled)  # update parameters  
@@ -128,7 +128,7 @@ class GradScaler(AmpScaler):
             data = paddle.rand([10, 3, 32, 32])
             with paddle.amp.auto_cast():
                 conv = model(data)
-                loss = paddle.fluid.layers.reduce_mean(conv) 
+                loss = paddle.mean(conv)
                 scaled = scaler.scale(loss)  # scale the loss 
                 scaled.backward()            # do backward
                 scaler.minimize(optimizer, scaled)  # update parameters  

python/paddle/fluid/tests/unittests/dygraph_to_static/simnet_dygraph_model_v2.py

@@ -105,7 +105,7 @@ class ReduceMeanLayer(object):
         """
         operation
         """
-        mean = paddle.fluid.layers.reduce_mean(input)
+        mean = paddle.mean(input)
         return mean
 
 

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

@@ -187,7 +187,7 @@ class PtbModel(paddle.nn.Layer):
         loss = paddle.nn.functional.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False)
         loss = paddle.reshape(loss, shape=[-1, self.num_steps])
-        loss = paddle.fluid.layers.reduce_mean(loss, dim=[0])
+        loss = paddle.mean(loss, axis=[0])
         loss = paddle.fluid.layers.reduce_sum(loss)
 
         return loss, last_hidden, last_cell

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

@@ -414,7 +414,7 @@ class TestLRScheduler(unittest.TestCase):
             for batch_id in range(2):
                 x = paddle.to_tensor(x)
                 out = linear(x)
-                loss = paddle.fluid.layers.reduce_mean(out)
+                loss = paddle.mean(out)
                 loss.backward()
                 adam.step()
                 adam.clear_grad()

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

@@ -73,8 +73,8 @@ class TestRetainGraph(unittest.TestCase):
             fake_AB = paddle.concat((real_data.detach(), interpolatesv), 1)
             disc_interpolates = netD(fake_AB)
 
-            outs = paddle.fluid.layers.fill_constant(disc_interpolates.shape,
-                                        disc_interpolates.dtype, 1.0)
+            outs = paddle.fluid.layers.fill_constant(
+                disc_interpolates.shape, disc_interpolates.dtype, 1.0)
             gradients = paddle.grad(
                 outputs=disc_interpolates,
                 inputs=fake_AB,
@@ -85,8 +85,8 @@ class TestRetainGraph(unittest.TestCase):
 
             gradients = paddle.reshape(gradients[0], [real_data.shape[0], -1])
 
-            gradient_penalty = paddle.fluid.layers.reduce_mean((paddle.norm(
-                gradients + 1e-16, 2, 1) - constant)**
+            gradient_penalty = paddle.mean((paddle.norm(gradients + 1e-16, 2, 1)
+                                            - constant)**
                                            2) * lambda_gp  # added eps
             return gradient_penalty, gradients
         else:
@@ -113,7 +113,8 @@ class TestRetainGraph(unittest.TestCase):
         fake_AB = paddle.concat((realA, fakeB), 1)
         G_pred_fake = d(fake_AB.detach())
 
-        false_target = paddle.fluid.layers.fill_constant(G_pred_fake.shape, 'float32', 0.0)
+        false_target = paddle.fluid.layers.fill_constant(G_pred_fake.shape,
+                                                         'float32', 0.0)
 
         G_gradient_penalty, _ = self.cal_gradient_penalty(
             d, realA, fakeB, lambda_gp=10.0)
@@ -125,7 +126,8 @@ class TestRetainGraph(unittest.TestCase):
         optim_g.clear_gradients()
         fake_AB = paddle.concat((realA, fakeB), 1)
         G_pred_fake = d(fake_AB)
-        true_target = paddle.fluid.layers.fill_constant(G_pred_fake.shape, 'float32', 1.0)
+        true_target = paddle.fluid.layers.fill_constant(G_pred_fake.shape,
+                                                        'float32', 1.0)
         loss_g = l1_criterion(fakeB, realB) + gan_criterion(G_pred_fake,
                                                             true_target)
 

python/paddle/optimizer/lr.py

@@ -229,7 +229,7 @@ class NoamDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -325,7 +325,7 @@ class PiecewiseDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -407,7 +407,7 @@ class NaturalExpDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -485,7 +485,7 @@ class InverseTimeDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -580,7 +580,7 @@ class PolynomialDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -695,7 +695,7 @@ class LinearWarmup(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -798,7 +798,7 @@ class ExponentialDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -885,7 +885,7 @@ class MultiStepDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -992,7 +992,7 @@ class StepDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -1086,7 +1086,7 @@ class LambdaDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -1184,7 +1184,7 @@ class ReduceOnPlateau(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()
@@ -1390,7 +1390,7 @@ class CosineAnnealingDecay(LRScheduler):
                 for batch_id in range(2):
                     x = paddle.uniform([10, 10])
                     out = linear(x)
-                    loss = paddle.fluid.layers.reduce_mean(out)
+                    loss = paddle.mean(out)
                     loss.backward()
                     sgd.step()
                     sgd.clear_gradients()

python/paddle/optimizer/optimizer.py

@@ -377,7 +377,7 @@ class Optimizer(object):
                 linear = paddle.nn.Linear(10, 10)
                 inp = paddle.to_tensor(inp)
                 out = linear(inp)
-                loss = paddle.fluid.layers.reduce_mean(out)
+                loss = paddle.mean(out)
                 
                 bd = [2, 4, 6, 8]
                 value = [0.2, 0.4, 0.6, 0.8, 1.0]