@@ -201,7 +201,7 @@ The recognition model is the same.
## WINDOWS Users
Windows does not support Pipeline Serving, if we want to lauch paddle serving on Windows, we should use Web Service, for more infomation please refer to [Paddle Serving for Windows Users](https://github.com/PaddlePaddle/Serving/blob/develop/doc/WINDOWS_TUTORIAL.md)
Windows does not support Pipeline Serving, if we want to lauch paddle serving on Windows, we should use Web Service, for more infomation please refer to [Paddle Serving for Windows Users](https://github.com/PaddlePaddle/Serving/blob/develop/doc/Windows_Tutorial_EN.md)
**WINDOWS user can only use version 0.5.0 CPU Mode**
Focal Loss 出自论文《Focal Loss for Dense Object Detection》, 该loss最先提出的时候主要是为了解决one-stage目标检测中正负样本比例严重失衡的问题。该损失函数降低了大量简单负样本在训练中所占的权重,也可理解为一种困难样本挖掘。
Focal Loss 出自论文《[Focal Loss for Dense Object Detection](https://arxiv.org/abs/1708.02002)》, 该loss最先提出的时候主要是为了解决one-stage目标检测中正负样本比例严重失衡的问题。该损失函数降低了大量简单负样本在训练中所占的权重,也可理解为一种困难样本挖掘。
其损失函数形式如下:
<divalign="center">
<imgsrc="./focal_loss_formula.png"width = "600"/>
</div>
...
...
@@ -29,50 +30,51 @@ Focal Loss 出自论文《Focal Loss for Dense Object Detection》, 该loss最
C-CTC Loss是CTC Loss + Center Loss的简称。 其中Center Loss出自论文《[A Discriminative Feature Learning Approach for Deep Face Recognition](https://link.springer.com/chapter/10.1007/978-3-319-46478-7_31)》。最早用于人脸识别任务,用于增大类间距离,减小类内距离, 是Metric Learning领域一种较早的、也比较常用的一种算法。