[Docathon][Update Doc No.29] fix the LossFunction #7227
Merged
Conversation
This file contains hidden or 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
|
感谢你贡献飞桨文档，文档预览构建中，Docs-New 跑完后即可预览，预览链接：http://preview-pr-7227.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html |
|
@DrRyanHuang pls review |
DrRyanHuang
requested changes
Apr 7, 2025
There was a problem hiding this comment.
辛苦同学按照预览链接，修复一下 rst 文档的格式，删去与 fluid 相关的内容
http://preview-pr-7227.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/develop/api_guides/low_level/layers/loss_function.html
| @@ -11,30 +11,30 @@ Paddle Fluid 中提供了面向多种任务的多种类型的损失函数，以 | |||
| ==== | |||
|
|
|||
| 平方误差损失（squared error loss）使用预测值和真实值之间误差的平方作为样本损失，是回归问题中最为基本的损失函数。 | |||
| API Reference 请参考 :ref:`cn_api_fluid_layers_square_error_cost`。 | |||
| API Reference 请参考 :ref:`cn_api_nn_functional_square_error_cost`。 | |||
There was a problem hiding this comment.
辛苦同学以develop最新版为准修改一下，下同
Suggested change
| API Reference 请参考 :ref:`cn_api_nn_functional_square_error_cost`。 | |
| API Reference 请参考 :ref:`cn_api_paddle_nn_functional_square_error_cost`。 |
DrRyanHuang
reviewed
Apr 16, 2025
|
|
||
| * 序列分类（Sequence Classification）问题，整个序列对应一个预测标签，如文本分类。这种即是普通的分类问题，可以使用 cross entropy 作为损失函数。 | ||
| * 序列片段分类（Segment Classification）问题，序列中的各个片段对应有自己的类别标签，如命名实体识别。对于这种序列标注问题，`（线性链）条件随机场（Conditional Random Field，CRF） <http://www.cs.columbia.edu/~mcollins/fb.pdf>`_ 是一种常用的模型方法，其使用句子级别的似然概率，序列中不同位置的标签不再是条件独立，能够有效解决标记偏置问题。Paddle Fluid 中提供了 CRF 对应损失函数的支持，API Reference 请参考 :ref:`cn_api_fluid_layers_linear_chain_crf`。 | ||
| * 时序分类（Temporal Classification）问题，需要对未分割的序列进行标注，如语音识别。对于这种时序分类问题，`CTC（Connectionist Temporal Classification） <http://people.idsia.ch/~santiago/papers/icml2006.pdf>`_ 损失函数不需要对齐输入数据及标签，可以进行端到端的训练，Paddle Fluid 提供了 warpctc 的接口来计算相应的损失，API Reference 请参考 :ref:`cn_api_fluid_layers_warpctc`。 | ||
| * 时序分类（Temporal Classification）问题，需要对未分割的序列进行标注，如语音识别。对于这种时序分类问题，`CTC（Connectionist Temporal Classification） <http://people.idsia.ch/~santiago/papers/icml2006.pdf>`_ 损失函数不需要对齐输入数据及标签，可以进行端到端的训练，Paddle Fluid 提供了 warpctc 的接口来计算相应的损失，API Reference 请参考 :ref:`cn_api_paddle_nn_functional_ctc_loss`。 |
DrRyanHuang
reviewed
Apr 16, 2025
| @@ -35,27 +35,26 @@ For large-scale classification problems, special methods and corresponding loss | |||
|
|
|||
| * NCE solves the binary-classification problem of discriminating the true distribution and the noise distribution by converting the multi-classification problem into a classifier. The maximum likelihood estimation is performed based on the binary-classification to avoid calculating the normalization factor in the full-class space to reduce computational complexity. | |||
| * Hierarchical sigmoid realizes multi-classification by hierarchical classification of binary trees. The loss of each sample corresponds to the sum of the cross-entropy of the binary-classification for each node on the coding path, which avoids the calculation of the normalization factor and reduces the computational complexity. | |||
| The loss functions for both methods are available in Paddle Fluid. For API Reference please refer to :ref:`api_fluid_layers_nce` and :ref:`api_fluid_layers_hsigmoid`. | |||
| The loss functions for both methods are available in Paddle . For API Reference please refer to :ref:`api_paddle_static_nn_nce` and :ref:`api_paddle_nn_functional_hsigmoid_loss`. | |||
There was a problem hiding this comment.
同学看一下英文文档的 preview
这部分要加一个空行
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.
参考新文档将原来的LossFunction中使用的过时函数进行替换
Paddle 1.8 与 Paddle 2.0 API 映射表
@sunzhongkai588 @DrRyanHuang