当前位置:网站首页>Anchor free series network yolox source code line by line explanation Part 2 (a total of 10, ensure to explain line by line, after reading, you can change the network at will, not just as a participan
Anchor free series network yolox source code line by line explanation Part 2 (a total of 10, ensure to explain line by line, after reading, you can change the network at will, not just as a participan
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 Middle class PAFPN The construction of the structure , Before that, you must read an article , Otherwise, there will be many articles in this one that cannot be understood .
Above, YOLOX Of FPN Implementation diagram of structure , 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 . Start by opening yolox\models\yolo_pafpn.py. Whole FPN The official implementation process of is only the following code , It can be said that it is very simple . Simple statements will be directly annotated :
边栏推荐
- Android advanced interview question record in 2022
- Vb+access hotel service management system
- 2021 Li Hongyi machine learning (2): pytorch
- 【LeetCode】404. Sum of left leaves (2 brushes of wrong questions)
- [download white paper] does your customer relationship management (CRM) really "manage" customers?
- Privatization lightweight continuous integration deployment scheme -- 01 environment configuration (Part 1)
- 腾讯云,实现图片上传
- Why is this an undefined behavior- Why is this an undefined behavior?
- El select, El option drop-down selection box
- ELFK部署
猜你喜欢
【LeetCode】110. Balanced binary tree (2 brushes of wrong questions)
Learn game model 3D characters, come out to find a job?
Chinese natural language processing, medical, legal and other public data sets, sorting and sharing
Sqoop命令
2021 Li Hongyi machine learning (3): what if neural network training fails
Zabbix
ELFK部署
【LeetCode】222. The number of nodes of a complete binary tree (2 mistakes)
this+闭包+作用域 面试题
Yolov5 model training and detection
随机推荐
Breaking the information cocoon - my method of actively obtaining information - 3
Azkaban安装部署
【LeetCode】501. Mode in binary search tree (2 wrong questions)
this+闭包+作用域 面试题
Apache Web page security optimization
Azkaban概述
Why are there fewer and fewer good products produced by big Internet companies such as Tencent and Alibaba?
Bumblebee: build, deliver, and run ebpf programs smoothly like silk
[uc/os-iii] chapter 1.2.3.4 understanding RTOS
Linux Installation redis
打破信息茧房-我主动获取信息的方法 -#3
Which common ports should the server open
How to make OS X read bash_ Profile instead of Profile file - how to make OS X to read bash_ profile not . profile file
Zabbix
2021 Li Hongyi machine learning (1): basic concepts
Design and practice of kubernetes cluster and application monitoring scheme
Start the remedial work. Print the contents of the array using the pointer
Master Fur
Use UDP to send a JPEG image, and UPD will convert it into the mat format of OpenCV after receiving it
Sqoop命令