文档反馈

问题文档片段

问题文档片段包含公式时，显示为空格。

提交类型

issue

有点复杂...

找人问问吧。

请选择提交类型

问题类型

规范和低错类

- 规范和低错类：

- 错别字或拼写错误，标点符号使用错误、公式错误或显示异常。

- 链接错误、空单元格、格式错误。

- 英文中包含中文字符。

- 界面和描述不一致，但不影响操作。

- 表述不通顺，但不影响理解。

- 版本号不匹配：如软件包名称、界面版本号。

易用性

- 易用性：

- 关键步骤错误或缺失，无法指导用户完成任务。

- 缺少主要功能描述、关键词解释、必要前提条件、注意事项等。

- 描述内容存在歧义指代不明、上下文矛盾。

- 逻辑不清晰，该分类、分项、分步骤的没有给出。

正确性

- 正确性：

- 技术原理、功能、支持平台、参数类型、异常报错等描述和软件实现不一致。

- 原理图、架构图等存在错误。

- 命令、命令参数等错误。

- 代码片段错误。

- 命令无法完成对应功能。

- 界面错误，无法指导操作。

- 代码样例运行报错、运行结果不符。

风险提示

- 风险提示：

- 对重要数据或系统存在风险的操作，缺少安全提示。

内容合规

- 内容合规：

- 违反法律法规，涉及政治、领土主权等敏感词。

- 内容侵权。

请选择问题类型

问题描述

点击输入详细问题描述，以帮助我们快速定位问题。

提交

文档反馈

mindspore.ops.BCEWithLogitsLoss

class mindspore.ops.BCEWithLogitsLoss(reduction='mean')

Adds sigmoid activation function to input logits, and uses the given logits to compute binary cross entropy between the logits and the label.

Sets input logits as $X$, input label as $Y$, input weight as $W$, output as $L$. Then,

$$\begin{array}{r}\begin{array}{l}\\ p_{ij}=sigmoid(X_{ij})=\frac{1}{1+e^{-X_{ij}}}\\ L_{ij}=-[Y_{ij}\ast log(p_{ij})+(1-Y_{ij})log(1-p_{ij})]\end{array}\end{array}$$

$i$ indicates the $i^{th}$ sample, $j$ indicates the category. Then,

$$\begin{array}{r}\ell (x,y)=\{\begin{array}{ll}L,& \text{if reduction}=\text{'none';}\\ \mathrm{mean}(L),& \text{if reduction}=\text{'mean';}\\ \mathrm{sum}(L),& \text{if reduction}=\text{'sum'.}\end{array}\end{array}$$

$\ell$ indicates the method of calculating the loss. There are three methods: the first method is to provide the loss value directly, the second method is to calculate the average value of all losses, and the third method is to calculate the sum of all losses.

This operator will multiply the output by the corresponding weight. The tensor weight assigns different weights to each piece of data in the batch, and the tensor pos_weight adds corresponding weights to the positive examples of each category.

In addition, it can trade off recall and precision by adding weights to positive examples. In the case of multi-label classification the loss can be described as:

$$\begin{array}{r}\begin{array}{l}\\ p_{ij,c}=sigmoid(X_{ij,c})=\frac{1}{1+e^{-X_{ij,c}}}\\ L_{ij,c}=-[P_c{Y}_{ij,c}\ast log(p_{ij,c})+(1-Y_{ij,c})log(1-p_{ij,c})]\end{array}\end{array}$$

where c is the class number (c>1 for multi-label binary classification, c=1 for single-label binary classification), n is the number of the sample in the batch and $p_c$ is the weight of the positive answer for the class c. $p_c>1$ increases the recall, $p_c<1$ increases the precision.

Parameters

reduction (str) – Type of reduction to be applied to loss. The optional values are ‘mean’, ‘sum’, and ‘none’, not case sensitive. If ‘none’, do not perform reduction. Default:’mean’.

Inputs:

• logits (Tensor) - Input logits. Data type must be float16 or float32. Tensor of shape $(N,\ast )$ where $\ast$ means, any number of additional dimensions.

• label (Tensor) - Ground truth label, has the same shape as logits. Data type must be float16 or float32.

• weight (Tensor) - A rescaling weight applied to the loss of each batch element. It can be broadcast to a tensor with shape of logits. Data type must be float16 or float32.

• pos_weight (Tensor) - A weight of positive examples. Must be a vector with length equal to the number of classes. It can be broadcast to a tensor with shape of logits. Data type must be float16 or float32.

Outputs:

Tensor or Scalar, if reduction is ‘none’, it’s a tensor with the same shape and type as input logits. Otherwise, the output is a scalar.

Raises

• TypeError – If data type of any input is neither float16 nor float32.

• ValueError – If weight or pos_weight can not be broadcast to a tensor with shape of logits.

• ValueError – If reduction is not one of ‘none’, ‘mean’ or ‘sum’.

Supported Platforms:

Ascend GPU

Examples

>>> logits = Tensor(np.array([[-0.8, 1.2, 0.7], [-0.1, -0.4, 0.7]]), mindspore.float32)
>>> label = Tensor(np.array([[0.3, 0.8, 1.2], [-0.6, 0.1, 2.2]]), mindspore.float32)
>>> weight = Tensor(np.array([1.0, 1.0, 1.0]), mindspore.float32)
>>> pos_weight = Tensor(np.array([1.0, 1.0, 1.0]), mindspore.float32)
>>> loss = ops.BCEWithLogitsLoss()
>>> output = loss(logits, label, weight, pos_weight)
>>> print(output)
0.3463612