diff --git a/python/paddle/sparse/binary.py b/python/paddle/sparse/binary.py
index 45c39e874a54c213caf01562f3037046ea89c0b2..2d6b36922f3a4ed494885a7cd837fc812cbc9d4c 100644
--- a/python/paddle/sparse/binary.py
+++ b/python/paddle/sparse/binary.py
@@ -239,17 +239,15 @@ def add(x, y, name=None):
     ..  code-block:: python
 
         import paddle
-        from paddle.fluid.framework import _test_eager_guard
 
         paddle.device.set_device("cpu")
 
-        with _test_eager_guard():
-            x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
-            y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
-            sparse_x = x.to_sparse_csr()
-            sparse_y = y.to_sparse_csr()
-            sparse_z = paddle.sparse.add(sparse_x, sparse_y)
-            print(sparse_z.to_dense())
+        x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
+        y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
+        sparse_x = x.to_sparse_csr()
+        sparse_y = y.to_sparse_csr()
+        sparse_z = paddle.sparse.add(sparse_x, sparse_y)
+        print(sparse_z.to_dense())
 
         # [[ 0., -1.,  0.,  0.],
         # [ 0.,  2., -6.,  0.],
@@ -295,17 +293,15 @@ def subtract(x, y, name=None):
     ..  code-block:: python
 
         import paddle
-        from paddle.fluid.framework import _test_eager_guard
 
         paddle.device.set_device("cpu")
 
-        with _test_eager_guard():
-            x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
-            y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
-            sparse_x = x.to_sparse_csr()
-            sparse_y = y.to_sparse_csr()
-            sparse_z = paddle.sparse.subtract(sparse_x, sparse_y)
-            print(sparse_z.to_dense())
+        x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
+        y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
+        sparse_x = x.to_sparse_csr()
+        sparse_y = y.to_sparse_csr()
+        sparse_z = paddle.sparse.subtract(sparse_x, sparse_y)
+        print(sparse_z.to_dense())
 
         # [[ 0., -1.,  0.,  4.],
         # [ 0., -2.,  0.,  0.],
@@ -340,17 +336,15 @@ def multiply(x, y, name=None):
     ..  code-block:: python
 
         import paddle
-        from paddle.fluid.framework import _test_eager_guard
 
         paddle.device.set_device("cpu")
 
-        with _test_eager_guard():
-            x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
-            y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
-            sparse_x = x.to_sparse_csr()
-            sparse_y = y.to_sparse_csr()
-            sparse_z = paddle.sparse.multiply(sparse_x, sparse_y)
-            print(sparse_z.to_dense())
+        x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
+        y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
+        sparse_x = x.to_sparse_csr()
+        sparse_y = y.to_sparse_csr()
+        sparse_z = paddle.sparse.multiply(sparse_x, sparse_y)
+        print(sparse_z.to_dense())
 
         # [[ 0.,  0.,  0., -4.],
         # [ 0.,  0.,  9.,  0.],
@@ -388,17 +382,15 @@ def divide(x, y, name=None):
     ..  code-block:: python
 
         import paddle
-        from paddle.fluid.framework import _test_eager_guard
 
         paddle.device.set_device("cpu")
 
-        with _test_eager_guard():
-            x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
-            y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
-            sparse_x = x.to_sparse_csr()
-            sparse_y = y.to_sparse_csr()
-            sparse_z = paddle.sparse.divide(sparse_x, sparse_y)
-            print(sparse_z.to_dense())
+        x = paddle.to_tensor([[0, -1, 0, 2], [0, 0, -3, 0], [4, 5, 0, 0]], 'float32')
+        y = paddle.to_tensor([[0, 0, 0, -2], [0, 2, -3, 0], [2, 3, 4, 8]], 'float32')
+        sparse_x = x.to_sparse_csr()
+        sparse_y = y.to_sparse_csr()
+        sparse_z = paddle.sparse.divide(sparse_x, sparse_y)
+        print(sparse_z.to_dense())
 
         # [[ nan      , -inf.     ,  nan      , -1.       ],
         # [ nan      ,  0.       ,  1.       ,  nan      ],
diff --git a/python/paddle/sparse/creation.py b/python/paddle/sparse/creation.py
index 684d449af7126b1e13bdbaa48da99cdba440832a..6f0c9cb42e430abcd2ade370cae59a497fa0e36f 100644
--- a/python/paddle/sparse/creation.py
+++ b/python/paddle/sparse/creation.py
@@ -98,18 +98,16 @@ def sparse_coo_tensor(
     .. code-block:: python
 
         import paddle
-        from paddle.fluid.framework import _test_eager_guard
-
-        with _test_eager_guard():
-            indices = [[0, 1, 2], [1, 2, 0]]
-            values = [1.0, 2.0, 3.0]
-            dense_shape = [3, 3]
-            coo = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape)
-            # print(coo)
-            # Tensor(shape=[2, 3], dtype=paddle.float32, place=Place(gpu:0), stop_gradient=True,
-            #       indices=[[0, 1, 2],
-            #                [1, 2, 0]],
-            #       values=[1., 2., 3.])
+
+        indices = [[0, 1, 2], [1, 2, 0]]
+        values = [1.0, 2.0, 3.0]
+        dense_shape = [3, 3]
+        coo = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape)
+        # print(coo)
+        # Tensor(shape=[2, 3], dtype=paddle.float32, place=Place(gpu:0), stop_gradient=True,
+        #       indices=[[0, 1, 2],
+        #                [1, 2, 0]],
+        #       values=[1., 2., 3.])
     """
 
     if in_dynamic_mode():
@@ -218,19 +216,17 @@ def sparse_csr_tensor(
     .. code-block:: python
 
         import paddle
-        from paddle.fluid.framework import _test_eager_guard
-
-        with _test_eager_guard():
-            crows = [0, 2, 3, 5]
-            cols = [1, 3, 2, 0, 1]
-            values = [1, 2, 3, 4, 5]
-            dense_shape = [3, 4]
-            csr = paddle.sparse.sparse_csr_tensor(crows, cols, values, dense_shape)
-            # print(csr)
-            # Tensor(shape=[3, 4], dtype=paddle.int64, place=Place(gpu:0), stop_gradient=True,
-            #       crows=[0, 2, 3, 5],
-            #       cols=[1, 3, 2, 0, 1],
-            #       values=[1, 2, 3, 4, 5])
+
+        crows = [0, 2, 3, 5]
+        cols = [1, 3, 2, 0, 1]
+        values = [1, 2, 3, 4, 5]
+        dense_shape = [3, 4]
+        csr = paddle.sparse.sparse_csr_tensor(crows, cols, values, dense_shape)
+        # print(csr)
+        # Tensor(shape=[3, 4], dtype=paddle.int64, place=Place(gpu:0), stop_gradient=True,
+        #       crows=[0, 2, 3, 5],
+        #       cols=[1, 3, 2, 0, 1],
+        #       values=[1, 2, 3, 4, 5])
     """
 
     place = _get_place(place)
diff --git a/python/paddle/sparse/nn/functional/conv.py b/python/paddle/sparse/nn/functional/conv.py
index ec1907a7770c8be33f900c18d440ac7ac66258fb..4e7cbd7caad40b1ca80c0ea686f46ad79bc7095a 100644
--- a/python/paddle/sparse/nn/functional/conv.py
+++ b/python/paddle/sparse/nn/functional/conv.py
@@ -149,36 +149,17 @@ def conv3d(
     * :math:`b`: Bias value, a 1-D tensor with shape [M].
     * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different.
 
-    Example:
-
-        - Input:
-
-          Input shape: :math:`(N, D_{in}, H_{in}, W_{in}, C_{in})`
-
-          Filter shape: :math:`(D_f, H_f, W_f, C_{in}, C_{out})`
-
-        - Output:
-          Output shape: :math:`(N, D_{out}, H_{out}, W_{out}, C_{out})`
-
-        Where
-
-        ..  math::
-
-            D_{out}&= \\frac{(D_{in} + 2 * paddings[0] - (dilations[0] * (D_f - 1) + 1))}{strides[0]} + 1 \\\\
-            H_{out}&= \\frac{(H_{in} + 2 * paddings[1] - (dilations[1] * (H_f - 1) + 1))}{strides[1]} + 1 \\\\
-            W_{out}&= \\frac{(W_{in} + 2 * paddings[2] - (dilations[2] * (W_f - 1) + 1))}{strides[2]} + 1
-
     Args:
         x (Tensor): The input is 5-D SparseCooTensor with shape [N, D, H, W, C], the data
             type of input is float16 or float32 or float64.
         weight (Tensor): The convolution kernel, a Tensor with shape [kD, kH, kW, C/g, M],
             where M is the number of filters(output channels), g is the number of groups,
             kD, kH, kW are the filter's depth, height and width respectively.
-        bias (Tensor, optional): The bias, a Tensor of shape [M, ], currently, only support bias is None.
-        stride (int|list|tuple): The stride size. It means the stride in convolution. If stride is a
+        bias (Tensor, optional): The bias, a Tensor of shape [M].
+        stride (int|list|tuple, optional): The stride size. It means the stride in convolution. If stride is a
             list/tuple, it must contain three integers, (stride_depth, stride_height, stride_width).
             Otherwise, stride_depth = stride_height = stride_width = stride. Default: stride = 1.
-        padding (string|int|list|tuple): The padding size. It means the number of zero-paddings
+        padding (string|int|list|tuple, optional): The padding size. It means the number of zero-paddings
             on both sides for each dimension. If `padding` is a string, either 'VALID' or
             'SAME' which is the padding algorithm. If padding size is a tuple or list,
             it could be in three forms: `[pad_depth, pad_height, pad_width]` or
@@ -188,11 +169,11 @@ def conv3d(
             when `data_format` is `"NDHWC"`, `padding` can be in the form
             `[[0,0], [pad_depth_front, pad_depth_back], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]`.
             Default: padding = 0.
-        dilation (int|list|tuple): The dilation size. It means the spacing between the kernel points.
+        dilation (int|list|tuple, optional): The dilation size. It means the spacing between the kernel points.
             If dilation is a list/tuple, it must contain three integers, (dilation_depth, dilation_height,
             dilation_width). Otherwise, dilation_depth = dilation_height = dilation_width = dilation.
             Default: dilation = 1.
-        groups (int): The groups number of the Conv3D Layer. According to grouped
+        groups (int, optional): The groups number of the Conv3D Layer. According to grouped
             convolution in Alex Krizhevsky's Deep CNN paper: when group=2,
             the first half of the filters is only connected to the first half
             of the input channels, while the second half of the filters is only
@@ -201,7 +182,7 @@ def conv3d(
             will be consistent with that of the input. An optional string from: `"NCDHW"`, `"NDHWC"`.
             The default is `"NDHWC"`. When it is `"NDHWC"`, the data is stored in the order of:
             `[batch_size, input_depth, input_height, input_width, input_channels]`.
-        name(str|None): For detailed information, please refer
+        name(str, optional): For detailed information, please refer
            to :ref:`api_guide_Name`. Usually name is no need to set and
            None by default.
 
@@ -212,19 +193,17 @@ def conv3d(
         .. code-block:: python
 
             import paddle
-            from paddle.fluid.framework import _test_eager_guard
-
-            with _test_eager_guard():
-              indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
-              values = [[1], [2], [3], [4]]
-              indices = paddle.to_tensor(indices, dtype='int32')
-              values = paddle.to_tensor(values, dtype='float32')
-              dense_shape = [1, 1, 3, 4, 1]
-              sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
-              weight = paddle.randn((1, 3, 3, 1, 1), dtype='float32')
-              y = paddle.sparse.nn.functional.conv3d(sparse_x, weight)
-              print(y.shape)
-              # (1, 1, 1, 2, 1)
+
+            indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
+            values = [[1], [2], [3], [4]]
+            indices = paddle.to_tensor(indices, dtype='int32')
+            values = paddle.to_tensor(values, dtype='float32')
+            dense_shape = [1, 1, 3, 4, 1]
+            sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
+            weight = paddle.randn((1, 3, 3, 1, 1), dtype='float32')
+            y = paddle.sparse.nn.functional.conv3d(sparse_x, weight)
+            print(y.shape)
+            # (1, 1, 1, 2, 1)
     """
     return _conv3d(
         x,
@@ -277,33 +256,14 @@ def subm_conv3d(
     * :math:`b`: Bias value, a 1-D tensor with shape [M].
     * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different.
 
-    Example:
-
-        - Input:
-
-          Input shape: :math:`(N, D_{in}, H_{in}, W_{in}, C_{in})`
-
-          Filter shape: :math:`(D_f, H_f, W_f, C_{in}, C_{out})`
-
-        - Output:
-          Output shape: :math:`(N, D_{out}, H_{out}, W_{out}, C_{out})`
-
-        Where
-
-        ..  math::
-
-            D_{out}&= \\frac{(D_{in} + 2 * paddings[0] - (dilations[0] * (D_f - 1) + 1))}{strides[0]} + 1 \\\\
-            H_{out}&= \\frac{(H_{in} + 2 * paddings[1] - (dilations[1] * (H_f - 1) + 1))}{strides[1]} + 1 \\\\
-            W_{out}&= \\frac{(W_{in} + 2 * paddings[2] - (dilations[2] * (W_f - 1) + 1))}{strides[2]} + 1
-
     Args:
         x (Tensor): The input is 5-D SparseCooTensor with shape [N, D, H, W, C], the data
             type of input is float16 or float32 or float64.
         weight (Tensor): The convolution kernel, a Tensor with shape [kD, kH, kW, C/g, M],
             where M is the number of filters(output channels), g is the number of groups,
             kD, kH, kW are the filter's depth, height and width respectively.
-        bias (Tensor, optional): The bias, a Tensor of shape [M, ], currently, only support bias is None.
-        stride (int|list|tuple): The stride size. It means the stride in convolution. If stride is a
+        bias (Tensor, optional): The bias, a Tensor of shape [M].
+        stride (int|list|tuple, optional): The stride size. It means the stride in convolution. If stride is a
             list/tuple, it must contain three integers, (stride_depth, stride_height, stride_width).
             Otherwise, stride_depth = stride_height = stride_width = stride. Default: stride = 1.
         padding (string|int|list|tuple): The padding size. It means the number of zero-paddings
@@ -316,11 +276,11 @@ def subm_conv3d(
             when `data_format` is `"NHWC"`, `padding` can be in the form
             `[[0,0], [pad_depth_front, pad_depth_back], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]`.
             Default: padding = 0.
-        dilation (int|list|tuple): The dilation size. It means the spacing between the kernel points.
+        dilation (int|list|tuple, optional): The dilation size. It means the spacing between the kernel points.
             If dilation is a list/tuple, it must contain three integers, (dilation_depth, dilation_height,
             dilation_width). Otherwise, dilation_depth = dilation_height = dilation_width = dilation.
             Default: dilation = 1.
-        groups (int): The groups number of the Conv3D Layer. According to grouped
+        groups (int, optional): The groups number of the Conv3D Layer. According to grouped
             convolution in Alex Krizhevsky's Deep CNN paper: when group=2,
             the first half of the filters is only connected to the first half
             of the input channels, while the second half of the filters is only
@@ -333,7 +293,7 @@ def subm_conv3d(
             the definition and role of rulebook refers to
             https://pdfs.semanticscholar.org/5125/a16039cabc6320c908a4764f32596e018ad3.pdf. The
             default value is None.
-        name(str|None): For detailed information, please refer
+        name(str, optional): For detailed information, please refer
            to :ref:`api_guide_Name`. Usually name is no need to set and
            None by default.
 
@@ -345,19 +305,17 @@ def subm_conv3d(
         .. code-block:: python
 
             import paddle
-            from paddle.fluid.framework import _test_eager_guard
-
-            with _test_eager_guard():
-              indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
-              values = [[1], [2], [3], [4]]
-              indices = paddle.to_tensor(indices, dtype='int32')
-              values = paddle.to_tensor(values, dtype='float32')
-              dense_shape = [1, 1, 3, 4, 1]
-              sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
-              weight = paddle.randn((1, 3, 3, 1, 1), dtype='float32')
-              y = paddle.sparse.nn.functional.subm_conv3d(sparse_x, weight)
-              print(y.shape)
-              #(1, 1, 3, 4, 1)
+
+            indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
+            values = [[1], [2], [3], [4]]
+            indices = paddle.to_tensor(indices, dtype='int32')
+            values = paddle.to_tensor(values, dtype='float32')
+            dense_shape = [1, 1, 3, 4, 1]
+            sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
+            weight = paddle.randn((1, 3, 3, 1, 1), dtype='float32')
+            y = paddle.sparse.nn.functional.subm_conv3d(sparse_x, weight)
+            print(y.shape)
+            #(1, 1, 3, 4, 1)
     """
     return _conv3d(
         x,
diff --git a/python/paddle/sparse/nn/functional/pooling.py b/python/paddle/sparse/nn/functional/pooling.py
index 740324ea3979d49fb456349248cd6792e30fab2e..98aaad61369629448a492132d549367c4f96ff5b 100644
--- a/python/paddle/sparse/nn/functional/pooling.py
+++ b/python/paddle/sparse/nn/functional/pooling.py
@@ -39,18 +39,18 @@ def max_pool3d(
             is a tuple or list, it must contain three integers,
             (kernel_size_Depth, kernel_size_Height, kernel_size_Width).
             Otherwise, the pool kernel size will be the cube of an int.
-        stride (int|list|tuple): The pool stride size. If pool stride size is a tuple or list,
+        stride (int|list|tuple, optional): The pool stride size. If pool stride size is a tuple or list,
             it must contain three integers, [stride_Depth, stride_Height, stride_Width).
             Otherwise, the pool stride size will be a cube of an int.
-        padding (string|int|list|tuple): The padding size. Padding could be in one of the following forms.
+        padding (string|int|list|tuple, optional): The padding size. Padding could be in one of the following forms.
             1. A string in ['valid', 'same'].
             2. An int, which means the feature map is zero padded by size of `padding` on every sides.
             3. A list[int] or tuple(int) whose length is 3, [pad_depth, pad_height, pad_weight] whose value means the padding size of each dimension.
             4. A list[int] or tuple(int) whose length is 6. [pad_depth_front, pad_depth_back, pad_height_top, pad_height_bottom, pad_width_left, pad_width_right] whose value means the padding size of each side.
             5. A list or tuple of pairs of integers. It has the form [[pad_before, pad_after], [pad_before, pad_after], ...]. Note that, the batch dimension and channel dimension should be [0,0] or (0,0).
             The default value is 0.
-        ceil_mode (bool): ${ceil_mode_comment}
-        data_format (string): The data format of the input and output data. An optional string from: `"NCDHW"`, `"NDHWC"`.
+        ceil_mode (bool, optional): ${ceil_mode_comment}
+        data_format (string, optional): The data format of the input and output data. An optional string from: `"NCDHW"`, `"NDHWC"`.
                         The default is `"NCDHW"`. When it is `"NCDHW"`, the data is stored in the order of:
                         `[batch_size, input_channels, input_depth, input_height, input_width]`. Currently only support `"NDHWC"` .
         name(str, optional): For detailed information, please refer
@@ -64,16 +64,14 @@ def max_pool3d(
         .. code-block:: python
 
             import paddle
-            from paddle.fluid.framework import _test_eager_guard
 
-            with _test_eager_guard():
-                dense_x = paddle.randn((1, 4, 4, 4, 3))
-                sparse_x = dense_x.to_sparse_coo(4)
-                kernel_sizes = [3, 3, 3]
-                paddings = [0, 0, 0]
-                strides = [1, 1, 1]
-                out = paddle.sparse.nn.functional.max_pool3d(sparse_x, kernel_sizes, stride=strides, padding=paddings)
-                #[1, 2, 2, 2, 3]
+            dense_x = paddle.randn((1, 4, 4, 4, 3))
+            sparse_x = dense_x.to_sparse_coo(4)
+            kernel_sizes = [3, 3, 3]
+            paddings = [0, 0, 0]
+            strides = [1, 1, 1]
+            out = paddle.sparse.nn.functional.max_pool3d(sparse_x, kernel_sizes, stride=strides, padding=paddings)
+            #[1, 2, 2, 2, 3]
     """
 
     assert in_dynamic_mode(), "Currently, Sparse API only support dynamic mode"
diff --git a/python/paddle/sparse/nn/layer/conv.py b/python/paddle/sparse/nn/layer/conv.py
index 599fb2d7b2e5cb59bda5171e989816d6fd789b03..451d6611fc9b029f3293866c7b00ce2c354bdd11 100644
--- a/python/paddle/sparse/nn/layer/conv.py
+++ b/python/paddle/sparse/nn/layer/conv.py
@@ -221,19 +221,17 @@ class Conv3D(_Conv3D):
         .. code-block:: python
 
           import paddle
-          from paddle.fluid.framework import _test_eager_guard
-
-          with _test_eager_guard():
-            indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
-            values = [[1], [2], [3], [4]]
-            indices = paddle.to_tensor(indices, dtype='int32')
-            values = paddle.to_tensor(values, dtype='float32')
-            dense_shape = [1, 1, 3, 4, 1]
-            sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
-            conv = paddle.sparse.nn.Conv3D(1, 1, (1, 3, 3))
-            y = conv(sparse_x)
-            print(y.shape)
-            # (1, 1, 1, 2, 1)
+
+          indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
+          values = [[1], [2], [3], [4]]
+          indices = paddle.to_tensor(indices, dtype='int32')
+          values = paddle.to_tensor(values, dtype='float32')
+          dense_shape = [1, 1, 3, 4, 1]
+          sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
+          conv = paddle.sparse.nn.Conv3D(1, 1, (1, 3, 3))
+          y = conv(sparse_x)
+          print(y.shape)
+          # (1, 1, 1, 2, 1)
     """
 
     def __init__(
@@ -269,8 +267,8 @@ class Conv3D(_Conv3D):
 
 class SubmConv3D(_Conv3D):
     r"""
-    **Sparse Submanifold Convlution3d Layer**
-    The Sparse submanifold convolution3d layer calculates the output based on the input, filter
+    **Submanifold Sparse Convlution3d Layer**
+    The submanifold sparse convolution3d layer calculates the output based on the input, filter
     and strides, paddings, dilations, groups parameters. Input(Input) and
     Output(Output) are multidimensional SparseCooTensors with a shape of
     :math:`[N, D, H, W, C]` . Where N is batch size, C is the number of
@@ -281,7 +279,7 @@ class SubmConv3D(_Conv3D):
 
     ..  math::
 
-        Out =(W \ast X + b
+        Out = W \ast X + b
 
     In the above equation:
 
@@ -362,19 +360,17 @@ class SubmConv3D(_Conv3D):
         .. code-block:: python
 
           import paddle
-          from paddle.fluid.framework import _test_eager_guard
-
-          with _test_eager_guard():
-            indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
-            values = [[1], [2], [3], [4]]
-            dense_shape = [1, 1, 3, 4, 1]
-            indices = paddle.to_tensor(indices, dtype='int32')
-            values = paddle.to_tensor(values, dtype='float32')
-            sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
-            subm_conv = paddle.sparse.nn.SubmConv3D(1, 1, (1, 3, 3))
-            y = subm_conv(sparse_x)
-            print(y.shape)
-            # (1, 1, 3, 4, 1)
+
+          indices = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]]
+          values = [[1], [2], [3], [4]]
+          dense_shape = [1, 1, 3, 4, 1]
+          indices = paddle.to_tensor(indices, dtype='int32')
+          values = paddle.to_tensor(values, dtype='float32')
+          sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True)
+          subm_conv = paddle.sparse.nn.SubmConv3D(1, 1, (1, 3, 3))
+          y = subm_conv(sparse_x)
+          print(y.shape)
+          # (1, 1, 3, 4, 1)
     """
 
     def __init__(
diff --git a/python/paddle/sparse/nn/layer/norm.py b/python/paddle/sparse/nn/layer/norm.py
index 99b96fb530aef5f19351e95510356c4677540e77..8bbad41ef38c179f7f21bb9feca28712027306fd 100644
--- a/python/paddle/sparse/nn/layer/norm.py
+++ b/python/paddle/sparse/nn/layer/norm.py
@@ -83,18 +83,16 @@ class BatchNorm(paddle.nn.BatchNorm1D):
         .. code-block:: python
 
           import paddle
-          from paddle.fluid.framework import _test_eager_guard
-
-          with _test_eager_guard():
-              paddle.seed(123)
-              channels = 3
-              x_data = paddle.randn((1, 6, 6, 6, channels)).astype('float32')
-              dense_x = paddle.to_tensor(x_data)
-              sparse_x = dense_x.to_sparse_coo(4)
-              batch_norm = paddle.sparse.nn.BatchNorm(channels)
-              batch_norm_out = batch_norm(sparse_x)
-              print(batch_norm_out.shape)
-              # [1, 6, 6, 6, 3]
+
+          paddle.seed(123)
+          channels = 3
+          x_data = paddle.randn((1, 6, 6, 6, channels)).astype('float32')
+          dense_x = paddle.to_tensor(x_data)
+          sparse_x = dense_x.to_sparse_coo(4)
+          batch_norm = paddle.sparse.nn.BatchNorm(channels)
+          batch_norm_out = batch_norm(sparse_x)
+          print(batch_norm_out.shape)
+          # [1, 6, 6, 6, 3]
     """
 
     def __init__(
@@ -270,6 +268,8 @@ class SyncBatchNorm(paddle.nn.SyncBatchNorm):
              will create ParamAttr as bias_attr. If the Initializer of the bias_attr
              is not set, the bias is initialized zero. If it is set to False, this layer will not
              have trainable bias parameter. Default: None.
+        data_format(str, optional): Specify the input data format, may be "NCHW". Default "NCHW".
+        name(str, optional): Name for the BatchNorm, default is None. For more information, please refer to :ref:`api_guide_Name`..
 
     Shapes:
         input: Tensor that the dimension from 2 to 5.
@@ -282,10 +282,8 @@ class SyncBatchNorm(paddle.nn.SyncBatchNorm):
           # required: gpu
           import paddle
           import paddle.sparse.nn as nn
-          import numpy as np
 
-          x = np.array([[[[0.3, 0.4], [0.3, 0.07]], [[0.83, 0.37], [0.18, 0.93]]]]).astype('float32')
-          x = paddle.to_tensor(x)
+          x = paddle.to_tensor([[[[0.3, 0.4], [0.3, 0.07]], [[0.83, 0.37], [0.18, 0.93]]]], dtype='float32')
           x = x.to_sparse_coo(len(x.shape)-1)
 
           if paddle.is_compiled_with_cuda():
diff --git a/python/paddle/sparse/nn/layer/pooling.py b/python/paddle/sparse/nn/layer/pooling.py
index 7d6141bab0fd53f170f5637a87243ad7309e35f7..340e7e5e1fce1c8598cb0bdf3ce84940390e3b08 100644
--- a/python/paddle/sparse/nn/layer/pooling.py
+++ b/python/paddle/sparse/nn/layer/pooling.py
@@ -61,15 +61,13 @@ class MaxPool3D(Layer):
         .. code-block:: python
 
             import paddle
-            from paddle.fluid.framework import _test_eager_guard
 
-            with _test_eager_guard():
-                dense_x = paddle.randn((2, 3, 6, 6, 3))
-                sparse_x = dense_x.to_sparse_coo(4)
-                max_pool3d = paddle.sparse.nn.MaxPool3D(
-                    kernel_size=3, data_format='NDHWC')
-                out = max_pool3d(sparse_x)
-                #shape=[2, 1, 2, 2, 3]
+            dense_x = paddle.randn((2, 3, 6, 6, 3))
+            sparse_x = dense_x.to_sparse_coo(4)
+            max_pool3d = paddle.sparse.nn.MaxPool3D(
+                kernel_size=3, data_format='NDHWC')
+            out = max_pool3d(sparse_x)
+            #shape=[2, 1, 2, 2, 3]
 
     """
 
diff --git a/python/paddle/sparse/unary.py b/python/paddle/sparse/unary.py
index 14a97d6cb03288c2c1f1715f90c0e910358e4301..9ce5857b57e84afeca720203fc04df88e1f70bf6 100644
--- a/python/paddle/sparse/unary.py
+++ b/python/paddle/sparse/unary.py
@@ -521,12 +521,14 @@ def abs(x, name=None):
 
 
 @dygraph_only
-def coalesce(x):
+def coalesce(x, name=None):
     r"""
     the coalesced operator include sorted and merge, after coalesced, the indices of x is sorted and unique.
 
     Parameters:
         x (Tensor): the input SparseCooTensor.
+        name (str, optional): Name for the operation (optional, default is None).
+            For more information, please refer to :ref:`api_guide_Name`.
 
     Returns:
         Tensor: return the SparseCooTensor after coalesced.