Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.
active 2023-08-16 → 2026-03-31 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 959 days from 2023-08-16 to 2026-03-31. Pushes: 20 total, peak 2 in a day. Pull requests: 52 total, peak 11 in a day. Issues: 158 total, peak 52 in a day. Comments: 153 total, peak 35 in a day. Stars: 461 total, peak 5 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 |
|---|---|---|---|---|
| luyao-cv | 71 | 0 | 0 | 16 |
| jerrywgz | 70 | 2 | 12 | 35 |
| cuicheng01 | 48 | 15 | 17 | 0 |
| westfish | 34 | 0 | 0 | 31 |
| paddle-bot[bot] | 16 | 0 | 0 | 16 |
| Bradly-s | 15 | 0 | 0 | 2 |
| Tortoise17 | 8 | 0 | 0 | 0 |
| liuhongen1234567 | 7 | 0 | 7 | 0 |
| Sunting78 | 5 | 1 | 4 | 0 |
| stereomatchingkiss | 5 | 0 | 0 | 2 |
| omp009 | 3 | 0 | 0 | 2 |
| swithmn1 | 3 | 0 | 0 | 0 |
| kakarotto007 | 3 | 0 | 0 | 0 |
| myAhua | 3 | 0 | 0 | 2 |
| CLAassistant | 3 | 0 | 0 | 3 |
| lmc2000 | 3 | 0 | 0 | 3 |
| dyning | 3 | 1 | 1 | 0 |
| fanplanet | 3 | 0 | 0 | 0 |
| liziqing123 | 2 | 0 | 0 | 2 |
| Tongkaio | 2 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#733KiritoMxh12025-12-05 09:17paddleVideo导出模型的问题
- Issue#737sqh852025-12-02 10:0812345
- Issue comment#730CuiYX032025-11-25 08:22模型导出只有json文件pdiparams文件
- Issue#355gzxy01022025-11-17 09:08使用NTU-RGBD数据集时配置文件报错
- Issue#733KiritoMxh12025-09-24 07:03paddleVideo导出模型的问题
- Issue#732RUM-RUM2025-05-27 03:03能否将pdiparams转换回pdparams
- Issue comment#731hybh-t2025-04-30 12:41FSD30的训练精度可以达到89%，但为何测试集的精度只有21%
- Issue#731hybh-t2025-04-30 12:40FSD30的训练精度可以达到89%，但为何测试集的精度只有21%
- Issue comment#694zhanshenbangde2025-04-01 09:41ppvideo: command not found
- Issue#730Tiseeee2025-03-30 03:30模型导出只有json文件pdiparams文件
- Issue comment#567cxkk1112025-03-21 09:21Football的LSTM模型导出输入tensor是6个，lstm_infer.py推理代码输入tensor是2个，导致推理失败。
- Issue comment#6852108LEO2025-03-09 04:27BILS 视频标注工具标注完成，导出json格式文件后，是不是还需要处理下才可以得到训练需要数据集？我看文档没有后续的相关介绍
- Issue#7294RSENALZ2025-03-08 03:13关于MutimodalVideoTag
- Issue comment#6784RSENALZ2025-03-05 08:07关于multimodalVideotag的问题
- Pull request#728Sunting782025-02-12 06:53
- Issue comment#728paddle-bot[bot]2025-02-11 12:55fix json model export format
- Pull request#728Sunting782025-02-11 12:55
- Issue comment#627yll12025-02-10 02:53ppvideo --model_name='ppTSM_v2' --use_gpu=True --video_file='data/example.avi' 不工作
- Issue#727ksdyxx2025-01-27 04:07FootballAction 训练PP-TSM时报错
- Issue#725Luhuanz2025-01-15 11:52环境问题 ，希望更新一下readme, 很多环境都跑不通
- Issue comment#726paddle-bot[bot]2025-01-13 09:47yowo for paddlex
- Pull request#724cuicheng012025-01-13 03:38
- Issue comment#724paddle-bot[bot]2025-01-10 06:33yowo for paddlex
- Pull request#724Sunting782025-01-10 06:33
- Pull request#717cuicheng012025-01-09 04:45
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 461 stars here means stars gained during the window, not the repo's star count.