Skip to content

[CVPR 2024] DynamicDet: A Unified Dynamic Architecture for Object Detection

active 2023-08-212025-07-31 (UTC)

Complete coverage26,495 / 26,495 hourly files (100%) · 2 absent upstream2023-08-152026-08-22 (UTC)
Events
102
Pushes
1
Pull requests
3
Issues
20
Stars
49
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 711 days from 2023-08-21 to 2025-07-31. Pushes: 1 total, peak 1 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 20 total, peak 4 in a day. Comments: 20 total, peak 4 in a day. Stars: 49 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

ContributorContributionsPushesPRsComments
LZHgrla151111
mansi-aggarwal-250414004
CZY-Code3001
feidufuzhou3001
gongyan12001
fxYOLO2020
ojasvijain2001
zhuxz02991000
chenxlin2221000
Wang-Ling-jie1001

Recent activity

Latest issues, pull requests and releases

  • Issue#30zhuxz02992024-06-29 06:34
    在训练了几个epoch之后报错:CUDA out of memory
  • Pull request#29fxYOLO2024-04-16 11:55
  • Pull request#29fxYOLO2024-04-01 04:03
  • Issue comment#28LZHgrla2024-03-25 03:38
    Why do you use segmentation labels instead of bounding boxes in the COCO dataset?
  • Issue comment#28gongyan12024-03-25 02:02
    Why do you use segmentation labels instead of bounding boxes in the COCO dataset?
  • Issue comment#28LZHgrla2024-03-24 14:48
    Why do you use segmentation labels instead of bounding boxes in the COCO dataset?
  • Issue#28gongyan12024-03-24 13:23
    Why do you use segmentation labels instead of bounding boxes in the COCO dataset?
  • Issue#27mansi-aggarwal-25042024-02-21 02:38
    Continue training model on new data
  • Issue comment#26ojasvijain2024-01-09 23:16
    Evaluation metrics explanation
  • Issue comment#26LZHgrla2024-01-09 08:30
    Evaluation metrics explanation
  • Issue#26ojasvijain2024-01-08 23:10
    Evaluation metrics explanation
  • Issue#25mansi-aggarwal-25042023-12-17 23:32
    Early stopping or using epoch_xx.pt
  • Issue comment#25mansi-aggarwal-25042023-12-17 23:30
    Early stopping or using epoch_xx.pt
  • Issue#25mansi-aggarwal-25042023-12-17 23:30
    Early stopping or using epoch_xx.pt
  • Issue#24mansi-aggarwal-25042023-12-14 23:46
    Config for custom data
  • Issue#25mansi-aggarwal-25042023-12-14 23:46
    Early stopping or using epoch_xx.pt
  • Issue comment#24LZHgrla2023-12-14 08:36
    Config for custom data
  • Issue comment#24mansi-aggarwal-25042023-12-14 08:34
    Config for custom data
  • Issue comment#25LZHgrla2023-12-14 08:34
    Early stopping or using epoch_xx.pt
  • Issue comment#24LZHgrla2023-12-14 08:29
    Config for custom data
  • Issue#25mansi-aggarwal-25042023-12-13 22:33
    Early stopping or using epoch_xx.pt
  • Issue#24mansi-aggarwal-25042023-12-13 21:09
    Config for custom data
  • Issue#23mansi-aggarwal-25042023-12-13 21:07
    Which model path should be provided for dynamic thresholds for variable-speed inference step?
  • Issue comment#23LZHgrla2023-12-11 04:06
    Which model path should be provided for dynamic thresholds for variable-speed inference step?
  • Issue comment#23mansi-aggarwal-25042023-12-10 22:39
    Which model path should be provided for dynamic thresholds for variable-speed inference step?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 49 stars here means stars gained during the window, not the repo's star count.