最近重温DETR模型,越发感觉detr模型结构精妙之处,不同于anchor base 与anchor free设计,直接利用100框给出预测结果,使用可学习learn query深度查找,使用二分匹配方式训练模型。为此,我基于detr源码提取解码decode、loss计算等系列模块,并重构、修改、整合一套解码与loss实现的框架,该框架可适用任何backbone特征提取接我框架,实现完整训练与预测,我也有相应demo指导使用我的�
active 2023-11-02 → 2025-01-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 446 days from 2023-11-02 to 2025-01-20. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 4 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Nobody pushed, opened or commented here in the loaded window — this repo's activity is stars and forks only.
Recent activity
Latest issues, pull requests and releases
No issue or PR events — this repo's activity is pushes only.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 4 stars here means stars gained during the window, not the repo's star count.