Skip to content

shaofengzeng/SuperPoint-Pytorch

View on GitHub ↗Related repositories →

ViT implementation of Pytorch implementation of SuperPoint

active 2023-08-172026-03-22 (UTC)

Complete coverage26,485 / 26,485 hourly files (100%) · 2 absent upstream2023-08-152026-08-22 (UTC)
Events
215
Pushes
35
Pull requests
2
Issues
13
Stars
116
Forks
23

Activity over time

Daily event counts in the loaded window

Line chart, 949 days from 2023-08-17 to 2026-03-22. Pushes: 35 total, peak 20 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 13 total, peak 1 in a day. Comments: 25 total, peak 6 in a day. Stars: 116 total, peak 3 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue#49ykang-88082025-12-15 05:54
    Environmental dependency issue
  • Issue#48Alexander88482025-04-23 06:55
    第三步是重新训还是加载预训练模型
  • Issue comment#36FreeCars2025-04-14 01:07
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#26Alexander88482025-04-14 00:51
    About pre-trained model
  • Issue comment#22ps-star2025-03-22 07:32
    About magic_point_coco_train.yaml
  • Issue comment#45ps-star2025-03-18 15:29
    你好,请问Export coco labels data set v1 这一步,是默认在cpu上执行吗,一共会有多少个npz文件导出呀,我已经跑了一天多,不太确定还需多长时间
  • Issue#47upc-sun-wukong2025-03-07 13:16
    数据集
  • Issue#46zcsgitt2025-01-12 12:09
    关于重复率和单应性估计
  • Issue comment#45shaofengzeng2025-01-11 07:50
    你好,请问Export coco labels data set v1 这一步,是默认在cpu上执行吗,一共会有多少个npz文件导出呀,我已经跑了一天多,不太确定还需多长时间
  • Issue#45jk-ux2025-01-10 13:49
    你好,请问Export coco labels data set v1 这一步,是默认在cpu上执行吗,一共会有多少个npz文件导出呀,我已经跑了一天多,不太确定还需多长时间
  • Pull request#35shaofengzeng2024-12-04 05:59
  • Issue comment#36PMRS-lab2024-11-05 09:36
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#36PMRS-lab2024-11-05 02:46
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#36LJH17560622024-11-05 02:13
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#36LJH17560622024-11-05 02:10
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#36shaofengzeng2024-11-05 02:10
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#36PMRS-lab2024-11-05 01:37
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#36shaofengzeng2024-11-04 06:54
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#36LJH17560622024-11-03 10:44
    关于使用此superpoint代码训练后的测试效果?
  • Issue comment#26RomanticFisher2024-09-03 12:45
    About pre-trained model
  • Issue#44jjn0372024-09-02 09:32
    bug
  • Issue comment#4320181313zhang2024-05-30 12:45
    请问相比于源代码做了哪些改进呢?在hpatch数据集上推理时间更快了
  • Issue#43ZhangshenHuang2024-03-13 05:26
    请问相比于源代码做了哪些改进呢?在hpatch数据集上推理时间更快了
  • Issue#42coginfsun2024-03-11 03:16
    About The pretrained model
  • Issue#40shreyasr-upenn2024-01-28 20:27
    Training Speed Quite Slow!

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 116 stars here means stars gained during the window, not the repo's star count.