darknet之VSCode单步调试

最新推荐文章于 2023-07-28 12:59:07 发布

原创最新推荐文章于 2023-07-28 12:59:07 发布 · 458 阅读

2 ·

CC 4.0 BY-SA版权

deeplearning 专栏收录该内容

77 篇文章

订阅专栏

本文详细介绍使用Darknet进行目标检测训练的配置方法与具体流程，包括launch.json文件的设置，Makefile中CFLAGS参数的调整，以及从darknet.c到train_network_datum的完整调用过程。

1. How

参考这篇博客

launch.json内容如下

{
// Use IntelliSense to learn about possible attributes.
// Hover to view descriptions of existing attributes.
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0",
"configurations": [
    {
        "name": "region",
        "type": "cppdbg",
        "request": "launch",
        "program": "${workspaceFolder}/darknet",
        "args": ["detector", "train", "${workspaceFolder}/data/candle.data", "${workspaceFolder}/cfg/candle11-tr.cfg", "${workspaceFolder}/yolov2-tiny.conv.11"],
        "stopAtEntry": false,
        "cwd": "${workspaceFolder}",
        "environment": [],
        "externalConsole": false,
        "MIMode": "gdb",
        "preLaunchTask": "make",
        "setupCommands": [
            {
                "description": "Enable pretty-printing for gdb",
                "text": "-enable-pretty-printing",
                "ignoreFailures": true
            }
        ]
    }
]}

修改Makefile，在CFLAGS最后加-g

2. 训练流程

darknet.c调用detector.c的run_detector
run_detector调用train_detector
train_detector调用parser.c的parse_network_cfg，实际调用parse_network_cfg_custom
- parse_network_cfg_custom调用解析网络层的函数，以region层为例，调用parse_region
- parse_region调用region_layer.c的make_region_layer，并设置anchor
train_detector调用data.c的load_data
train_detector调用network.c的train_network_waitkey（只用1个GPU时）
- train_network_waitkey调用train_network_datum
- train_network_datum调用forward_network和backward_network
train_detector调用validate_detector_map（需要的时候）