Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
yolov7_migraphx
Commits
5b756a4c
Commit
5b756a4c
authored
Oct 17, 2023
by
liucong
Browse files
修改readme
parent
b6dc9b65
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
3 additions
and
3 deletions
+3
-3
Doc/YoloV7_model.png
Doc/YoloV7_model.png
+0
-0
README.md
README.md
+3
-3
No files found.
Doc/YoloV7
模型结构
.png
→
Doc/YoloV7
_model
.png
View file @
5b756a4c
File moved
README.md
View file @
5b756a4c
...
...
@@ -8,13 +8,13 @@ YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object
## 模型结构
YOLOV7是2022年最新出现的一种YOLO系列目标检测模型,
在论文
[
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
](
https://arxiv.org/abs/2207.02696
)
中提出
。
YOLOV7是2022年最新出现的一种YOLO系列目标检测模型,
该模型的网络结构包括三个部分:input、backbone和head
。
<img
src=
"./Doc/YoloV7
模型结构
.png"
alt=
"YOLOV7_02"
style=
"zoom:67%;"
/>
<img
src=
"./Doc/YoloV7
_model
.png"
alt=
"YOLOV7_02"
style=
"zoom:67%;"
/>
## 算法原理
YoloV7模型的网络结构包括三个部分:input、backbone和head。
与yolov5不同的是,将neck层与head层合称为head层,实际上的功能是一样的。各个部分的功能和yolov5相同,如backbone用于提取特征,head用于预测。yolov7依旧基于anchor based的方法,同时在网络架构上增加E-ELAN层,并将REP层也加入进来,方便后续部署,同时在训练时,在head时,新增Aux_detect用于辅助检测。
与yolov5不同的是,
yolov7
将neck层与head层合称为head层,实际上的功能是一样的。各个部分的功能和yolov5相同,如backbone用于提取特征,head用于预测。yolov7依旧基于anchor based的方法,同时在网络架构上增加E-ELAN层,并将REP层也加入进来,方便后续部署,同时在训练时,在head时,新增Aux_detect用于辅助检测。
## 环境配置
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment