Skip to content

Commit 46d6fa9

Browse files
authored
Merge branch 'develop' into lyly-B
2 parents 784a648 + e212cf3 commit 46d6fa9

File tree

5 files changed

+5
-5
lines changed

5 files changed

+5
-5
lines changed

docs/api/paddle/nn/TripletMarginLoss_cn.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ TripletMarginLoss
1919
d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_p
2020
2121
22-
``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>`_ 。
22+
``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>`_ 。
2323

2424
参数
2525
:::::::::

docs/api/paddle/nn/TripletMarginWithDistanceLoss_cn.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ TripletMarginWithDistanceLoss
2020
d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_2
2121
2222
23-
``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>`_ 。
23+
``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>`_ 。
2424

2525

2626

docs/api/paddle/nn/functional/triplet_margin_loss_cn.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ triplet_margin_loss
2020
2121
2222
23-
``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>`_ 。
23+
``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>`_ 。
2424

2525
参数
2626
:::::::::

docs/api/paddle/nn/functional/triplet_margin_with_distance_loss_cn.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ triplet_margin_with_distance_loss
2020
d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_2
2121
2222
23-
``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>`_ 。
23+
``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>`_ 。
2424

2525

2626
参数

docs/api/paddle/static/nn/nce_cn.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ nce
1212
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。
1313

1414
论文参考:`Noise-contrastive estimation: A new estimation principle for unnormalized statistical models
15-
<http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf>`_
15+
<http://proceedings.mlr.press/v9/gutmann10a/gutmann10a.pdf>`_
1616

1717

1818
参数

0 commit comments

Comments
 (0)