Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
Paddle
提交
a2327374
P
Paddle
项目概览
PaddlePaddle
/
Paddle
大约 1 年 前同步成功
通知
2292
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
a2327374
编写于
8月 15, 2021
作者:
H
HydrogenSulfate
提交者:
chajchaj
8月 27, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Update loss.py
上级
87513117
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
5 addition
and
5 deletion
+5
-5
python/paddle/nn/functional/loss.py
python/paddle/nn/functional/loss.py
+5
-5
未找到文件。
python/paddle/nn/functional/loss.py
浏览文件 @
a2327374
...
...
@@ -1521,7 +1521,7 @@ def cross_entropy(input,
:math:`[N_1, N_2, ..., N_k]` or :math:`[N_1, N_2, ..., N_k, 1]`, k >= 1.
the data type is int32, int64, float32, float64, where each value is [0, C-1].
2. If soft_label=True, the shape and data type should be same with ``input`` ,
2. If soft_label=True, the shape and data type should be same with ``input`` ,
and the sum of the labels for each sample should be 1.
- **weight** (Tensor, optional)
...
...
@@ -1606,7 +1606,7 @@ def cross_entropy(input,
Example2(soft labels):
.. code-block:: python
import paddle
paddle.seed(99999)
axis = -1
...
...
@@ -1889,12 +1889,12 @@ def sigmoid_focal_loss(logit,
it is used in one-stage object detection where the foreground-background class
imbalance is extremely high.
This operator measures focal loss function as follows:
This operator measures focal loss function as follows:
.. math::
Out = -Labels * alpha * {(1 - \sigma(Logit))}^{gamma}\log(\sigma(Logit)) - (1 - Labels) * (1 - alpha) * {\sigma(Logit)}^{gamma}\log(1 - \sigma(Logit))
We know that :math:`\sigma(Logit) = \frac{1}{1 + \exp(-Logit)}`.
We know that :math:`\sigma(Logit) = \frac{1}{1 + \exp(-Logit)}`.
Then, if :attr:`normalizer` is not None, this operator divides the
normalizer tensor on the loss `Out`:
...
...
@@ -1921,7 +1921,7 @@ def sigmoid_focal_loss(logit,
For object detection task, it is the the number of positive samples.
If set to None, the focal loss will not be normalized. Default is None.
alpha(int|float, optional): Hyper-parameter to balance the positive and negative example,
it should be between 0 and 1. Default value is set to 0.25.
it should be between 0 and 1. Default value is set to 0.25.
gamma(int|float, optional): Hyper-parameter to modulate the easy and hard examples.
Default value is set to 2.0.
reduction (str, optional): Indicate how to average the loss by batch_size,
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录