AlibabaResearch / AlibabaResearch/efficientteacher

训练自己数据集过程中P/R成0了是哪里参数配错了吗?

Open
#98 11 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
813
Forks
126
PR merge metrics
No merged PRs in 30d

Description

![QQ20230610-0](https://github.com/AlibabaResearch/efficientteacher/assets/41991173/88b48062-96a9-4ee5-b2b7-ed682e826248)

训练自己数据集过程中P/R成0了是哪里参数配错了吗?
1.我用yolov5,训练了5个epochs全监督学习,得到一个权重custom_best.pt;
2.我将这个权重通过 convert_pt_to_efficient.py 转换成 efficient-yolov5s.pt;
3.通过 find -name "*.jpg" >> unlabel.txt 生成对应的伪标签txt文件
4. 参考 configs/ssod/custom/yolov5l_custom_ssod.yaml 自定义一份 yolov5s_custom_ssod.yaml 配置数据,weights是efficient-yolov5s.pt, epochs = 50 默认burn_epochs 为 10;

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.