这是各个主干网络分类模型的源码，可以用于训练自己的分类模型。
active 2023-08-15 → 2026-03-29 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 958 days from 2023-08-15 to 2026-03-29. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 1 in a day. Comments: 10 total, peak 6 in a day. Stars: 109 total, peak 2 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 |
|---|---|---|---|---|
| zhujilin1995 | 4 | 0 | 0 | 4 |
| seudwh123 | 3 | 0 | 0 | 3 |
| Bug-CUDA | 2 | 0 | 0 | 1 |
| renyu-renyu | 2 | 0 | 0 | 1 |
| hao-ux | 1 | 0 | 0 | 1 |
| ScottXiao233 | 1 | 0 | 0 | 0 |
| 2458zhanghehe | 1 | 0 | 0 | 0 |
| liu491197006 | 1 | 0 | 0 | 0 |
| xuwenlong0315 | 1 | 0 | 0 | 0 |
| heeeeyuhang | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#362458zhanghehe2024-10-26 15:16release_v1.0里面少了swinTransformer的base权重
- Issue#35liu4911970062024-07-04 07:44从0开始训练的效果差
- Issue#34heeeeyuhang2024-06-28 11:08使用vit进行预测的问题
- Issue#33Bug-CUDA2024-06-21 02:28报错RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasSgemm
- Issue comment#3Bug-CUDA2024-06-21 02:20迭代到50之后就停止了
- Issue comment#27zhujilin19952024-03-18 03:55为什么验证精度比训练精度高？
- Issue comment#27seudwh1232024-03-18 03:47为什么验证精度比训练精度高？
- Issue comment#27zhujilin19952024-03-18 03:42为什么验证精度比训练精度高？
- Issue comment#27seudwh1232024-03-18 03:28为什么验证精度比训练精度高？
- Issue comment#27zhujilin19952024-03-18 03:22为什么验证精度比训练精度高？
- Issue comment#27zhujilin19952024-03-18 02:55为什么验证精度比训练精度高？
- Issue comment#27seudwh1232024-03-07 01:23为什么验证精度比训练精度高？
- Issue comment#30hao-ux2024-02-08 05:49为什么dataloader中没有标签的onehot编码？
- Issue#30xuwenlong03152023-12-21 02:23为什么dataloader中没有标签的onehot编码？
- Issue#28ScottXiao2332023-11-25 03:19Google Drive预训练权重
- Issue#27renyu-renyu2023-11-18 01:51为什么验证精度比训练精度高？
- Issue comment#19renyu-renyu2023-11-14 06:19您好，请问dataloader中对验证集数据先resize再center_crop的目的是什么呢？
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 109 stars here means stars gained during the window, not the repo's star count.