Skip to content
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

Update F.multi_label_soft_margin_loss/nn.MultiLabelSoftMarginLoss docs 易用性提升 #7028

Merged
merged 3 commits into from
Jan 2, 2025
Merged

Update F.multi_label_soft_margin_loss/nn.MultiLabelSoftMarginLoss docs 易用性提升 #7028

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
713ca31
update docs
NKNaN Dec 21, 2024
9b1d2e6
update
NKNaN Dec 26, 2024
d2b9bb3
update
NKNaN Dec 26, 2024
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: 3 additions & 1 deletion docs/api/paddle/nn/MultiLabelSoftMarginLoss_cn.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,9 @@ MultiLabelSoftMarginLoss
损失函数按照下列公式计算

.. math::
\text{loss}(x, y) = \sum_{ij}\frac{\max(0, 1 - (x[y[j]] - x[i]))}{\text{x.shape}(0)}
\text{loss}(input, label) = - \frac{1}{\text{C}} * \sum_i label[i] * \log((1 + \exp(-input[i]))^{-1}) + (1-label[i]) * \log\left(\frac{\exp(-input[i])}{(1 + \exp(-input[i]))}\right)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

是文档写成了MultiLabelMarginLoss，但是实现是MultiLabelSoftMarginLoss 对吧？MultiLabelSoftMarginLoss 没有问题吧

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

是的


其中 :math:`\text{C}` 为类别数量,
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这个后面是一个逗号吗

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

已改为句号，这一句是对上面公式的说明


如果添加权重则再乘以对应的权重值
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这两句话 感觉也不太通顺


Expand Down
4 changes: 3 additions & 1 deletion docs/api/paddle/nn/functional/multi_label_soft_margin_loss_cn.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,9 @@ multi_label_soft_margin_loss
损失函数按照下列公式计算

.. math::
\text{loss}(x, y) = \sum_{ij}\frac{\max(0, 1 - (x[y[j]] - x[i]))}{\text{x.shape}(0)}
\text{loss}(input, label) = - \frac{1}{\text{C}} * \sum_i label[i] * \log((1 + \exp(-input[i]))^{-1}) + (1-label[i]) * \log\left(\frac{\exp(-input[i])}{(1 + \exp(-input[i]))}\right)

其中 :math:`\text{C}` 为类别数量,
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

同上

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

已改为句号，这一句是对上面公式的说明


如果添加权重则再乘以对应的权重值

Expand Down
44 changes: 0 additions & 44 deletions ...convert/convert_from_pytorch/api_difference/nn/torch.nn.MultiLabelMarginLoss.md
View file
Open in desktop

This file was deleted.

1 change: 1 addition & 0 deletions docs/guides/model_convert/convert_from_pytorch/pytorch_api_mapping_cn.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -529,6 +529,7 @@
| NOT-IMPLEMENTED-ITEM(`torch.xpu.current_device`, https://pytorch.org/docs/stable/generated/torch.xpu.current_device.html#torch-xpu-current-device, 有对应相近功能但设计差异大无法映射，一般无需新增) |
| NOT-IMPLEMENTED-ITEM(`torch.xpu.get_device_properties`, https://pytorch.org/docs/stable/generated/torch.xpu.get_device_properties.html#torch-xpu-get-device-properties, 有对应相近功能但设计差异大无法映射，一般无需新增) |
| NOT-IMPLEMENTED-ITEM(`torch.nn.functional.multilabel_margin_loss`, https://pytorch.org/docs/stable/generated/torch.nn.functional.multilabel_margin_loss.html#torch-nn-functional-multilabel-margin-loss, 可新增，且框架底层有相关设计，成本低) |
| NOT-IMPLEMENTED-ITEM(`torch.nn.functional.MultiLabelMarginLoss`, https://pytorch.org/docs/stable/generated/torch.nn.MultiLabelMarginLoss.html#torch.nn.MultiLabelMarginLoss, 可新增，且框架底层有相关设计，成本低) |
| NOT-IMPLEMENTED-ITEM(`torch.gradient`, https://pytorch.org/docs/stable/generated/torch.gradient.html#torch-gradient, 可新增，且框架底层有相关设计，成本低) |
| NOT-IMPLEMENTED-ITEM(`torch.Tensor.sparse_resize_`, https://pytorch.org/docs/stable/generated/torch.Tensor.sparse_resize_.html#torch-tensor-sparse-resize, 可新增，且框架底层有相关设计，成本低) |
| NOT-IMPLEMENTED-ITEM(`torch.autograd.profiler.profile`, https://pytorch.org/docs/stable/autograd.html#torch.autograd.profiler.profile, 可新增，但框架底层无相关设计，成本高) |
Expand Down