Hackathon No.26 #4301
Merged
Hackathon No.26 #4301
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
✅ This PR's description meets the template requirements! |
|
Thanks for your contribution! |
Ligoml
reviewed
Apr 19, 2022
|
|
||
| .. py:class:: paddle.nn.TripletMarginLoss(margin: float = 1.0, p: float = 2., eps: float = 1e-6, swap: bool = False,reduction: str = 'mean') | ||
|
|
||
| 该OP可创建一个TripletMarginLoss的可调用类，计算输入 `input` 和 `positive` 和 `negative` 间的 `triplet margin loss` 损失。 |
There was a problem hiding this comment.
去掉「该OP」的描述，API和OP概念尽量不要混用~
| d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_p | ||
|
|
||
|
|
||
| 然后， ``p`` 为距离函数的范数。 ``margin`` 为（input,positive）与（input,negative）的距离间隔， ``swap`` 的内容可以看论文Learning shallow convolutional feature descriptors with triplet losses by V. Balntas, E. Riba et al. 。 |
There was a problem hiding this comment.
论文最好附上链接，参考格式：
Learning shallow convolutional feature descriptors with triplet losses<http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf>_
| - **swap** (bool，可选) | ||
| - **margin** (float，可选) - 手动指定间距，默认为1 | ||
| - **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 Loss 的均值；设置为 ``'sum'`` 时，计算 Loss 的总和；设置为 ``'none'`` 时，则返回原始Loss。 | ||
| - **name** (str，可选) - 操作的名称（可选，默认值为None）。更多信息请参见 :ref:`api_guide_Name` 。 |
There was a problem hiding this comment.
- 每一个参数都需要介绍，swap也需要
- 中英文标点不要混用「,」-->「，」，参数末尾注意加「。」
- 注意中英文文档需要同步修改
| negative = paddle.to_tensor([[2, 1, -3], [1, 1, -1], [4, -2, 1]], dtype=paddle.float32) | ||
| triplet_margin_loss = L.TripletMarginLoss(margin=1.0, reduction='none') | ||
|
|
||
| loss = triplet_margin_loss(input, positive, negative,) |
There was a problem hiding this comment.
另外需要增加 paddle.nn.functional.triplet_margin_loss的文档吗？
Ligoml
reviewed
Apr 19, 2022
| ::::::::: | ||
|
|
||
| .. code-block:: python | ||
|
|
Ligoml
reviewed
May 9, 2022
|
|
||
| .. py:class:: paddle.nn.functional.triplet_margin_loss(input, positive, negative, p:float = 2.0, margin: float = 1.0, swap: bool = False, reduction: str = 'mean') | ||
|
|
||
| 该 api 计算输入 `input` 和 `positive` 和 `negative` 间的 `triplet margin loss` 损失，测量 `input`与 `positive examples` 和 `negative examples` 之间的相对相似性。所有输入张量的形状都为 :math:`(N, *)`，`*` 是任意其他维度。 |
|
|
||
|
|
||
|
|
||
| ``p`` 为距离函数的范数。 ``margin`` 为（input,positive）与（input,negative）的距离间隔， ``swap`` 的内容可以看论文 `Learning shallow convolutional feature descriptors with triplet losses <http://www.bmva.org/bmvc/2016/papers/paper119/paper119.pdf>`_。 |
| - **negative** (Tensor) - :math:`[N, *]` ，负样本。 | ||
| - **p** (float，可选) - 手动指定范数，默认为2。 | ||
| - **swap** (bool，可选) - 默认为False。 | ||
| - **margin** (float，可选) - 手动指定间距，默认为1。 |
There was a problem hiding this comment.
swap和margin换一下，注意和源码的参数顺序保持一致
| - **swap** (bool，可选) - 默认为False。 | ||
| - **margin** (float，可选) - 手动指定间距，默认为1。 | ||
| - **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 Loss 的均值；设置为 ``'sum'`` 时，计算 Loss 的总和；设置为 ``'none'`` 时，则返回原始Loss。 | ||
| - **name** (str，可选) - 操作的名称（可选，默认值为None）。更多信息请参见 :ref:`api_guide_Name` 。 |
| - **p** (float，可选) - 手动指定范数，默认为2。 | ||
| - **swap** (bool，可选) - 默认为False。 | ||
| - **margin** (float，可选) - 手动指定间距，默认为1。 | ||
| - **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 Loss 的均值；设置为 ``'sum'`` 时，计算 Loss 的总和；设置为 ``'none'`` 时，则返回原始Loss。 |
| - **input** (Tensor) - :math:`[N, * ]` , 其中N是batch_size， `*` 是任意其他维度。数据类型是float32、float64。 | ||
| - **positive** (Tensor) - :math:`[N, *]` ，标签 ``positive`` 的维度、数据类型与输入 ``input`` 相同。 | ||
| - **negative** (Tensor) - :math:`[N, *]` ，标签 ``negative`` 的维度、数据类型与输入 ``input`` 相同。 | ||
| - **output** (Tensor) - 输出的Tensor。如果 :attr:`reduction` 是 ``'none'``, 则输出的维度为 :math:`[N, *]` , 与输入 ``input`` 的形状相同。如果 :attr:`reduction` 是 ``'mean'`` 或 ``'sum'``, 则输出的维度为 :math:`[1]` 。 |
|
CI没过，辛苦再检查一下 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
TripletMarginLoss API 中文文档
PADDLEPADDLE_PR=40487
【Hackathon No.26】PaddlePaddle/Paddle#40487