[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition
active 2023-11-24 → 2026-05-03 (UTC)
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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| DingXiaoH | 49 | 40 | 0 | 6 |
| invictus717 | 28 | 7 | 1 | 12 |
| prestyan | 5 | 0 | 0 | 4 |
| songwan1 | 3 | 0 | 0 | 2 |
| tinggh | 2 | 0 | 0 | 1 |
| elokuuM | 2 | 0 | 0 | 1 |
| VERYBC | 2 | 0 | 0 | 1 |
| Changee-git | 2 | 0 | 0 | 1 |
| Zoesxw | 2 | 0 | 0 | 1 |
| SherryYu33 | 2 | 0 | 0 | 0 |
| EveningLin | 2 | 0 | 0 | 1 |
| zimenglan-sysu-512 | 1 | 0 | 0 | 0 |
| ZackSong0319 | 1 | 0 | 0 | 0 |
| eltociear | 1 | 0 | 1 | 0 |
| powermano | 1 | 0 | 0 | 0 |
| monologuesmw | 1 | 0 | 0 | 0 |
| ZhuShengchen | 1 | 0 | 0 | 0 |
| yanghu819 | 1 | 0 | 0 | 1 |
| Manningchan | 1 | 0 | 0 | 0 |
| TKroos18 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#24llbbl2025-06-14 19:50
- Issue comment#23DoranLyong2025-04-27 03:23Issues related to Point Cloud Training
- Issue comment#22VERYBC2024-10-30 08:47unireplknet_s is slower than convnext_b
- Issue comment#22invictus7172024-10-26 07:57unireplknet_s is slower than convnext_b
- Issue#22VERYBC2024-10-23 11:20unireplknet_s is slower than convnext_b
- Issue comment#18KT3132024-10-18 07:56Install install 19_large_depthwise_conv2d_torch_extension but ”bash: ./setup.py: Permission denied“
- Issue#21monologuesmw2024-08-29 08:34How to convert TesorRT
- Issue#20SherryYu332024-07-19 02:38How could i use reparameterization to convtranspose
- Issue#20SherryYu332024-07-18 10:30How could i use reparameterization to convtranspose
- Issue comment#19invictus7172024-07-06 08:33It's stuck in the./setup.py install --user step
- Issue comment#19Changee-git2024-07-06 01:27It's stuck in the./setup.py install --user step
- Issue#19Changee-git2024-07-03 01:40It's stuck in the./setup.py install --user step
- Issue comment#18invictus7172024-04-28 14:00Install install 19_large_depthwise_conv2d_torch_extension but ”bash: ./setup.py: Permission denied“
- Issue#18CYYJL2024-04-25 11:47Install install 19_large_depthwise_conv2d_torch_extension but ”bash: ./setup.py: Permission denied“
- Issue#17powermano2024-03-25 08:39Why 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 10:41input_size 384*128 tends to be nan
- Issue#14invictus7172024-03-12 10:41input_size 384*128 tends to be nan
- Issue comment#14Zoesxw2024-03-12 06:14input_size 384*128 tends to be nan
- Issue comment#15invictus7172024-03-11 04:22The training is very slow
- Issue#15invictus7172024-03-11 04:22The training is very slow
- Issue comment#15tinggh2024-03-11 03:02The training is very slow
- Issue comment#14invictus7172024-03-10 09:05input_size 384*128 tends to be nan
- Issue comment#15invictus7172024-03-10 08:57The training is very slow
- Issue#15tinggh2024-03-10 06:35My 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.