Skip to content

[API Compatibility No.155] Update docs for bce_with_logits alias support -part #7842

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
luotao1 merged 4 commits into from
Mar 24, 2026
Merged

[API Compatibility No.155] Update docs for bce_with_logits alias support -part #7842

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6c5faea
[API Compatibility No.155] Update docs for bce_with_logits alias support
Aidenwu0209 Mar 5, 2026
20d841a
Merge branch 'develop' into api-compat-76301-no155-bce-with-logits-alias
luotao1 Mar 16, 2026
1d97f7a
Merge remote-tracking branch 'origin/develop' into api-compat-76301-n…
Aidenwu0209 Mar 23, 2026
306bf51
[API Compatibility No.155] Align bce_with_logits docs with latest doc…
Aidenwu0209 Mar 23, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/api/paddle/nn/functional/binary_cross_entropy_with_logits_cn.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,8 +34,8 @@ binary_cross_entropy_with_logits

参数
:::::::::
- **logit** (Tensor) - :math:`[N, *]`，其中 N 是 batch_size， ``*`` 是任意其他维度。输入数据 ``logit`` 一般是线性层的输出，不需要经过 ``sigmoid`` 层。数据类型是 float32、float64。
- **label** (Tensor) - :math:`[N, *]`，标签 ``label`` 的维度、数据类型与输入 ``logit`` 相同。
- **logit** (Tensor) - :math:`[N, *]`，其中 N 是 batch_size， ``*`` 是任意其他维度。输入数据 ``logit`` 一般是线性层的输出，不需要经过 ``sigmoid`` 层。数据类型是 float32、float64。别名：``input``。
- **label** (Tensor) - :math:`[N, *]`，标签 ``label`` 的维度、数据类型与输入 ``logit`` 相同。别名：``target``。
- **weight** (Tensor，可选) - 手动指定每个 batch 二值交叉熵的权重，如果指定的话，维度必须是一个 batch 的数据的维度。数据类型是 float32, float64。默认值是：None。
- **reduction** (str，可选) - 指定应用于输出结果的计算方式，可选值有：``'none'``, ``'mean'``, ``'sum'``。默认为 ``'mean'``，计算 ``BCELoss`` 的均值；设置为 ``'sum'`` 时，计算 ``BCELoss`` 的总和；设置为 ``'none'`` 时，则返回原始 loss。
- **pos_weight** (Tensor，可选) - 手动指定正类的权重，必须是与类别数相等长度的向量。数据类型是 float32, float64。默认值是：None。
Expand Down
6 changes: 4 additions & 2 deletions ...ference/torch_more_args/torch.nn.functional.binary_cross_entropy_with_logits.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,14 +9,16 @@ torch.nn.functional.binary_cross_entropy_with_logits(input, target, weight=None,
paddle.nn.functional.binary_cross_entropy_with_logits(logit, label, weight=None, reduction='mean', pos_weight=None, name=None)
```

其中 `input` 是 Paddle 参数 `logit` 的别名，`target` 是 Paddle 参数 `label` 的别名。

PyTorch 相比 Paddle 支持更多其他参数，具体如下：

### 参数映射

| PyTorch | PaddlePaddle | 备注 |
| ------------- | ------------ | ------------------------------------------------------ |
| input | logit | 表示输入的 Tensor。 |
| target | label | 标签，和 input 具有相同的维度，仅参数名不一致。 |
| input | logit | 表示输入的 Tensor。Paddle 兼容 `input` 别名，无需改写。 |
| target | label | 标签，和 input 具有相同的维度。Paddle 兼容 `target` 别名，无需改写。 |
| weight | weight | 类别权重。 |
| size_average | - | 已废弃，和 reduce 组合决定损失计算方式。 Paddle 无此参数，需要转写。 |
| reduce | - | 已废弃，和 size_average 组合决定损失计算方式。 Paddle 无此参数，需要转写。 |
Expand Down
Loading