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
s920243400
PaddleDetection
提交
14df92fe
P
PaddleDetection
项目概览
s920243400
/
PaddleDetection
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleDetection
通知
2
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleDetection
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
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
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
提交
14df92fe
编写于
2月 22, 2019
作者:
D
dengkaipeng
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix spell error. test=develop
上级
144016fc
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
6 addition
and
6 deletion
+6
-6
paddle/fluid/operators/detection/yolov3_loss_op.cc
paddle/fluid/operators/detection/yolov3_loss_op.cc
+6
-6
未找到文件。
paddle/fluid/operators/detection/yolov3_loss_op.cc
浏览文件 @
14df92fe
...
...
@@ -156,8 +156,8 @@ class Yolov3LossOpMaker : public framework::OpProtoAndCheckerMaker {
second(channel) dimension, apart from 4 box location coordinates x, y, w, h,
also includes confidence score of the box and class one-hot key of each anchor box.
Assume the 4 location coordinates
is
:math:`t_x, t_y, t_w, t_h`, the box predictions
should be
following
:
Assume the 4 location coordinates
are
:math:`t_x, t_y, t_w, t_h`, the box predictions
should be
as follows
:
$$
b_x = \\sigma(t_x) + c_x
...
...
@@ -172,12 +172,12 @@ class Yolov3LossOpMaker : public framework::OpProtoAndCheckerMaker {
b_h = p_h e^{t_h}
$$
In the equa
l
tion above, :math:`c_x, c_y` is the left top corner of current grid
In the equation above, :math:`c_x, c_y` is the left top corner of current grid
and :math:`p_w, p_h` is specified by anchors.
As for confidence score, it is the logistic regression value of IoU between
anchor boxes and ground truth boxes, the score of the anchor box which has
the max IoU should be 1, and if the anchor box has IoU bigger th
e
n ignore
the max IoU should be 1, and if the anchor box has IoU bigger th
a
n ignore
thresh, the confidence score loss of this anchor box will be ignored.
Therefore, the yolov3 loss consist of three major parts, box location loss,
...
...
@@ -192,13 +192,13 @@ class Yolov3LossOpMaker : public framework::OpProtoAndCheckerMaker {
In order to trade off box coordinate losses between big boxes and small
boxes, box coordinate losses will be mutiplied by scale weight, which is
calculated as follow.
calculated as follow
s
.
$$
weight_{box} = 2.0 - t_w * t_h
$$
Final loss will be represented as follow.
Final loss will be represented as follow
s
.
$$
loss = (loss_{xy} + loss_{wh}) * weight_{box}
...
...
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