[CVPR 2023] Code for PConv and FasterNet
active 2023-08-15 → 2026-05-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 997 days from 2023-08-15 to 2026-05-07. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 26 total, peak 3 in a day. Comments: 24 total, peak 3 in a day. Stars: 380 total, peak 4 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 |
|---|---|---|---|---|
| nobody2231 | 7 | 0 | 0 | 3 |
| hefangnan | 4 | 0 | 0 | 3 |
| xiaoche-24 | 4 | 0 | 0 | 1 |
| haiduo | 3 | 0 | 0 | 1 |
| GUIMINLONG | 2 | 0 | 0 | 1 |
| Aurora-zgz | 2 | 0 | 0 | 2 |
| kido1412y2y | 2 | 0 | 0 | 2 |
| BUHUIQUMING-D | 2 | 0 | 0 | 2 |
| Zhangyuhaoo | 1 | 0 | 0 | 0 |
| xuewengeophysics | 1 | 0 | 0 | 1 |
| PowerKaly | 1 | 0 | 0 | 0 |
| 23jisuper | 1 | 0 | 0 | 0 |
| YuchaoXu | 1 | 0 | 0 | 0 |
| WCC0810 | 1 | 0 | 0 | 0 |
| 1chenchen22 | 1 | 0 | 0 | 1 |
| 19970393981 | 1 | 0 | 0 | 0 |
| Sparklexa | 1 | 0 | 0 | 1 |
| jinlingwang0326 | 1 | 0 | 0 | 1 |
| puyiwen | 1 | 0 | 0 | 0 |
| mojeedoyedeji | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#51hairenaa2024-11-13 02:59怎样采用Pconv+Pwconv替换常规的3x3卷积？
- Issue#69199703939812024-11-12 11:38I encountered an error when using the train command
- Issue comment#54Aurora-zgz2024-11-12 02:25When I load the pre-training weights times get get-root-logger not found
- Issue comment#35Aurora-zgz2024-11-12 02:23some question
- Issue#68WCC08102024-10-31 07:00About PWConv
- Issue#67GUIMINLONG2024-10-30 08:19Dose it support input as "32-bit float image"?
- Issue comment#52xuewengeophysics2024-09-14 03:46pconv+pwconv
- Issue#66Zhangyuhaoo2024-08-31 02:28Concerns about information loss
- Issue#65zhangchengyumiao2024-08-23 09:19加载了预训练的权重后模型评估分数只有1分是为什么，前面两个预训练权重都试过了，找不到问题所在，请问能否提供一下帮助。
- Issue comment#34lizha0yan2024-08-01 23:40About the use of pconv in resnet
- Issue comment#49Sparklexa2024-07-24 07:37How to get a pretrained weight
- Issue comment#34BUHUIQUMING-D2024-07-21 07:12About the use of pconv in resnet
- Issue comment#47BUHUIQUMING-D2024-07-21 06:20Completely replace Resnet18 with FasterNet?
- Issue#64wsy-yjys2024-05-10 09:14FasterNet 在GPU, CPU, and ARM processors上的速度是直接基于pytorch环境，还是使用了Tensorrt、OpenVINO、ONNX进行了部署
- Issue#63Weeknd02142024-04-06 13:34这样的配置文件怎么在pcconv里融合注意力机制呢
- Issue comment#511chenchen222024-03-26 08:52怎样采用Pconv+Pwconv替换常规的3x3卷积？
- Issue comment#61GUIMINLONG2024-03-14 05:26Configuration steps for other datasets
- Issue comment#34okt77602024-01-28 07:16About the use of pconv in resnet
- Issue comment#34myiy2024-01-28 06:57About the use of pconv in resnet
- Issue#6223jisuper2024-01-22 03:29Partial_conv3和group convolution
- Issue#61mojeedoyedeji2024-01-04 07:43Configuration steps for other datasets
- Issue comment#51duoxiangqinzuo2023-12-20 07:26怎样采用Pconv+Pwconv替换常规的3x3卷积？
- Issue#58xiaoche-242023-12-19 09:30onnx转为trt后，速度提升不明显
- Issue#60puyiwen2023-12-19 01:31为什么要把pooling层放在1x1卷积之前？
- Issue#59PowerKaly2023-12-08 01:57关于网络结构打印出来和论文不一致的问题
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 380 stars here means stars gained during the window, not the repo's star count.