Skip to content

ChenhongyiYang/QueryDet-PyTorch

View on GitHub ↗Related repositories →

[CVPR 2022 Oral] QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection

active 2023-08-172026-03-13 (UTC)

Partial coverage21,659 / 26,308 hourly files (82%) · 2 absent upstream · 4,648 failed, retryable2023-08-152026-08-15 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
153
Pushes
0
Pull requests
0
Issues
22
Stars
87
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 940 days from 2023-08-17 to 2026-03-13. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 22 total, peak 4 in a day. Comments: 36 total, peak 5 in a day. Stars: 87 total, peak 2 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 comment#100yuwentao882025-08-20 01:42
    about time consuming when training and test with query
  • Issue comment#100yuwentao882025-08-20 01:38
    about time consuming when training and test with query
  • Issue#106zjh-lgtm2025-08-19 04:44
    test problem
  • Issue#105zjh-lgtm2025-08-18 10:49
    cuda
  • Issue#95nooneAB2024-08-23 03:17
    Hello, the AP result I gave after training with the default settings is quite low, only 0.XXXX data, not even 1, I want to know where my reason appears
  • Issue#103nooneAB2024-08-23 02:15
    About the gap in results on Visdrone
  • Issue comment#90pkuj1032024-07-09 06:46
    attribute:'torch.device' object has no attribute 'device'
  • Issue comment#90pkuj1032024-07-09 06:36
    attribute:'torch.device' object has no attribute 'device'
  • Issue#102wisan-dhammatorn2024-07-06 09:32
    How to visualize query heatmap from test image
  • Issue#101wenxi22024-06-30 12:50
    reg loss function
  • Issue comment#90nooneAB2024-06-11 02:47
    attribute:'torch.device' object has no attribute 'device'
  • Issue comment#90201916612024-06-11 02:44
    attribute:'torch.device' object has no attribute 'device'
  • Issue#100shaoyandea2024-06-05 05:48
    about time consuming when training and test with query
  • Issue comment#97shaoyandea2024-06-05 01:06
    Hi, we have recently updated a new VisDrone training config (gradient clip added), which can avoid NaN now.
  • Issue comment#98lebron-20162024-06-04 02:11
    A question about the efficiency of 2D sparse operations
  • Issue comment#40lebron-20162024-06-02 07:58
    loss nan!
  • Issue#98lebron-20162024-06-02 07:42
    A question about the efficiency of 2D sparse operations
  • Issue comment#40shaoyandea2024-05-31 01:22
    loss nan!
  • Issue#97shaoyandea2024-05-31 01:18
    Hi, we have recently updated a new VisDrone training config (gradient clip added), which can avoid NaN now.
  • Issue#96liuw202024-05-10 06:16
    Does the environment configuration affect the experimental results?
  • Issue#96liuw202024-05-10 06:16
    Does the environment configuration affect the experimental results?
  • Issue#96liuw202024-05-10 06:16
    Does the environment configuration affect the experimental results?
  • Issue comment#96liuw202024-05-10 06:15
    Does the environment configuration affect the experimental results?
  • Issue comment#96liuw202024-05-10 03:58
    Does the environment configuration affect the experimental results?
  • Issue#96liuw202024-05-10 03:57
    Does the environment configuration affect the experimental results?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 87 stars here means stars gained during the window, not the repo's star count.