当前位置:网站首页>Three line by line explanations of the source code of anchor free series network yolox (a total of ten articles, which are guaranteed to be explained line by line. After reading it, you can change the
Three line by line explanations of the source code of anchor free series network yolox (a total of ten articles, which are guaranteed to be explained line by line. After reading it, you can change the
2022-07-05 02:47:00 【@Flying caterpillar】
The whole series includes :Demo Explain the source code line by line ->train The script source code is explained line by line ->backbone Explain the source code line by line ->FPN Explain the source code line by line ->Head Explain the source code line by line ->loss Explain the source code line by line -> The source code of data loading is explained line by line -> The source code of data enhancement is explained line by line ->simOTA Explain the source code line by line . Ensure line by line , Note that line by line , Include python grammar ,tensor Role and application of dimension and line by line code . In fact, there is no mystery about the network structure , It's a stack of modules , There is no reason why you can modify any module . After reading this series, I can do anything about any network structure at will , It's not just limited to one caller .
This article is about YOLOX Medium decoupling Head Build , Before that, you must read the previous blog posts , Otherwise, there will be a lot of content in this article that you can't understand .
Above, YOLOX Network structure diagram of the whole decoupling head . The yellow font is the intermediate variable in the code , Easy to understand . Dimension is when yolox_s Network is the output characteristic dimension of the whole network , And the default detection categories are 8 individual . First of all, we must understand what is decoupling head : Decoupling head is to separate classification and detection tasks . Classification task and regression task are completely different in principle , Forecast them separately , The accuracy of the results is improved , Real time proof is true
边栏推荐
- 【LeetCode】98. Verify the binary search tree (2 brushes of wrong questions)
- d3js小记
- Bert fine tuning skills experiment
- [micro service SCG] 33 usages of filters
- TCP security of network security foundation
- The most powerful new household god card of Bank of communications. Apply to earn 2100 yuan. Hurry up if you haven't applied!
- Unpool(nn.MaxUnpool2d)
- Problem solving: attributeerror: 'nonetype' object has no attribute 'append‘
- 2021 Li Hongyi machine learning (1): basic concepts
- Application and Optimization Practice of redis in vivo push platform
猜你喜欢
Apache Web page security optimization
Master Fur
Exploration of short text analysis in the field of medical and health (I)
Devtools的简单使用
Design of KTV intelligent dimming system based on MCU
Application and Optimization Practice of redis in vivo push platform
【LeetCode】106. Construct binary tree from middle order and post order traversal sequence (wrong question 2)
为什么腾讯阿里等互联网大厂诞生的好产品越来越少?
Linux安装Redis
Design of kindergarten real-time monitoring and control system
随机推荐
Eight days of learning C language - while loop (embedded) (single chip microcomputer)
Azkaban实战
Open source SPL optimized report application coping endlessly
Sqoop command
Hmi-32- [motion mode] add light panel and basic information column
Asp+access campus network goods trading platform
Blue bridge - maximum common divisor and minimum common multiple
When the low alcohol race track enters the reshuffle period, how can the new brand break the three major problems?
Azkaban安装部署
TCP security of network security foundation
Utilisation simple de devtools
Kotlin - coroutine
Zabbix
Azkaban overview
丸子百度小程序详细配置教程,审核通过。
Unpool(nn.MaxUnpool2d)
Hmi-31- [motion mode] solve the problem of picture display of music module
Use UDP to send a JPEG image, and UPD will convert it into the mat format of OpenCV after receiving it
Bumblebee: build, deliver, and run ebpf programs smoothly like silk
Single line function*