training stuff
active 2024-03-30 → 2026-06-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 810 days from 2024-03-30 to 2026-06-17. Pushes: 10 total, peak 2 in a day. Pull requests: 6 total, peak 1 in a day. Issues: 42 total, peak 4 in a day. Comments: 78 total, peak 12 in a day. Stars: 794 total, peak 8 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 |
|---|---|---|---|---|
| hzwer | 55 | 10 | 2 | 29 |
| Felix3322 | 12 | 0 | 0 | 12 |
| ZXMMD | 4 | 0 | 0 | 1 |
| husssaince | 4 | 0 | 0 | 3 |
| pengjunxing | 4 | 0 | 0 | 3 |
| guijuzhejiang | 3 | 0 | 0 | 1 |
| yeluohuazhifou | 3 | 0 | 0 | 2 |
| MikuIsMyLife | 3 | 0 | 0 | 1 |
| liyuli1997 | 3 | 0 | 0 | 2 |
| zehaisang | 3 | 0 | 0 | 1 |
| tyDiffusion | 3 | 0 | 0 | 1 |
| luyiwen-user | 2 | 0 | 0 | 1 |
| routineLife1 | 2 | 0 | 0 | 2 |
| aiyuedeyang | 2 | 0 | 0 | 1 |
| Threepointso | 2 | 0 | 0 | 1 |
| Dianli-Moli | 2 | 0 | 0 | 2 |
| ROTTK | 2 | 0 | 0 | 1 |
| Ofrila | 2 | 0 | 0 | 1 |
| DataAIPlayer | 2 | 0 | 1 | 1 |
| DX8906 | 2 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#85Felix33222026-03-15 23:34"assert len(arr) == framesize" throws an error
- Issue comment#128Felix33222026-03-15 23:34Training with mixed-precision
- Issue comment#133Felix33222026-03-15 23:34Open Issue of Motion Estimation
- Issue comment#140Felix33222026-03-15 23:34Could TPUs/XLA increase performance?
- Issue comment#152Felix33222026-03-15 23:34FFmpeg error
- Issue comment#188Felix33222026-03-15 23:34Errors when using fp16-mode with high resolutions
- Issue comment#205Felix33222026-03-15 23:34纯色背景或天空位置的马赛克问题
- Issue comment#280Felix33222026-03-15 23:33train error (nccl) torch.distributed
- Issue comment#287Felix33222026-03-15 23:33对相邻帧之间的补帧，同样的场景输入图像大小不同补帧结果不同
- Issue comment#301Felix33222026-03-15 23:33[Enhancement] Use MPS for device when the repository is running in MacOS
- Issue comment#307Felix33222026-03-15 23:30将fastmode设置为false后图像的插帧效果不佳
- Issue comment#337Felix33222026-03-15 23:30Failed to retrieve frame 0 with error: Resize error: Resize error 3074: unrecognized color primaries (1/1/0 => 0/1/0)
- Issue comment#266Yunxiang-Wang2026-03-09 02:41显存6G不够用，请问如何兼顾4K视频精度下解决这个问题、
- Issue comment#388kubinka05052026-02-07 21:29NumPy Deprecation Issues and Installation Failures in scikit-video
- Issue comment#223Devilmanta2026-01-16 15:43video glitch/distorted at the beginning
- Pull request#407ben8132025-12-02 00:55
- Issue#404Threepointso2025-09-12 02:29如何改变训练时输入图像的尺寸 并且不会使得模型性能下降
- Issue comment#384Threepointso2025-09-12 02:27关于RIFE模型，为什么在训练的时候图片固定为224*224，但在推理时任意尺寸图片都可以进行处理
- Issue comment#401hzwer2025-08-31 13:30模型都跑哪里去了？
- Issue#400poooyanpoo128-cyber2025-08-24 12:29pelak
- Issue comment#399hzwer2025-08-21 06:19关于任意帧插值
- Issue#399FkMauzi2025-08-21 02:29关于任意帧插值
- Issue#385hzwer2025-07-28 06:56scale=0.5或者0.25时报错
- Issue comment#385hzwer2025-07-25 09:02scale=0.5或者0.25时报错
- Issue comment#385w-zinan2025-07-23 02:24scale=0.5或者0.25时报错
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 794 stars here means stars gained during the window, not the repo's star count.