Skip to content

[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

active 2023-11-242026-05-03 (UTC)

Complete coverage26,443 / 26,443 hourly files (100%) · 2 absent upstream2023-08-152026-08-20 (UTC)
Events
1.2K
Pushes
47
Pull requests
3
Issues
31
Stars
1K
Forks
63

Activity over time

Daily event counts in the loaded window

Line chart, 892 days from 2023-11-24 to 2026-05-03. Pushes: 47 total, peak 11 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 31 total, peak 3 in a day. Comments: 34 total, peak 3 in a day. Stars: 1,036 total, peak 76 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

  • Pull request#24llbbl2025-06-14 19:50
  • Issue comment#23DoranLyong2025-04-27 03:23
    Issues related to Point Cloud Training
  • Issue comment#22VERYBC2024-10-30 08:47
    unireplknet_s is slower than convnext_b
  • Issue comment#22invictus7172024-10-26 07:57
    unireplknet_s is slower than convnext_b
  • Issue#22VERYBC2024-10-23 11:20
    unireplknet_s is slower than convnext_b
  • Issue comment#18KT3132024-10-18 07:56
    Install install 19_large_depthwise_conv2d_torch_extension but ”bash: ./setup.py: Permission denied“
  • Issue#21monologuesmw2024-08-29 08:34
    How to convert TesorRT
  • Issue#20SherryYu332024-07-19 02:38
    How could i use reparameterization to convtranspose
  • Issue#20SherryYu332024-07-18 10:30
    How could i use reparameterization to convtranspose
  • Issue comment#19invictus7172024-07-06 08:33
    It's stuck in the./setup.py install --user step
  • Issue comment#19Changee-git2024-07-06 01:27
    It's stuck in the./setup.py install --user step
  • Issue#19Changee-git2024-07-03 01:40
    It's stuck in the./setup.py install --user step
  • Issue comment#18invictus7172024-04-28 14:00
    Install install 19_large_depthwise_conv2d_torch_extension but ”bash: ./setup.py: Permission denied“
  • Issue#18CYYJL2024-04-25 11:47
    Install install 19_large_depthwise_conv2d_torch_extension but ”bash: ./setup.py: Permission denied“
  • Issue#17powermano2024-03-25 08:39
    Why ConvNeXT does not using droppath.
  • Issue#16wsy-yjys2024-03-16 09:35
    关于UniRepLKNetBlock中的self.gamma的作用
  • Issue comment#14invictus7172024-03-12 10:41
    input_size 384*128 tends to be nan
  • Issue#14invictus7172024-03-12 10:41
    input_size 384*128 tends to be nan
  • Issue comment#14Zoesxw2024-03-12 06:14
    input_size 384*128 tends to be nan
  • Issue comment#15invictus7172024-03-11 04:22
    The training is very slow
  • Issue#15invictus7172024-03-11 04:22
    The training is very slow
  • Issue comment#15tinggh2024-03-11 03:02
    The training is very slow
  • Issue comment#14invictus7172024-03-10 09:05
    input_size 384*128 tends to be nan
  • Issue comment#15invictus7172024-03-10 08:57
    The training is very slow
  • Issue#15tinggh2024-03-10 06:35
    My train seems too slow comoared with ConvNeXt and SwinTransformer

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,036 stars here means stars gained during the window, not the repo's star count.