Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/TripletMarginLoss_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ TripletMarginLoss
d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_p
``p`` 为距离函数的范数。``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf>`_ 。
``p`` 为距离函数的范数。``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://bmva-archive.org.uk/bmvc/2016/papers/paper119/paper119.pdf>`_ 。

参数
:::::::::
Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/TripletMarginWithDistanceLoss_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ TripletMarginWithDistanceLoss
d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_2
``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)的值换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf>`_ 。
``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)的值换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://bmva-archive.org.uk/bmvc/2016/papers/paper119/paper119.pdf>`_ 。



Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/nn/functional/triplet_margin_loss_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ triplet_margin_loss
``p`` 为距离函数的范数。``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf>`_ 。
``p`` 为距离函数的范数。``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://bmva-archive.org.uk/bmvc/2016/papers/paper119/paper119.pdf>`_ 。

参数
:::::::::
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ triplet_margin_with_distance_loss
d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_2
``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)的值换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf>`_ 。
``margin`` 为(input,positive)与(input,negative)的距离间隔,``swap`` 为 True 时,会比较(input,negative)和(positive,negative)的大小,并将(input,negative)的值换为其中较小的值,内容详见论文 `Learning shallow convolutional feature descriptors with triplet losses <http://bmva-archive.org.uk/bmvc/2016/papers/paper119/paper119.pdf>`_ 。


参数
Expand Down
2 changes: 1 addition & 1 deletion docs/api/paddle/static/nn/nce_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ nce
计算并返回噪音对比估计损失值( noise-contrastive estimation training loss)。该层默认使用均匀分布进行抽样。

论文参考:`Noise-contrastive estimation: A new estimation principle for unnormalized statistical models
<http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf>`_
<http://proceedings.mlr.press/v9/gutmann10a/gutmann10a.pdf>`_


参数
Expand Down