fix 2.0 api docs (PaddlePaddle#2849)

doc/paddle/api/paddle/fluid/layers/prelu_cn.rst

@@ -3,16 +3,12 @@
 prelu
 -------------------------------
 
+.. py:function:: paddle.static.nn.prelu(x, mode, param_attr=None, name=None)
 
-.. py:function:: paddle.fluid.layers.prelu(x, mode, param_attr=None, name=None)
-
-
-
-
-等式：
+prelu激活函数
 
 .. math::
-    y = max(0, x) + \alpha min(0, x)
+    prelu(x) = max(0, x) + \alpha * min(0, x)
 
 共提供三种激活方式：
 
@@ -24,27 +20,23 @@ prelu
 
 
 参数：
-          - **x** （Variable）- 多维Tensor或LoDTensor，数据类型为float32。
-          - **mode** (str) - 权重共享模式。
-          - **param_attr** (ParamAttr，可选) - 可学习权重 :math:`[\alpha]` 的参数属性，可由ParamAttr创建。默认值为None，表示使用默认的权重参数属性。具体用法请参见 :ref:`cn_api_fluid_ParamAttr` 。
-          - **name** (str，可选) – 具体用法请参见 :ref:`api_guide_Name` ，一般无需设置，默认值为None。 
+    - **x** （Tensor）- 多维Tensor或LoDTensor，数据类型为float32。
+    - **mode** (str) - 权重共享模式。
+    - **param_attr** (ParamAttr，可选) - 可学习权重 :math:`[\alpha]` 的参数属性，可由ParamAttr创建。默认值为None，表示使用默认的权重参数属性。具体用法请参见 :ref:`cn_api_fluid_ParamAttr` 。
+    - **name** (str，可选) – 具体用法请参见 :ref:`api_guide_Name` ，一般无需设置，默认值为None。 
 
 
-返回： 表示激活输出Tensor或LoDTensor，数据类型为float32。与输入形状相同。
-
-
-返回类型：Variable
-
+返回： 表示激活输出Tensor，数据类型和形状于输入相同。
 
 **代码示例：**
 
 .. code-block:: python
 
-    import paddle.fluid as fluid
-    from paddle.fluid.param_attr import ParamAttr
-    x = fluid.data(name="x", shape=[None,5,10,10], dtype="float32")
-    mode = 'channel'
-    output = fluid.layers.prelu(
-             x,mode,param_attr=ParamAttr(name='alpha'))
+    import paddle
+
+    x = paddle.to_tensor([-1., 2., 3.])
+    param = paddle.ParamAttr(initializer=paddle.nn.initializer.Constant(0.2))
+    out = paddle.static.nn.prelu(x, 'all', param)
+    # [-0.2, 2., 3.]
 
 

doc/paddle/api/paddle/nn/functional/activation/elu_cn.rst

@@ -32,11 +32,8 @@ elu激活层（ELU Activation Operator）
 
     import paddle
     import paddle.nn.functional as F
-    import numpy as np
 
-    x = paddle.to_tensor(np.array([[-1,6],[1,15.6]]))
-    out = F.elu(x, alpha=0.2) 
+    x = paddle.to_tensor([[-1., 6.], [1., 15.6]])
+    out = F.elu(x, alpha=0.2)
     # [[-0.12642411  6.        ]
     #  [ 1.          15.6      ]]
-
-

doc/paddle/api/paddle/nn/functional/activation/gelu_cn.rst

@@ -38,9 +38,12 @@ gelu激活层（GELU Activation Operator）
 
     import paddle
     import paddle.nn.functional as F
-    import numpy as np
 
-    x = paddle.to_tensor(np.array([[-1, 0.5],[1, 1.5]]))
-    out1 = F.gelu(x) # [-0.158655 0.345731 0.841345 1.39979]
-    out2 = F.gelu(x, True) # [-0.158808 0.345714 0.841192 1.39957]
+    x = paddle.to_tensor([[-1, 0.5], [1, 1.5]])
+    out1 = F.gelu(x)
+    # [[-0.15865529,  0.34573123],
+    #  [ 0.84134471,  1.39978933]]
+    out2 = F.gelu(x, True)
+    # [[-0.15880799,  0.34571400],
+    #  [ 0.84119201,  1.39957154]]
 

doc/paddle/api/paddle/nn/functional/activation/leaky_relu_cn.rst

@@ -35,9 +35,6 @@ leaky_relu激活层。计算公式如下：
 
     import paddle
     import paddle.nn.functional as F
-    import numpy as np
 
-    paddle.disable_static()
-
-    x = paddle.to_tensor(np.array([-2, 0, 1], 'float32'))
+    x = paddle.to_tensor([-2., 0., 1.])
     out = F.leaky_relu(x) # [-0.02, 0., 1.]

doc/paddle/api/paddle/nn/functional/activation/log_softmax_cn.rst

@@ -8,7 +8,10 @@ log_softmax
 
 .. math::
 
-    Out[i, j] = log(softmax(x)) = log(\frac{\exp(X[i, j])}{\sum_j(exp(X[i, j])})
+    \begin{aligned} 
+    log\_softmax[i, j] &= log(softmax(x)) \\
+    &= log(\frac{\exp(X[i, j])}{\sum_j(\exp(X[i, j])})
+    \end{aligned}
 
 参数
 ::::::::::
@@ -28,16 +31,13 @@ log_softmax
 
     import paddle
     import paddle.nn.functional as F
-    import numpy as np
 
-    paddle.disable_static()
-
-    x = np.array([[[-2.0, 3.0, -4.0, 5.0],
-                    [3.0, -4.0, 5.0, -6.0],
-                    [-7.0, -8.0, 8.0, 9.0]],
-                    [[1.0, -2.0, -3.0, 4.0],
-                    [-5.0, 6.0, 7.0, -8.0],
-                    [6.0, 7.0, 8.0, 9.0]]]).astype('float32')
+    x = [[[-2.0, 3.0, -4.0, 5.0],
+            [3.0, -4.0, 5.0, -6.0],
+            [-7.0, -8.0, 8.0, 9.0]],
+            [[1.0, -2.0, -3.0, 4.0],
+            [-5.0, 6.0, 7.0, -8.0],
+            [6.0, 7.0, 8.0, 9.0]]]
     x = paddle.to_tensor(x)
     out1 = F.log_softmax(x)
     out2 = F.log_softmax(x, dtype='float64')

doc/paddle/api/paddle/nn/functional/loss/hsigmoid_loss_cn.rst

@@ -30,8 +30,8 @@ hsigmoid_loss
     - **num_classes** (int) - 类别总数(字典大小)必须大于等于2。若使用默认树结构，即当 ``path_table`` 和 ``path_code`` 都为None时 ，必须设置该参数。若使用自定义树结构，即当 ``path_table`` 和 ``path_code`` 都不为None时，它取值应为自定义树结构的非叶节点的个数，用于指定二分类的类别总数。
     - **weight** (Tensor) - 该OP的权重参数。形状为 ``[numclasses-1, D]`` ，数据类型和 ``input`` 相同。
     - **bias** (Tensor, 可选) - 该OP的偏置参数。形状为 ``[numclasses-1, 1]`` ，数据类型和 ``input`` 相同。如果设置为None，将没有偏置参数。默认值为None。
-    - **path_table** (Variable，可选) – 存储每一批样本从类别（单词）到根节点的路径，按照从叶至根方向存储。 数据类型为int64，形状为 ``[N, L]`` ，其中L为路径长度。``path_table`` 和 ``path_code`` 应具有相同的形状, 对于每个样本i，path_table[i]为一个类似np.ndarray的结构，该数组内的每个元素都是其双亲结点权重矩阵的索引。默认值为None。
-    - **path_code** (Variable，可选) – 存储每一批样本从类别（单词）到根节点的路径编码，按从叶至根方向存储。数据类型为int64，形状为 ``[N, L]``。默认值为None。
+    - **path_table** (Tensor，可选) – 存储每一批样本从类别（单词）到根节点的路径，按照从叶至根方向存储。 数据类型为int64，形状为 ``[N, L]`` ，其中L为路径长度。``path_table`` 和 ``path_code`` 应具有相同的形状, 对于每个样本i，path_table[i]为一个类似np.ndarray的结构，该数组内的每个元素都是其双亲结点权重矩阵的索引。默认值为None。
+    - **path_code** (Tensor，可选) – 存储每一批样本从类别（单词）到根节点的路径编码，按从叶至根方向存储。数据类型为int64，形状为 ``[N, L]``。默认值为None。
     - **is_sparse** (bool，可选) – 是否使用稀疏更新方式。如果设置为True，W的梯度和输入梯度将会变得稀疏。默认值为False。
     - **name** (str，可选) – 具体用法请参见 :ref:`api_guide_Name` ，一般无需设置，默认值为None。
 

doc/paddle/api/paddle/nn/layer/activation/ELU_cn.rst

@@ -30,9 +30,8 @@ ELU激活层（ELU Activation Operator）
 .. code-block:: python
 
     import paddle
-    import numpy as np
 
-    x = paddle.to_tensor(np.array([[-1, 6],[1, 15.6]]))
+    x = paddle.to_tensor([[-1. ,6.], [1., 15.6]])
     m = paddle.nn.ELU(0.2)
     out = m(x)
     # [[-0.12642411  6.        ]

doc/paddle/api/paddle/nn/layer/activation/Hardshrink_cn.rst

@@ -34,7 +34,7 @@ Hardshrink激活层
 .. code-block:: python
 
     import paddle
-    paddle.disable_static()
+
     x = paddle.to_tensor([-1, 0.3, 2.5])
     m = paddle.nn.Hardshrink()
     out = m(x) # [-1., 0., 2.5]

doc/paddle/api/paddle/nn/layer/activation/Hardsigmoid_cn.rst

@@ -36,6 +36,6 @@ Hardsigmoid激活层。sigmoid的分段线性逼近激活函数，速度比sigmo
 
     import paddle
 
-    m = paddle.nn.Sigmoid()
+    m = paddle.nn.Hardsigmoid()
     x = paddle.to_tensor([-4., 5., 1.])
     out = m(x) # [0., 1, 0.666667]

doc/paddle/api/paddle/nn/layer/activation/Hardtanh_cn.rst

@@ -36,8 +36,7 @@ Hardtanh激活层（Hardtanh Activation Operator）。计算公式如下：
 .. code-block:: python
 
     import paddle
-    import numpy as np
 
-    x = paddle.to_tensor(np.array([-1.5, 0.3, 2.5]))
+    x = paddle.to_tensor([-1.5, 0.3, 2.5])
     m = paddle.nn.Hardtanh()
-    out = m(x) # # [-1., 0.3, 1.]
+    out = m(x) # [-1., 0.3, 1.]

doc/paddle/api/paddle/nn/layer/activation/LogSoftmax_cn.rst

@@ -8,8 +8,10 @@ LogSoftmax激活层，计算公式如下：
 
 .. math::
 
-    Out[i, j] = log(softmax(x)) 
-              = log(\\frac{\exp(X[i, j])}{\sum_j(exp(X[i, j])})
+    \begin{aligned} 
+    Out[i, j] &= log(softmax(x)) \\
+    &= log(\frac{\exp(X[i, j])}{\sum_j(\exp(X[i, j])})
+    \end{aligned}
 
 参数
 ::::::::::
@@ -26,16 +28,13 @@ LogSoftmax激活层，计算公式如下：
 .. code-block:: python
 
     import paddle
-    import numpy as np
 
-    paddle.disable_static()
-
-    x = np.array([[[-2.0, 3.0, -4.0, 5.0],
-                    [3.0, -4.0, 5.0, -6.0],
-                    [-7.0, -8.0, 8.0, 9.0]],
-                    [[1.0, -2.0, -3.0, 4.0],
-                    [-5.0, 6.0, 7.0, -8.0],
-                    [6.0, 7.0, 8.0, 9.0]]], 'float32')
+    x = [[[-2.0, 3.0, -4.0, 5.0],
+          [3.0, -4.0, 5.0, -6.0],
+          [-7.0, -8.0, 8.0, 9.0]],
+         [[1.0, -2.0, -3.0, 4.0],
+          [-5.0, 6.0, 7.0, -8.0],
+          [6.0, 7.0, 8.0, 9.0]]]
     m = paddle.nn.LogSoftmax()
     x = paddle.to_tensor(x)
     out = m(x)

doc/paddle/api/paddle/nn/layer/activation/ReLU_cn.rst

@@ -27,8 +27,7 @@ ReLU激活层（Rectified Linear Unit）。计算公式如下：
 .. code-block:: python
 
     import paddle
-    import numpy as np
 
-    x = paddle.to_tensor(np.array([-2, 0, 1]).astype('float32'))
+    x = paddle.to_tensor([-2., 0., 1.])
     m = paddle.nn.ReLU()
     out = m(x) # [0., 0., 1.]

doc/paddle/api/paddle/tensor/creation/arange_cn.rst

@@ -5,9 +5,6 @@ arange
 
 .. py:function:: paddle.arange(start=0, end=None, step=1, dtype=None, name=None)
 
-
-
-
 该OP返回以步长 ``step`` 均匀分隔给定数值区间[``start``, ``end``)的1-D Tensor，数据类型为 ``dtype``。
 
 当 ``dtype`` 表示浮点类型时，为了避免浮点计算误差，建议给 ``end`` 加上一个极小值epsilon，使边界可以更加明确。
@@ -33,21 +30,18 @@ arange
 
 .. code-block:: python
 
-        import paddle
-        import numpy as np
-
-        paddle.enable_imperative()
+    import paddle
 
-        out1 = paddle.arange(5)
-        # [0, 1, 2, 3, 4]
+    out1 = paddle.arange(5)
+    # [0, 1, 2, 3, 4]
 
-        out2 = paddle.arange(3, 9, 2.0)
-        # [3, 5, 7]
+    out2 = paddle.arange(3, 9, 2.0)
+    # [3, 5, 7]
 
-        # use 4.999 instead of 5.0 to avoid floating point rounding errors
-        out3 = paddle.arange(4.999, dtype='float32')
-        # [0., 1., 2., 3., 4.]
+    # use 4.999 instead of 5.0 to avoid floating point rounding errors
+    out3 = paddle.arange(4.999, dtype='float32')
+    # [0., 1., 2., 3., 4.]
 
-        start_var = paddle.imperative.to_variable(np.array([3]))
-        out4 = paddle.arange(start_var, 7)
-        # [3, 4, 5, 6]
+    start_var = paddle.to_tensor([3])
+    out4 = paddle.arange(start_var, 7)
+    # [3, 4, 5, 6]

doc/paddle/api/paddle/tensor/creation/ones_like_cn.rst

@@ -28,10 +28,7 @@ ones_like
 .. code-block:: python
 
     import paddle
-    import numpy as np
 
-    paddle.enable_imperative()
-
-    x = paddle.imperative.to_variable(np.array([1,2,3], dtype='float32'))
+    x = paddle.to_tensor([1,2,3])
     out1 = paddle.ones_like(x) # [1., 1., 1.]
     out2 = paddle.ones_like(x, dtype='int32') # [1, 1, 1]

doc/paddle/api/paddle/tensor/creation/zeros_like_cn.rst

@@ -28,10 +28,7 @@ zeros_like
 .. code-block:: python
 
     import paddle
-    import numpy as np
 
-    paddle.enable_imperative()
-
-    x = paddle.imperative.to_variable(np.array([1,2,3], dtype='float32'))
+    x = paddle.to_tensor([1, 2, 3])
     out1 = paddle.zeros_like(x) # [0., 0., 0.]
     out2 = paddle.zeros_like(x, dtype='int32') # [0, 0, 0]

doc/paddle/api/paddle/tensor/random/normal_cn.rst

@@ -31,18 +31,15 @@ normal
 .. code-block:: python
 
     import paddle
-    import numpy as np
-
-    paddle.disable_static()
 
     out1 = paddle.normal(shape=[2, 3])
     # [[ 0.17501129  0.32364586  1.561118  ]  # random
     #  [-1.7232178   1.1545963  -0.76156676]]  # random
 
-    mean_tensor = paddle.to_tensor(np.array([1.0, 2.0, 3.0]))
+    mean_tensor = paddle.to_tensor([1.0, 2.0, 3.0])
     out2 = paddle.normal(mean=mean_tensor)
     # [ 0.18644847 -1.19434458  3.93694787]  # random
 
-    std_tensor = paddle.to_tensor(np.array([1.0, 2.0, 3.0]))
+    std_tensor = paddle.to_tensor([1.0, 2.0, 3.0])
     out3 = paddle.normal(mean=mean_tensor, std=std_tensor)
     # [1.00780561 3.78457445 5.81058198]  # random

doc/paddle/api/paddle/tensor/random/rand_cn.rst

@@ -23,17 +23,15 @@ rand
 .. code-block:: python
 
     import paddle
-    import numpy as np
 
-    paddle.disable_static()
     # example 1: attr shape is a list which doesn't contain Tensor.
     out1 = paddle.rand(shape=[2, 3])
     # [[0.451152  , 0.55825245, 0.403311  ],  # random
     #  [0.22550228, 0.22106001, 0.7877319 ]]  # random
 
     # example 2: attr shape is a list which contains Tensor.
-    dim1 = paddle.full([1], 2, "int64")
-    dim2 = paddle.full([1], 3, "int32")
+    dim1 = paddle.to_tensor([2], 'int64')
+    dim2 = paddle.to_tensor([3], 'int32')
     out2 = paddle.rand(shape=[dim1, dim2, 2])
     # [[[0.8879919 , 0.25788337],  # random
     #   [0.28826773, 0.9712097 ],  # random
@@ -43,7 +41,7 @@ rand
     #   [0.870881  , 0.2984597 ]]]  # random
 
     # example 3: attr shape is a Tensor, the data type must be int64 or int32.
-    shape_tensor = paddle.to_tensor(np.array([2, 3]))
-    out2 = paddle.rand(shape_tensor)
+    shape_tensor = paddle.to_tensor([2, 3])
+    out3 = paddle.rand(shape_tensor)
     # [[0.22920267, 0.841956  , 0.05981819],  # random
     #  [0.4836288 , 0.24573246, 0.7516129 ]]  # random

doc/paddle/api/paddle/tensor/random/randint_cn.rst

@@ -25,9 +25,6 @@ randint
 .. code-block:: python
 
     import paddle
-    import numpy as np
-
-    paddle.disable_static()
 
     # example 1:
     # attr shape is a list which doesn't contain Tensor.
@@ -36,15 +33,15 @@ randint
 
     # example 2:
     # attr shape is a list which contains Tensor.
-    dim1 = paddle.full([1], 2, "int64")
-    dim2 = paddle.full([1], 3, "int32")
-    out2 = paddle.randint(low=-5, high=5, shape=[dim1, dim2], dtype="int32")
+    dim1 = paddle.to_tensor([2], 'int64')
+    dim2 = paddle.to_tensor([3], 'int32')
+    out2 = paddle.randint(low=-5, high=5, shape=[dim1, dim2])
     # [[0, -1, -3],  # random
     #  [4, -2,  0]]  # random
 
     # example 3:
     # attr shape is a Tensor
-    shape_tensor = paddle.to_tensor(np.array([3]))
+    shape_tensor = paddle.to_tensor(3)
     out3 = paddle.randint(low=-5, high=5, shape=shape_tensor)
     # [-2, 2, 3]  # random