[Docathon][Update Doc No.29] fix the LossFunction

docs/api_guides/low_level/layers/loss_function.rst

@@ -1,60 +1,60 @@
 ..  _api_guide_loss_function:
 
-#######
+############
 损失函数
-#######
+############
 
 损失函数定义了拟合结果和真实结果之间的差异，作为优化的目标直接关系模型训练的好坏，很多研究工作的内容也集中在损失函数的设计优化上。
-Paddle Fluid 中提供了面向多种任务的多种类型的损失函数，以下列出了一些 Paddle Fluid 中包含的较为常用的损失函数。
+Paddle 中提供了面向多种任务的多种类型的损失函数，以下列出了一些 Paddle 中包含的较为常用的损失函数。
 
 回归
-====
+======
 
 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_paddle_nn_functional_square_error_cost`。
 
 平滑 L1 损失（smooth_l1 loss）是一种分段的损失函数，较平方误差损失其对异常点相对不敏感，因而更为鲁棒。
-API Reference 请参考 :ref:`cn_api_fluid_layers_smooth_l1`。
+API Reference 请参考 :ref:`cn_api_paddle_nn_functional_smooth_l1_loss`。
 
 
 分类
-====
+======
 
-`交叉熵（cross entropy） <https://en.wikipedia.org/wiki/Cross_entropy>`_ 是分类问题中使用最为广泛的损失函数，Paddle Fluid 中提供了接受归一化概率值和非归一化分值输入的两种交叉熵损失函数的接口，并支持 soft label 和 hard label 两种样本类别标签。
-API Reference 请参考 :ref:`cn_api_fluid_layers_cross_entropy` 和 :ref:`cn_api_fluid_layers_softmax_with_cross_entropy`。
+`交叉熵（cross entropy） <https://en.wikipedia.org/wiki/Cross_entropy>`_ 是分类问题中使用最为广泛的损失函数，Paddle 中提供了接受归一化概率值和非归一化分值输入的两种交叉熵损失函数的接口，并支持 soft label 和 hard label 两种样本类别标签。
+API Reference 请参考 :ref:`cn_api_paddle_nn_functional_cross_entropy`。
 
 多标签分类
----------
-对于多标签分类问题，如一篇文章同属于政治、科技等多个类别的情况，需要将各类别作为独立的二分类问题计算损失，Paddle Fluid 中为此提供了 sigmoid_cross_entropy_with_logits 损失函数，
-API Reference 请参考 :ref:`cn_api_fluid_layers_sigmoid_cross_entropy_with_logits`。
+---------------------
+对于多标签分类问题，如一篇文章同属于政治、科技等多个类别的情况，需要将各类别作为独立的二分类问题计算损失，Paddle 中为此提供了 binary_cross_entropy 损失函数，
+API Reference 请参考 :ref:`cn_api_paddle_nn_functional_binary_cross_entropy`。
 
 大规模分类
----------
+---------------------
 对于大规模分类问题，通常需要特殊的方法及相应的损失函数以加速训练，常用的方法有 `噪声对比估计（Noise-contrastive estimation，NCE） <http://proceedings.mlr.press/v9/gutmann10a/gutmann10a.pdf>`_ 和 `层级 sigmoid <http://www.iro.umontreal.ca/~lisa/pointeurs/hierarchical-nnlm-aistats05.pdf>`_ 。
 
 * 噪声对比估计通过将多分类问题转化为学习分类器来判别数据来自真实分布和噪声分布的二分类问题，基于二分类来进行极大似然估计，避免在全类别空间计算归一化因子从而降低了计算复杂度。
 * 层级 sigmoid 通过二叉树进行层级的二分类来实现多分类，每个样本的损失对应了编码路径上各节点二分类交叉熵的和，避免了归一化因子的计算从而降低了计算复杂度。
-这两种方法对应的损失函数在 Paddle Fluid 中均有提供，API Reference 请参考 :ref:`cn_api_fluid_layers_nce` 和 :ref:`cn_api_fluid_layers_hsigmoid`。
+
+这两种方法对应的损失函数在 Paddle 中均有提供，API Reference 请参考 :ref:`cn_api_paddle_static_nn_nce` 和 :ref:`cn_api_paddle_nn_functional_hsigmoid_loss`。
 
 序列分类
--------
-序列分类可以分为以下三种：
+---------------------
+序列分类可以分为以下两种：
 
 * 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 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`。
 
 排序
-====
+======
 
 `排序问题 <https://en.wikipedia.org/wiki/Learning_to_rank>`_ 可以使用 Pointwise、Pairwise 和 Listwise 的学习方法，不同的方法需要使用不同的损失函数：
 
 * Pointwise 的方法通过近似为回归问题解决排序问题，可以使用回归问题的损失函数。
-* Pairwise 的方法需要特殊设计的损失函数，其通过近似为分类问题解决排序问题，使用两篇文档与 query 的相关性得分以偏序作为二分类标签来计算损失。Paddle Fluid 中提供了两种常用的 Pairwise 方法的损失函数，API Reference 请参考 :ref:`cn_api_fluid_layers_rank_loss` 和 :ref:`cn_api_fluid_layers_margin_rank_loss`。
+* Pairwise 的方法需要特殊设计的损失函数，其通过近似为分类问题解决排序问题，使用两篇文档与 query 的相关性得分以偏序作为二分类标签来计算损失。Paddle 中提供了一种常用的 Pairwise 方法的损失函数，API Reference 请参考 :ref:`cn_api_paddle_nn_functional_margin_ranking_loss`。
 
 更多
-====
+======
 
-对于一些较为复杂的损失函数，可以尝试使用其他损失函数组合实现；Paddle Fluid 中提供的用于图像分割任务的 :ref:`cn_api_fluid_layers_dice_loss` 即是使用其他 OP 组合（计算各像素位置似然概率的均值）而成；多目标损失函数也可看作这样的情况，如 Faster RCNN 就使用 cross entropy 和 smooth_l1 loss 的加权和作为损失函数。
+对于一些较为复杂的损失函数，可以尝试使用其他损失函数组合实现；Paddle 中提供的用于图像分割任务的 :ref:`cn_api_paddle_nn_functional_dice_loss` 即是使用其他 OP 组合（计算各像素位置似然概率的均值）而成；多目标损失函数也可看作这样的情况，如 Faster RCNN 就使用 cross entropy 和 smooth_l1 loss 的加权和作为损失函数。
 
-**注意**，在定义损失函数之后为能够使用 :ref:`api_guide_optimizer` 进行优化，通常需要使用 :ref:`cn_api_fluid_layers_mean` 或其他操作将损失函数返回的高维 Tensor 转换为 Scalar 值。
+**注意**，在定义损失函数之后为能够使用 :ref:`api_guide_optimizer` 进行优化，通常需要使用 :ref:`cn_api_paddle_mean` 或其他操作将损失函数返回的高维 Tensor 转换为 Scalar 值。

docs/api_guides/low_level/layers/loss_function_en.rst

@@ -5,28 +5,28 @@ Loss function
 ##############
 
 The loss function defines the difference between the inference result and the ground-truth result. As the optimization target, it directly determines whether the model training is good or not, and many researches also focus on the optimization of the loss function design.
-Paddle Fluid offers diverse types of loss functions for a variety of tasks. Let's take a look at the commonly-used loss functions included in Paddle Fluid.
+Paddle  offers diverse types of loss functions for a variety of tasks. Let's take a look at the commonly-used loss functions included in Paddle .
 
 Regression
 ===========
 
 The squared error loss uses the square of the error between the predicted value and the ground-truth value as the sample loss, which is the most basic loss function in the regression problems.
-For API Reference,  please refer to :ref:`api_fluid_layers_square_error_cost`.
+For API Reference,  please refer to :ref:`api_paddle_nn_functional_square_error_cost`.
 
 Smooth L1 loss (smooth_l1 loss) is a piecewise loss function that is relatively insensitive to outliers and therefore more robust.
-For API Reference,  please refer to :ref:`api_fluid_layers_smooth_l1`.
+For API Reference,  please refer to :ref:`api_paddle_nn_functional_smooth_l1_loss`.
 
 
 Classification
 ================
 
-`cross entropy <https://en.wikipedia.org/wiki/Cross_entropy>`_ is the most widely used loss function in classification problems.  The interfaces in Paddle Fluid for the cross entropy loss functions are divided into the one accepting fractional input of normalized probability values ​​and another for non-normalized input. And Fluid supports two types labels, namely soft label and hard label.
-For API Reference,  please refer to :ref:`api_fluid_layers_cross_entropy` and :ref:`api_fluid_layers_softmax_with_cross_entropy`.
+`cross entropy <https://en.wikipedia.org/wiki/Cross_entropy>`_ is the most widely used loss function in classification problems.  The interfaces in Paddle  for the cross entropy loss functions are divided into the one accepting fractional input of normalized probability values ​​and another for non-normalized input. And  supports two types labels, namely soft label and hard label.
+For API Reference,  please refer to :ref:`api_nn_functional_cross_entropy`.
 
 Multi-label classification
 ----------------------------
 For the multi-label classification, such as the occasion that an article belongs to multiple categories like politics, technology, it is necessary to calculate the loss by treating each category as an independent binary-classification problem. We provide the sigmoid_cross_entropy_with_logits loss function for this purpose.
-For API Reference,  please refer to :ref:`api_fluid_layers_sigmoid_cross_entropy_with_logits`.
+For API Reference,  please refer to :ref:`api_paddle_nn_functional_binary_cross_entropy`.
 
 Large-scale classification
 -----------------------------
@@ -35,27 +35,27 @@ 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`.
 
 Sequence classification
 -------------------------
-Sequence classification can be divided into the following three types:
+Sequence classification can be divided into the following two types:
 
 * Sequence Classification problem is that the entire sequence corresponds to a prediction label, such as text classification. This is a common classification problem, you can use cross entropy as the loss function.
-* Segment Classification problem is that each segment in the sequence corresponds to its own category tag, such as named entity recognition. For this sequence labeling problem, `the (Linear Chain) Conditional Random Field (CRF) <http://www.cs.columbia.edu/~mcollins/fb.pdf>`_ is a commonly used model. The method uses the likelihood probability on the sentence level, and the labels for different positions in the sequence are no longer conditionally independent, which can effectively solve the label offset problem. Support for CRF loss functions is available in Paddle Fluid. For API Reference please refer to :ref:`api_fluid_layers_linear_chain_crf` .
-* Temporal Classification problem needs to label unsegmented sequences, such as speech recognition. For this time-based classification problem, `CTC(Connectionist Temporal Classification) <http://people.idsia.ch/~santiago/papers/icml2006.pdf>`_ loss function does not need to align input data and labels, and is able to perform end-to-end training. Paddle Fluid provides a warpctc interface to calculate the corresponding loss. For API Reference,  please refer to :ref:`api_fluid_layers_warpctc` .
+* Temporal Classification problem needs to label unsegmented sequences, such as speech recognition. For this time-based classification problem, `CTC(Connectionist Temporal Classification) <http://people.idsia.ch/~santiago/papers/icml2006.pdf>`_ loss function does not need to align input data and labels, and is able to perform end-to-end training. Paddle  provides a warpctc interface to calculate the corresponding loss. For API Reference,  please refer to :ref:`api_paddle_nn_functional_ctc_loss` .
 
 Rank
 =========
 
 `Rank problems <https://en.wikipedia.org/wiki/Learning_to_rank>`_ can use learning methods of Pointwise, Pairwise, and Listwise. Different methods require different loss functions:
 
 * The Pointwise method solves the ranking problem by approximating the regression problem. Therefore the loss function of the regression problem can be used.
-* Pairwise's method requires a special loss function. Pairwise solves the sorting problem by approximating the classification problem, using relevance score of two documents and the query to use the partial order as the binary-classification label to calculate the loss. Paddle Fluid provides two commonly used loss functions for Pairwise methods. For API Reference please refer to :ref:`api_fluid_layers_rank_loss` and :ref:`api_fluid_layers_margin_rank_loss`.
+* Pairwise's method requires a special loss function. Pairwise solves the sorting problem by approximating the classification problem, using relevance score of two documents and the query to use the partial order as the binary-classification label to calculate the loss. Paddle  provides one commonly used loss functions for Pairwise methods. For API Reference please refer to :ref:`api_paddle_nn_functional_margin_ranking_loss`.
 
 More
 ====
 
-For more complex loss functions, try to use combinations of other loss functions; the :ref:`api_fluid_layers_dice_loss` provided in Paddle Fluid for image segmentation tasks is an example of using combinations of other operators  (calculate the average likelihood probability of each pixel position). The multi-objective loss function can also be considered similarly, such as Faster RCNN that uses the weighted sum of cross entropy and smooth_l1 loss as a loss function.
+For more complex loss functions, try to use combinations of other loss functions; the :ref:`api_paddle_nn_functional_dice_loss` provided in Paddle  for image segmentation tasks is an example of using combinations of other operators  (calculate the average likelihood probability of each pixel position). The multi-objective loss function can also be considered similarly, such as Faster RCNN that uses the weighted sum of cross entropy and smooth_l1 loss as a loss function.
 
-**Note**, after defining the loss function, in order to optimize with :ref:`api_guide_optimizer_en`, you usually need to use :ref:`api_fluid_layers_mean` or other operations to convert the high-dimensional Tensor returned by the loss function to a Scalar value.
+**Note**, after defining the loss function, in order to optimize with :ref:`api_guide_optimizer_en`, you usually need to use :ref:`api_paddle_mean` or other operations to convert the high-dimensional Tensor returned by the loss function to a Scalar value.