mindspore-Ecosystem
/
mindspore
21
0
Fork 27
Code Issues Pull Requests 6 Projects Releases Wiki Activity

!40082 modify format 

Merge pull request !40082 from 俞涵/code_docs_0707
This commit is contained in:
i-robot 2022-08-09 09:41:54 +00:00 committed by Gitee
parent e3ac847504 a5f415d578
commit 6eb72535ec
No known key found for this signature in database
GPG Key ID: 173E9B9CA92EEF8F
9 changed files with 59 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/api/api_python/ops/mindspore.ops.Custom.rst
View File

@ -5,7 +5,7 @@ mindspore.ops.Custom
`Custom` 算子是MindSpore自定义算子的统一接口。用户可以利用该接口自行定义MindSpore内置算子库尚未包含的算子。
根据输入函数的不用，你可以创建多个自定义算子，并且把它们用在神经网络中。
关于自定义算子的详细说明和介绍，包括参数的正确书写，见编程指南 https://www.mindspore.cn/tutorials/experts/zh-CN/master/operation/op_custom.html 。
关于自定义算子的详细说明和介绍，包括参数的正确书写，见 `教程 <https://www.mindspore.cn/tutorials/experts/zh-CN/master/operation/op_custom.html>`_ 。
.. warning::
这是一个实验性接口，后续可能删除或修改。

2
docs/api/api_python/ops/mindspore.ops.func_scatter_div.rst
View File

@ -17,7 +17,7 @@ mindspore.ops.scatter_div
- **indices** (Tensor) - 指定相除操作的索引，数据类型必须为mindspore.int32或者mindspore.int64。
- **updates** (Tensor) - 指定与 `input_x` 相除的Tensor，数据类型与 `input_x` 相同，shape为 `indices.shape + input_x.shape[1:]` 。
输出：
返回：
Tensor，更新后的 `input_x` ，shape和类型与 `input_x` 相同。
异常：

2
docs/api/api_python/ops/mindspore.ops.func_scatter_max.rst
View File

@ -18,7 +18,7 @@ mindspore.ops.scatter_max
- **indices** (Tensor) - 指定最大值操作的索引，数据类型必须为mindspore.int32或者mindspore.int64。
- **updates** (Tensor) - 指定与 `input_x` 取最大值操作的Tensor，数据类型与 `input_x` 相同，shape为 `indices.shape + input_x.shape[1:]` 。
输出：
返回：
Tensor，更新后的 `input_x` ，shape和类型与 `input_x` 相同。
异常：

2
docs/api/api_python/ops/mindspore.ops.func_scatter_min.rst
View File

@ -18,7 +18,7 @@ mindspore.ops.scatter_min
- **indices** (Tensor) - 指定最小值操作的索引，数据类型必须为mindspore.int32或者mindspore.int64。
- **updates** (Tensor) - 指定与 `input_x` 取最小值操作的Tensor，数据类型与 `input_x` 相同，shape为 `indices.shape + input_x.shape[1:]` 。
输出：
返回：
Tensor，更新后的 `input_x` ，shape和类型与 `input_x` 相同。
异常：

4
mindspore/python/mindspore/ops/composite/array_ops.py
View File

@ -65,7 +65,7 @@ def repeat_elements(x, rep, axis=0):
rep (int): The number of times to repeat, must be positive.
axis (int): The axis along which to repeat, default 0.
Outputs:
Returns:
One tensor with values repeated along the specified axis. If x has shape
(s1, s2, ..., sn) and axis is i, the output will have shape (s1, s2, ...,
si * rep, ..., sn). The output type will be the same as the type of `x`.
@ -142,7 +142,7 @@ def sequence_mask(lengths, maxlen=None):
maxlen (int): size of the last dimension of returned tensor. Must be positive and same
type as elements in `lengths`. Default is None.
Outputs:
Returns:
One mask tensor of shape `lengths.shape + (maxlen,)` .
Raises:

8
mindspore/python/mindspore/ops/composite/math_ops.py
View File

@ -258,7 +258,7 @@ def tensor_dot(x1, x2, axes):
automatically picks up last N dims from `a` input shape and first N dims from `b` input shape in order
as axes for each respectively.
Outputs:
Returns:
Tensor, the shape of the output tensor is :math:`(N + M)`. Where :math:`N` and :math:`M` are the free axes not
contracted in both inputs
@ -346,7 +346,7 @@ def dot(x1, x2):
x2 (Tensor): Second tensor in Dot op with datatype float16 or float32,
The rank must be greater than or equal to 2.
Outputs:
Returns:
Tensor, dot product of x1 and x2.
Raises:
@ -559,7 +559,7 @@ def batch_dot(x1, x2, axes=None):
`a` input shape and last N dimensions from `b` input shape in order as axes for each respectively.
Default: None.
Outputs:
Returns:
Tensor, batch dot product of `x1` and `x2`. For example: The Shape of output
for input `x1` shapes (batch, d1, axes, d2) and `x2` shapes (batch, d3, axes, d4) is (batch, d1, d2, d3, d4),
where d1 and d2 means any number.
@ -779,7 +779,7 @@ def resize_nearest_neighbor(input_x, size, align_corners=False):
align_corners (bool): Whether the centers of the 4 corner pixels of the input
and output tensors are aligned. Default: False.
Outputs:
Returns:
Tensor, the shape of the output tensor is :math:`(N, C, NEW\_H, NEW\_W)`.
The data type is the same as the `input_x`.

10
mindspore/python/mindspore/ops/function/array_func.py
View File

@ -1237,7 +1237,7 @@ def squeeze(input_x, axis=()):
all the dimensions of size 1 in the given axis parameter. If specified, it must be int32 or int64.
Default: (), an empty tuple.
Outputs:
Returns:
Tensor, the shape of tensor is :math:`(x_1, x_2, ..., x_S)`.
Raises:
@ -1419,7 +1419,7 @@ def scatter_max(input_x, indices, updates):
updates (Tensor): The tensor doing the max operation with `input_x`,
the data type is same as `input_x`, the shape is `indices.shape + x.shape[1:]`.
Outputs:
Returns:
Tensor, the updated `input_x`, the type and shape same as `input_x`.
Raises:
@ -1511,7 +1511,7 @@ def scatter_min(input_x, indices, updates):
updates (Tensor): The tensor doing the min operation with `input_x`,
the data type is same as `input_x`, the shape is `indices.shape + input_x.shape[1:]`.
Outputs:
Returns:
Tensor, the updated `input_x`, has the same shape and type as `input_x`.
Raises:
@ -1566,7 +1566,7 @@ def scatter_div(input_x, indices, updates):
updates (Tensor): The tensor doing the divide operation with `input_x`,
the data type is same as `input_x`, the shape is `indices.shape + input_x.shape[1:]`.
Outputs:
Returns:
Tensor, the updated `input_x`, has the same shape and type as `input_x`.
Raises:
@ -3487,7 +3487,7 @@ def index_fill(x, dim, index, value):
a Tensor, it must be a 0-dimensional Tensor and has the same dtype as `x`. Otherwise,
the `value` will be cast to a 0-dimensional Tensor with the same data type as `x`.
Outputs:
Returns:
Tensor, has the same dtype and shape as input Tensor.
Raises:

65
mindspore/python/mindspore/ops/function/math_func.py
View File

@ -2123,7 +2123,7 @@ def linspace(start, stop, num):
num (int): Number of ticks in the interval, inclusive of start and stop.
Must be positive int number.
Outputs:
Returns:
Tensor, has the same dtype as `start`, and the shape of :math:`(num)`
Raises:
@ -2380,7 +2380,7 @@ def ldexp(x, other):
x (Tensor): The input tensor.
other (Tensor): A tensor of exponents, typically integers.
Outputs:
Returns:
out (Tensor, optional) : the output tensor.
Raises:
@ -2600,12 +2600,15 @@ def ge(x, y):
r"""
Computes the boolean value of :math:`x >= y` element-wise.
Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
The inputs must be two tensors or one tensor and one scalar.
When the inputs are two tensors,
dtypes of them cannot be bool at the same time, and the shapes of them could be broadcast.
When the inputs are one tensor and one scalar,
the scalar could only be a constant.
Note:
- Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
- The inputs must be two tensors or one tensor and one scalar.
- When the inputs are two tensors, dtypes of them cannot be bool at the same time,
and the shapes of them can be broadcast.
- When the inputs are one tensor and one scalar, the scalar could only be a constant.
- Broadcasting is supported.
- If the input Tensor can be broadcast, the low dimension will be extended to the corresponding high dimension
in another input by copying the value of the dimension.
.. math::
@ -2691,10 +2694,12 @@ def ne(x, y):
r"""
Computes the non-equivalence of two tensors element-wise.
Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
The inputs must be two tensors or one tensor and one scalar.
When the inputs are two tensors, the shapes of them could be broadcast.
When the inputs are one tensor and one scalar, the scalar could only be a constant.
Note:
- Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
- The inputs must be two tensors or one tensor and one scalar.
- When the inputs are two tensors, the shapes of them could be broadcast.
- When the inputs are one tensor and one scalar, the scalar could only be a constant.
- Broadcasting is supported.
.. math::
@ -2757,7 +2762,7 @@ def approximate_equal(x, y, tolerance=1e-5):
y (Tensor): A tensor of the same type and shape as `x`.
tolerance (float): The maximum deviation that two elements can be considered equal. Default: 1e-05.
Outputs:
Returns:
Tensor, the shape is the same as the shape of `x`, and the data type is bool.
Raises:
@ -2964,13 +2969,15 @@ def maximum(x, y):
"""
Computes the maximum of input tensors element-wise.
Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
The inputs must be two tensors or one tensor and one scalar.
When the inputs are two tensors,
dtypes of them cannot be bool at the same time, and the shapes of them could be broadcast.
When the inputs are one tensor and one scalar,
the scalar could only be a constant.
If one of the elements being compared is a NaN, then that element is returned.
Note:
- Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
- The inputs must be two tensors or one tensor and one scalar.
- When the inputs are two tensors,
dtypes of them cannot be bool at the same time, and the shapes of them could be broadcast.
- When the inputs are one tensor and one scalar,
the scalar could only be a constant.
- Broadcasting is supported.
- If one of the elements being compared is a NaN, then that element is returned.
.. math::
output_i = max(x_i, y_i)
@ -3416,7 +3423,7 @@ def mv(mat, vec):
mat (Tensor): Input matrix of the tensor. The shape of the tensor is :math:`(N, M)`.
vec (Tensor): Input vector of the tensor. The shape of the tensor is :math:`(M,)`.
Outputs:
Returns:
Tensor, the shape of the output tensor is :math:`(N,)`.
Raises:
@ -3478,7 +3485,7 @@ def addmv(x, mat, vec, beta=1, alpha=1):
alpha (scalar[int, float, bool], optional): Multiplier for `mat` @ `vec` (α). The `alpha` must
be int or float or bool, Default: 1.
Outputs:
Returns:
Tensor, the shape of the output tensor is :math:`(N,)`, has the same dtype as `x`.
Raises:
@ -3838,7 +3845,7 @@ def deg2rad(x):
x (Tensor[Number]): The input tensor. It must be a positive-definite matrix.
With float16, float32 or float64 data type.
Outputs:
Returns:
Tensor, has the same dtype as the `x`.
Raises:
@ -3876,7 +3883,7 @@ def rad2deg(x):
Args:
x (Tensor): The input tensor.
Outputs:
Returns:
Tensor, has the same shape and dtype as the `x`.
Raises:
@ -4127,7 +4134,7 @@ def logsumexp(x, axis, keep_dims=False):
If False, don't keep these dimensions.
Default : False.
Outputs:
Returns:
Tensor, has the same dtype as the `x`.
- If axis is (), and keep_dims is False,
@ -5020,7 +5027,7 @@ def log2(x):
Args:
x (Tensor): Input Tensor of any dimension. The value must be greater than 0.
Outputs:
Returns:
Tensor, has the same shape and dtype as the `x`.
Raises:
@ -5195,7 +5202,7 @@ def log10(x):
Args:
x (Tensor): Input Tensor of any dimension. The value must be greater than 0.
Outputs:
Returns:
Tensor, has the same shape and dtype as the `x`.
Raises:
@ -5474,9 +5481,9 @@ def remainder(x, y):
y (Union[Tensor, numbers.Number, bool]): When the first input is a tensor, The second input
could be a number, a bool or a tensor whose data type is number.
Outputs:
Returns:
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with higher precision or higher digits among the two inputs.
and the data type is the one with higher precision or higher digits among the two inputs.
Raises:
TypeError: If neither `x` nor `y` is one of the following: Tensor, number, bool.

18
mindspore/python/mindspore/ops/function/nn_func.py
View File

@ -843,7 +843,7 @@ def softsign(x):
x (Tensor): Tensor of shape :math:`(N, *)`, where :math:`*` means, any number of
additional dimensions, with float16 or float32 data type.
Outputs:
Returns:
Tensor, with the same type and shape as the `x`.
Raises:
@ -921,7 +921,7 @@ def soft_shrink(x, lambd=0.5):
x (Tensor): The input of soft shrink with data type of float16 or float32.
lambd(float): The :math:`\lambda` must be no less than zero. Default: 0.5.
Outputs:
Returns:
Tensor, has the same shape and data type as `x`.
Raises:
@ -1236,9 +1236,9 @@ def mirror_pad(input_x, paddings, mode):
Pads the input tensor according to the paddings and mode.
Args:
**input_x** (Tensor) - Tensor of shape :math:`(N, *)`, where :math:`*` means, any number of
input_x (Tensor): Tensor of shape :math:`(N, *)`, where :math:`*` means, any number of
additional dimensions.
**paddings** (Tensor) - Paddings requires constant tensor. The value of `paddings` is a
paddings (Tensor): Paddings requires constant tensor. The value of `paddings` is a
matrix(list), and its shape is (N, 2). N is the rank of input data. All elements of paddings
are int type. For the input in the `D` th dimension, paddings[D, 0] indicates how many sizes
to be extended ahead of the input tensor in the `D` th dimension, and paddings[D, 1]
@ -1248,8 +1248,7 @@ def mirror_pad(input_x, paddings, mode):
mode (str): Specifies the padding mode. The optional values are "REFLECT" and "SYMMETRIC".
Default: "REFLECT".
Outputs:
Returns:
Tensor, the tensor after padding.
- If `mode` is "REFLECT", it uses a way of symmetrical copying through the axis of symmetry to fill in.
@ -1366,7 +1365,6 @@ def cross_entropy(inputs, target, weight=None, ignore_index=-100, reduction='mea
``Ascend`` ``GPU`` ``CPU``
Examples:
>>> # Case 1: Indices labels
>>> inputs = mindspore.Tensor(np.random.randn(3, 5), mindspore.float32)
>>> target = mindspore.Tensor(np.array([1, 0, 4]), mindspore.int32)
@ -1447,7 +1445,7 @@ def nll_loss(inputs, target, weight=None, ignore_index=-100, reduction='mean', l
label_smoothing (float): Label smoothing values, a regularization tool used to prevent the model
from overfitting when calculating Loss. The value range is [0.0, 1.0]. Default value: 0.0.
Outputs:
Returns:
Tensor, the computed loss value.
Supported Platforms:
@ -1638,7 +1636,7 @@ def log_softmax(logits, axis=-1):
additional dimensions, with float16 or float32 data type.
axis (int): The axis to perform the Log softmax operation. Default: -1.
Outputs:
Returns:
Tensor, with the same type and shape as the logits.
Raises:
@ -1845,7 +1843,7 @@ def grid_sample(input_x, grid, interpolation_mode='bilinear', padding_mode='zero
to the corner points of the input’s corner pixels, making the sampling more resolution agnostic. Default:
`False`.
Outputs:
Returns:
Tensor, dtype is the same as `input_x` and whose shape is :math:`(N, C, H_{out}, W_{out})` (4-D) and
:math:`(N, C, D_{out}, H_{out}, W_{out})` (5-D).