diff --git a/python/paddle/incubate/nn/functional/fused_transformer.py b/python/paddle/incubate/nn/functional/fused_transformer.py
index dffddb8b9eca21f13403a5db660271fa0159e792..0887cd56aefe42e166d61c67ac570f0fef6d20da 100644
--- a/python/paddle/incubate/nn/functional/fused_transformer.py
+++ b/python/paddle/incubate/nn/functional/fused_transformer.py
@@ -947,7 +947,6 @@ def fused_multi_transformer(
             # required: gpu
             import paddle
             import paddle.incubate.nn.functional as F
-            import numpy as np
 
             # input: [batch_size, seq_len, embed_dim]
             x = paddle.rand(shape=(2, 4, 128), dtype="float32")
diff --git a/python/paddle/nn/layer/pooling.py b/python/paddle/nn/layer/pooling.py
index a9b5af5199faf0d9af79ca5bceb6d5a8554bd861..3c3abe5e3903f4b2a459c65a52e1f84952e655f6 100755
--- a/python/paddle/nn/layer/pooling.py
+++ b/python/paddle/nn/layer/pooling.py
@@ -1171,7 +1171,6 @@ class MaxUnPool1D(Layer):
 
             import paddle
             import paddle.nn.functional as F
-            import numpy as np
 
             data = paddle.rand(shape=[1, 3, 16])
             pool_out, indices = F.max_pool1d(data, kernel_size=2, stride=2, padding=0, return_mask=True)
@@ -1351,7 +1350,6 @@ class MaxUnPool3D(Layer):
 
             import paddle
             import paddle.nn.functional as F
-            import numpy as np
 
             data = paddle.rand(shape=[1, 1, 4, 4, 6])
             pool_out, indices = F.max_pool3d(data, kernel_size=2, stride=2, padding=0, return_mask=True)
diff --git a/python/paddle/optimizer/adagrad.py b/python/paddle/optimizer/adagrad.py
index a4d9416e93bcc2ff10a444a1d7b4af37582da350..522ca753a99767a25d77058764ba70e6fbf24960 100644
--- a/python/paddle/optimizer/adagrad.py
+++ b/python/paddle/optimizer/adagrad.py
@@ -70,7 +70,6 @@ class Adagrad(Optimizer):
         .. code-block:: python
 
             import paddle
-            import numpy as np
 
             inp = paddle.rand(shape=[10, 10])
             linear = paddle.nn.Linear(10, 10)
diff --git a/python/paddle/regularizer.py b/python/paddle/regularizer.py
index 395ec08a36848c1aed215fe84f7c3d7594e24f73..38060b8233fdbaf286876a0f9e408153b627e72f 100644
--- a/python/paddle/regularizer.py
+++ b/python/paddle/regularizer.py
@@ -105,7 +105,6 @@ class L2Decay(fluid.regularizer.L2Decay):
             # Example1: set Regularizer in optimizer
             import paddle
             from paddle.regularizer import L2Decay
-            import numpy as np
             linear = paddle.nn.Linear(10, 10)
             inp = paddle.rand(shape=[10, 10], dtype="float32")
             out = linear(inp)