!44907 q3_doc_collective_review_part2_master
Merge pull request !44907 from 李林杰/code_docs_1029_q3_doc_collective_review_part2_master
This commit is contained in:
Gitee
commit
55f61dde6b
|
|
@ -8,9 +8,9 @@ mindspore.ops.BoundingBoxDecode
|
|||
算子的功能是计算偏移量，此算子将偏移量转换为Bbox，用于在后续图像中标记目标等。
|
||||
|
||||
参数：
|
||||
- **means** (tuple) - 计算 `deltas` 的均值。默认值：（0.0, 0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算 `deltas` 的标准差。默认值：（1.0, 1.0, 1.0, 1.0）。
|
||||
- **max_shape** (tuple) - 解码框计算的上限值。
|
||||
- **means** (tuple) - 计算 `deltas` 的均值。默认值：（0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算 `deltas` 的标准差。默认值：（1.0, 1.0, 1.0, 1.0）。
|
||||
- **wh_ratio_clip** (float) - 解码框计算的宽高比限制。默认值：0.016。
|
||||
|
||||
输入：
|
||||
|
|
|
|||
|
|
@ -8,11 +8,11 @@ mindspore.ops.BoundingBoxEncode
|
|||
算子的功能是计算预测边界框和真实边界框之间的偏移，并将此偏移作为损失变量。
|
||||
|
||||
参数：
|
||||
- **means** (tuple) - 计算编码边界框的均值。默认值：（0.0, 0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算增量的标准偏差。默认值：（1.0、1.0、1.0、1.0）。
|
||||
- **means** (tuple) - 计算编码边界框的均值。默认值：（0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算增量的标准偏差。默认值：（1.0, 1.0, 1.0, 1.0）。
|
||||
|
||||
输入：
|
||||
- **anchor_box** (Tensor) - 锚框。锚框的shape必须为 :math:`(n,4)` 。
|
||||
- **anchor_box** (Tensor) - 锚框。锚框的shape必须为 :math:`(n, 4)` 。
|
||||
- **groundtruth_box** (Tensor) - 真实边界框。它的shape与锚框相同。
|
||||
|
||||
输出：
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ mindspore.ops.blackman_window
|
|||
.. math::
|
||||
w[n] = 0.42 - 0.5 cos(\frac{2\pi n}{N - 1}) + 0.08 cos(\frac{4\pi n}{N - 1})
|
||||
|
||||
\text{where : N is the full window size.}
|
||||
其中，N是总的窗口长度 `window_length` ，n为小于N的自然数 [0, 1, ..., N-1]。
|
||||
|
||||
参数：
|
||||
- **window_length** (Tensor) - 返回窗口的大小，数据类型为int32，int64。输入数据的值为[0,1000000]的整数。
|
||||
|
|
|
|||
|
|
@ -10,9 +10,9 @@ mindspore.ops.bounding_box_decode
|
|||
参数：
|
||||
- **anchor_box** (Tensor) - 锚框。锚框的shape必须为 :math:`(n, 4)` 。
|
||||
- **deltas** (Tensor) - 框的增量。它的shape与 `anchor_box` 相同。
|
||||
- **means** (tuple) - 计算 `deltas` 的均值。默认值：（0.0, 0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算 `deltas` 的标准差。默认值：（1.0, 1.0, 1.0, 1.0）。
|
||||
- **max_shape** (tuple) - 解码框计算的上限值。
|
||||
- **means** (tuple) - 计算 `deltas` 的均值。默认值：（0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算 `deltas` 的标准差。默认值：（1.0, 1.0, 1.0, 1.0）。
|
||||
- **wh_ratio_clip** (float) - 解码框计算的宽高比限制。默认值：0.016。
|
||||
|
||||
返回：
|
||||
|
|
|
|||
|
|
@ -10,8 +10,8 @@ mindspore.ops.bounding_box_encode
|
|||
参数：
|
||||
- **anchor_box** (Tensor) - 锚框。锚框的shape必须为 :math:`(n, 4)` 。
|
||||
- **groundtruth_box** (Tensor) - 真实边界框。它的shape与锚框相同。
|
||||
- **means** (tuple) - 计算编码边界框的均值。默认值：（0.0, 0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算增量的标准偏差。默认值：（1.0、1.0、1.0、1.0）。
|
||||
- **means** (tuple) - 计算编码边界框的均值。默认值：（0.0, 0.0, 0.0, 0.0）。
|
||||
- **stds** (tuple) - 计算增量的标准偏差。默认值：（1.0, 1.0, 1.0, 1.0）。
|
||||
|
||||
返回：
|
||||
Tensor，编码边界框。数据类型和shape与输入 `anchor_box` 相同。
|
||||
|
|
|
|||
|
|
@ -3,22 +3,22 @@ mindspore.ops.cdist
|
|||
|
||||
.. py:function:: mindspore.ops.cdist(x, y, p=2.0)
|
||||
|
||||
批量计算两个Tensor每一批次所有向量两两之间的p-范数距离。
|
||||
计算两个Tensor每对列向量之间的p-norm距离。
|
||||
|
||||
参数：
|
||||
- **x** (Tensor) - 输入tensor x，输入shape [B, P, M]，B维度可以为0，即shape为 [P, M]。
|
||||
- **y** (Tensor) - 输入tensor y，输入shape [B, R, M]。
|
||||
- **p** (float) - P -范数距离的P值，P∈[0，∞]。默认值:2.0。
|
||||
- **x** (Tensor) - 输入Tensor，shape为 :math: `(B, P, M)` ，B维度为0时该维度被忽略，shape为 :math:`(P, M)` 。在GPU上支持数据类型为[float32, float64]，在CPU上支持[float32]。
|
||||
- **y** (Tensor) - 输入Tensor，shape为 :math: `(B, R, M)` ，与 `x` 的数据类型一致。
|
||||
- **p** (float，可选) - 计算向量对p-norm距离的P值，P∈[0，∞]。默认值:2.0。
|
||||
|
||||
返回：
|
||||
Tensor，p-范数距离，shape为[B, P, R]。
|
||||
Tensor，p-范数距离，数据类型与 `x` 一致，shape为(B, P, R)。
|
||||
|
||||
异常：
|
||||
- **TypeError** - `input_x` 或 `input_x` 不是Tensor。
|
||||
- **TypeError** - `input_x` 或 `input_y` 的数据类型不是float16，也不是float32。
|
||||
- **TypeError** - `x` 或 `y` 不是Tensor。
|
||||
- **TypeError** - `x` 或 `y` 的数据类型在GPU环境不是float32或者float64，在CPU环境不是float32。
|
||||
- **TypeError** - `p` 不是float32。
|
||||
- **ValueError** - `p` 是负数。
|
||||
- **ValueError** - `input_x` 与 `input_y` 维度不同。
|
||||
- **ValueError** - `input_x` 与 `input_y` 的维度不是2，也不是3。
|
||||
- **ValueError** - `x` 与 `y` 维度不同。
|
||||
- **ValueError** - `x` 与 `y` 的维度既不是2，也不是3。
|
||||
- **ValueError** - 单批次训练下 `x` 和 `y` 的shape不一样。
|
||||
- **ValueError** - `x` 和 `y` 的列数不一样。
|
||||
|
|
|
|||
|
|
@ -3,10 +3,12 @@ mindspore.ops.celu
|
|||
|
||||
.. py:function:: mindspore.ops.celu(x, alpha=1.0)
|
||||
|
||||
celu激活函数，按输入元素计算输出。公式定义如下：
|
||||
celu激活函数，逐元素计算输入Tensor的celu（Continuously differentiable exponential linear units）值。公式定义如下：
|
||||
|
||||
.. math::
|
||||
\text{CeLU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))
|
||||
|
||||
详情请参考： `celu <https://arxiv.org/abs/1704.07483>`_ 。
|
||||
|
||||
参数：
|
||||
- **x** (Tensor) - celu的输入，数据类型为float16或float32。
|
||||
|
|
@ -17,6 +19,6 @@ mindspore.ops.celu
|
|||
|
||||
异常：
|
||||
- **TypeError** - `alpha` 不是float。
|
||||
- **ValueError** - `alpha` 的值为零。
|
||||
- **TypeError** - `x` 不是tensor。
|
||||
- **TypeError** - `x` 的dtype既不是float16也不是float32。
|
||||
- **TypeError** - `x` 不是Tensor。
|
||||
- **TypeError** - `x` 的dtype既不是float16也不是float32。
|
||||
- **ValueError** - `alpha` 的值为0。
|
||||
|
|
@ -8,7 +8,7 @@ mindspore.ops.check_valid
|
|||
检查边界框的交叉数据和数据边界是否有效。
|
||||
|
||||
.. warning::
|
||||
指定有效边界 `(长度 * 比率, 宽度 * 比率)` 。
|
||||
由 `bboxes` 指定的边界 `(长度 * 比率, 宽度 * 比率)` 需要时有效的。
|
||||
|
||||
参数：
|
||||
- **bboxes** (Tensor) - shape大小为 :math:`(N, 4)` 。:math:`N` 表示边界框的数量， `4` 表示 `x0` 、`x1` 、`y0` 、`y` 。数据类型必须是float16或float32。
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ mindspore.ops.choice_with_mask
|
|||
对输入进行随机取样，返回取样索引和掩码。
|
||||
|
||||
输入必须是秩不小于1的Tensor。如果其秩大于等于2，则第一个维度指定样本数。
|
||||
索引Tensor为取样的索引，掩码Tensor表示索引Tensor中的哪些元素取值为True。
|
||||
返回的索引Tensor为非空样本值的索引，掩码Tensor说明索引Tensor中的哪些元素是有效的。
|
||||
|
||||
参数：
|
||||
- **input_x** (Tensor[bool]) - 输入Tensor，bool类型。秩必须大于等于1且小于等于5。
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ mindspore.ops.cholesky
|
|||
|
||||
.. py:function:: mindspore.ops.cholesky(input_x, upper=False)
|
||||
|
||||
计算对称正定矩阵 :math:`A` 或对称正定矩阵批次的Cholesky分解。
|
||||
计算对称正定矩阵 :math:`A` 或一批对称正定矩阵的Cholesky分解。
|
||||
|
||||
如果 `upper` 为True，则返回的矩阵 :math:`U` 为上三角矩阵，分解形式为：
|
||||
|
||||
|
|
@ -26,5 +26,5 @@ mindspore.ops.cholesky
|
|||
- **TypeError** - 如果 `upper` 不是bool。
|
||||
- **TypeError** - 如果 `input_x` 的数据类型既不是float32，也不是float64。
|
||||
- **TypeError** - 如果 `input_x` 不是Tensor。
|
||||
- **ValueError** - 如果 `input_x` 不是批处理方。
|
||||
- **ValueError** - 如果 `input_x` 不是一个或多个方阵。
|
||||
- **ValueError** - 如果 `input_x` 不是对称正定矩阵。
|
||||
|
|
|
|||
|
|
@ -19,8 +19,8 @@ mindspore.ops.cholesky_inverse
|
|||
输入Tensor必须是一个上三角矩阵或者下三角矩阵。
|
||||
|
||||
参数：
|
||||
- **input_x** (Tensor) - 输入Tensor，数据类型为float32或float64。
|
||||
- **upper** (bool) - 是否返回上三角矩阵还是下三角矩阵的标志。默认值：False。
|
||||
- **input_x** (Tensor) - 输入Tensor，其rank为2，数据类型为float32或float64。
|
||||
- **upper** (bool) - 返回上三角矩阵还是下三角矩阵的标志。默认值：False。
|
||||
|
||||
返回：
|
||||
Tensor，shape和数据类型与 `input_x` 相同。
|
||||
|
|
|
|||
|
|
@ -14,8 +14,9 @@ mindspore.ops.conv2d
|
|||
|
||||
如果 `pad_mode` 设置为"valid"，则输出高度和宽度将分别为 :math:`\left \lfloor{1 + \frac{H_{in} + \text{padding[0]} + \text{padding[1]} - \text{kernel_size[0]} - (\text{kernel_size[0]} - 1) \times (\text{dilation[0]} - 1) }{\text{stride[0]}}} \right \rfloor` 和 :math:`\left \lfloor{1 + \frac{W_{in} + \text{padding[2]} + \text{padding[3]} - \text{kernel_size[1]} - (\text{kernel_size[1]} - 1) \times (\text{dilation[1]} - 1) }{\text{stride[1]}}} \right \rfloor` 。
|
||||
其中， :math:`dialtion` 为卷积核元素之间的间距， :math:`stride` 为移动步长， :math:`padding` 为添加到输入两侧的零填充。
|
||||
对于取其他值的 `pad_mode` 时候的输出高度和宽度的计算，请参考 :class:`mindspore.nn.Conv2d` 里的计算公式。
|
||||
|
||||
请参考论文 `Gradient Based Learning Applied to Document Recognition <http://vision.stanford.edu/cs598_spring07/papers/Lecun98.pdf>`_ 。更详细的介绍，参见：http://cs231n.github.io/convolutional-networks/。
|
||||
请参考论文 `Gradient Based Learning Applied to Document Recognition <http://vision.stanford.edu/cs598_spring07/papers/Lecun98.pdf>`_ 。更详细的介绍，参见： `ConvNets <http://cs231n.github.io/convolutional-networks/>`_ 。
|
||||
|
||||
参数：
|
||||
- **inputs** (Tensor) - shape为 :math:`(N, C_{in}, H_{in}, W_{in})` 的Tensor。
|
||||
|
|
|
|||
|
|
@ -108,7 +108,7 @@ def check_valid(bboxes, img_metas):
|
|||
Checks whether the bounding box cross data and data border are valid.
|
||||
|
||||
.. warning::
|
||||
specifying the valid boundary (heights x ratio, weights x ratio).
|
||||
Boundary(heights * ratio, widths * ratio) specified by `bboxes` is required to be valid.
|
||||
|
||||
Args:
|
||||
bboxes (Tensor): Bounding boxes tensor with shape :math:`(N, 4)`. :math:`N` indicates the number of
|
||||
|
|
|
|||
|
|
@ -3769,24 +3769,26 @@ def lcm(x1, x2):
|
|||
|
||||
def cdist(x, y, p=2.0):
|
||||
"""
|
||||
Computes batched the p-norm distance between each pair of the two collections of row vectors.
|
||||
Computes p-norm distance between each pair of row vectors of two input Tensors.
|
||||
|
||||
Args:
|
||||
x (Tensor): Input tensor of shape :math:`(B, P, M)`.
|
||||
Letter :math:`B` represents 0 or positive int number.
|
||||
When :math:`B` is equal to 0, it means this dimension can be ignored,
|
||||
i.e. shape of the tensor is :math:`(P, M)`.
|
||||
y (Tensor): Input tensor of shape :math:`(B, R, M)`.
|
||||
p (float): P value for the p-norm distance to calculate between each vector pair, P ∈ [0,∞]. Default: 2.0.
|
||||
i.e. shape of the tensor is :math:`(P, M)`. The supported dtype is
|
||||
[float32, float64] on GPU, or [float32] on CPU.
|
||||
y (Tensor): Input tensor of shape :math:`(B, R, M)`, has the same dtype as `x`.
|
||||
p (float, optional): P value for the p-norm distance to calculate between each
|
||||
vector pair, P ∈ [0,∞]. Default: 2.0.
|
||||
|
||||
Returns:
|
||||
Tensor, has the same dtype as `x`, which shape is :math:`(B, P, R)`.
|
||||
Tensor, p-norm distance, has the same dtype as `x`, its shape is :math:`(B, P, R)`.
|
||||
|
||||
Raises:
|
||||
TypeError: If `x` or `y` is not a Tensor.
|
||||
TypeError: If `x` or `y` is not Tensor.
|
||||
TypeError: If dtype of x or y is not in [float32, float64] on GPU, or is not in [float32] on CPU.
|
||||
TypeError: If `p` is not a float.
|
||||
ValueError: If `p` is a negative float.
|
||||
TypeError: If `p` is not float32.
|
||||
ValueError: If `p` is negative.
|
||||
ValueError: If dimension of `x` is not the same as `y`.
|
||||
ValueError: If dimension of `x` or `y` is neither 2 nor 3.
|
||||
ValueError: If the batch shape of `x` is not the same as the shape of `y`.
|
||||
|
|
@ -6367,7 +6369,7 @@ def cholesky(input_x, upper=False):
|
|||
TypeError: If `upper` is not a bool.
|
||||
TypeError: If dtype of `input_x` is not one of: float64, float32.
|
||||
TypeError: If `input_x` is not a Tensor.
|
||||
ValueError: If `input_x` is not batch square.
|
||||
ValueError: If `input_x` is not a or a batch of square matrix.
|
||||
ValueError: If `input_x` is not symmetric positive definite.
|
||||
|
||||
Supported Platforms:
|
||||
|
|
@ -6404,7 +6406,7 @@ def cholesky_inverse(input_x, upper=False):
|
|||
The input must be either an upper triangular matrix or a lower triangular matrix.
|
||||
|
||||
Args:
|
||||
input_x (Tensor): The input tensor. Types: float32, float64.
|
||||
input_x (Tensor): The input tensor with a rank of 2. Supported dtypes: float32, float64.
|
||||
upper(bool): Whether to return a lower or upper triangular matrix. Default: False.
|
||||
|
||||
Returns:
|
||||
|
|
|
|||
|
|
@ -1009,15 +1009,14 @@ def dropout(x, p=0.5, seed0=0, seed1=0):
|
|||
|
||||
def celu(x, alpha=1.0):
|
||||
r"""
|
||||
Computes celu (Continuously differentiable exponential linear units) of input tensors element-wise.
|
||||
celu activation function, computes celu (Continuously differentiable exponential
|
||||
linear units) of input tensors element-wise. The formula is defined as follows:
|
||||
|
||||
.. math::
|
||||
|
||||
\text{CeLU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))
|
||||
|
||||
It returns :math:`\max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))` element-wise.
|
||||
|
||||
The picture about celu looks like this `celu <https://arxiv.org/abs/1704.07483>`_.
|
||||
For more details, please refer to `celu <https://arxiv.org/abs/1704.07483>`_.
|
||||
|
||||
Args:
|
||||
x (Tensor): The input of celu with data type of float16 or float32.
|
||||
|
|
@ -1028,9 +1027,9 @@ def celu(x, alpha=1.0):
|
|||
|
||||
Raises:
|
||||
TypeError: If `alpha` is not a float.
|
||||
ValueError: If `alpha` has the value of 0.
|
||||
TypeError: If `x` is not a Tensor.
|
||||
TypeError: If dtype of `x` is neither float16 nor float32.
|
||||
ValueError: If `alpha` has the value of 0.
|
||||
|
||||
Supported Platforms:
|
||||
``Ascend`` ``CPU`` ``GPU``
|
||||
|
|
@ -3102,15 +3101,16 @@ def conv2d(inputs, weight, pad_mode="valid", padding=0, stride=1, dilation=1, gr
|
|||
|
||||
out_j = \sum_{i=0}^{C_{in} - 1} ccor(W_{ij}, X_i) + b_j,
|
||||
|
||||
where :math:`ccor` is the cross correlation operator, :math:`C_{in}` is the input channel number, :math:`j` ranges
|
||||
where :math:`ccor` is the `cross-correlation <https://en.wikipedia.org/wiki/Cross-correlation>`_ operator,
|
||||
:math:`C_{in}` is the input channel number, :math:`j` ranges
|
||||
from :math:`0` to :math:`C_{out} - 1`, :math:`W_{ij}` corresponds to the :math:`i`-th channel of the :math:`j`-th
|
||||
filter and :math:`out_{j}` corresponds to the :math:`j`-th channel of the output. :math:`W_{ij}` is a slice
|
||||
of kernel and it has shape :math:`(\text{kernel_size[0]}, \text{kernel_size[1]})`, where :math:`\text{
|
||||
kernel_size[0]}` and :math:`\text{kernel_size[1]}` are the height and width of the convolution kernel.
|
||||
The full kernel has shape :math:`(C_{out}, C_{in} / \text{group}, \text{kernel_size[0]}, \text{kernel_size[1]})`,
|
||||
where group is the group number to split the input in the channel dimension.
|
||||
where `group` is the group number to split the input in the channel dimension.
|
||||
|
||||
If the 'pad_mode' is set to be "valid", the output height and width will be
|
||||
If the `pad_mode` is set to be "valid", the output height and width will be
|
||||
:math:`\left \lfloor{
|
||||
1 + \frac{H_{in} + \text{padding[0]} + \text{padding[1]} - \text{kernel_size[0]} -
|
||||
(\text{kernel_size[0]} - 1) \times(\text{dilation[0]} - 1)} {\text { stride[0] }}} \right \rfloor` and
|
||||
|
|
@ -3121,10 +3121,12 @@ def conv2d(inputs, weight, pad_mode="valid", padding=0, stride=1, dilation=1, gr
|
|||
|
||||
Where :math:`dilation` is Spacing between kernel elements, :math:`stride` is The step length of each step,
|
||||
:math:`padding` is zero-padding added to both sides of the input.
|
||||
For output height and width on other `pad_mode`, please refer to formula on `mindspore.nn.Conv2d
|
||||
<https://www.mindspore.cn/docs/en/master/api_python/nn/mindspore.nn.Conv2d.html>`_.
|
||||
|
||||
The first introduction can be found in paper `Gradient Based Learning Applied to Document Recognition
|
||||
<http://vision.stanford.edu/cs598_spring07/papers/Lecun98.pdf>`_. More detailed introduction can be found here:
|
||||
http://cs231n.github.io/convolutional-networks/.
|
||||
`ConvNets <http://cs231n.github.io/convolutional-networks/>`_ .
|
||||
|
||||
Args:
|
||||
inputs (Tensor): Tensor of shape :math:`(N, C_{in}, H_{in}, W_{in})`.
|
||||
|
|
@ -3487,7 +3489,7 @@ def bias_add(input_x, bias):
|
|||
|
||||
def binary_cross_entropy(logits, labels, weight=None, reduction='mean'):
|
||||
r"""
|
||||
Computes the binary cross entropy between predivtive value `logits` and target value `labels`.
|
||||
Computes the binary cross entropy between predictive value `logits` and target value `labels`.
|
||||
|
||||
Set `logits` as :math:`x`, `labels` as :math:`y`, output as :math:`\ell(x, y)`, the
|
||||
weight of nth batch of binary cross entropy is :math:`w_n`.
|
||||
|
|
@ -3512,7 +3514,7 @@ def binary_cross_entropy(logits, labels, weight=None, reduction='mean'):
|
|||
- The value of `labels` must be `0` or `l`.
|
||||
|
||||
Args:
|
||||
logits (Tensor): The predivtive value whose data type must be float16 or float32,
|
||||
logits (Tensor): The predictive value whose data type must be float16 or float32.
|
||||
The shape is :math:`(N, *)` where :math:`*` means, any number of additional dimensions.
|
||||
labels (Tensor): The target value which has the same shape and data type as `logits`.
|
||||
weight (Tensor, optional): A rescaling weight applied to the loss of each batch element.
|
||||
|
|
|
|||
|
|
@ -482,10 +482,10 @@ def choice_with_mask(input_x, count=256, seed=0, seed2=0):
|
|||
"""
|
||||
Generates a random sample as index tensor with a mask tensor from a given tensor.
|
||||
|
||||
The input_x must be a tensor of rank not less than 1. If its rank is greater than or equal to 2,
|
||||
The `input_x` must be a tensor whose rank is not less than 1. If its rank is greater than or equal to 2,
|
||||
the first dimension specifies the number of samples.
|
||||
The index tensor and the mask tensor have the fixed shapes. The index tensor denotes the index of the nonzero
|
||||
sample, while the mask tensor denotes which elements in the index tensor are valid.
|
||||
The returned index tensor denotes the index of the nonzero
|
||||
sample, the mask tensor denotes which elements in the index tensor are valid.
|
||||
|
||||
Args:
|
||||
input_x (Tensor[bool]): The input tensor.
|
||||
|
|
|
|||
|
|
@ -24,8 +24,8 @@ def blackman_window(window_length, periodic=True, *, dtype=None):
|
|||
r"""
|
||||
Blackman window function.
|
||||
|
||||
The input `window_length` is a tensor that datatype must be a integer, which
|
||||
controlling the returned window size. In particular, If `window_length` is equal to `1`,
|
||||
The input `window_length` is a tensor with datatype int,
|
||||
it determines the returned window size. In particular, if `window_length` is equal to `1`,
|
||||
the returned window contains a single value `1`.
|
||||
Attr `periodic` determines whether the returned window trims off the last duplicate value
|
||||
from the symmetric window and is ready to be used as a periodic window with functions.
|
||||
|
|
@ -35,7 +35,7 @@ def blackman_window(window_length, periodic=True, *, dtype=None):
|
|||
|
||||
w[n] = 0.42 - 0.5 cos(\frac{2\pi n}{N - 1}) + 0.08 cos(\frac{4\pi n}{N - 1})
|
||||
|
||||
\text{where : N is the full window size.}
|
||||
where N is the full window size, and n is natural number less than N:[0, 1, ..., N-1].
|
||||
|
||||
Args:
|
||||
window_length (Tensor): the size of returned window, with data type int32, int64.
|
||||
|
|
|
|||
|
|
@ -5614,7 +5614,7 @@ class BinaryCrossEntropy(Primitive):
|
|||
Its value must be one of 'none', 'mean' or 'sum'. Default: 'mean'.
|
||||
|
||||
Inputs:
|
||||
- **logits** (Tensor) - The predivtive value whose data type must be float16 or float32,
|
||||
- **logits** (Tensor) - The predictive value whose data type must be float16 or float32,
|
||||
The shape is :math:`(N, *)` where :math:`*` means, any number of additional dimensions.
|
||||
- **labels** (Tensor) - The target value which has the same shape and data type as `logits`.
|
||||
- **weight** (Tensor, optional) - A rescaling weight applied to the loss of each batch element.
|
||||
|
|
|
|||
|
|
@ -224,9 +224,9 @@ class BoundingBoxDecode(Primitive):
|
|||
which is used to mark the target in the subsequent images, etc.
|
||||
|
||||
Args:
|
||||
max_shape (tuple): The max size limit for decoding box calculation.
|
||||
means (tuple): The means of deltas calculation. Default: (0.0, 0.0, 0.0, 0.0).
|
||||
stds (tuple): The standard deviations of deltas calculation. Default: (1.0, 1.0, 1.0, 1.0).
|
||||
max_shape (tuple): The max size limit for decoding box calculation.
|
||||
wh_ratio_clip (float): The limit of width and height ratio for decoding box calculation. Default: 0.016.
|
||||
|
||||
Inputs:
|
||||
|
|
|
|||
Loading…
Reference in New Issue