Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
active 2023-08-18 → 2026-05-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 988 days from 2023-08-18 to 2026-05-01. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 4 total, peak 1 in a day. Comments: 6 total, peak 4 in a day. Stars: 151 total, peak 3 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 |
|---|---|---|---|---|
| cjc20000323 | 3 | 0 | 0 | 3 |
| williamium3000 | 2 | 0 | 0 | 1 |
| wxqyyds | 1 | 0 | 0 | 0 |
| hanyiwei799 | 1 | 0 | 0 | 0 |
| onlinehuazai | 1 | 0 | 0 | 0 |
| yiwengxie | 1 | 0 | 0 | 1 |
| dahuaxiya | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#54hanyiwei7992024-09-02 09:58训练的准确率一直是10%，显然是没有作用的因为一共就只有10个类别
- Issue comment#42yiwengxie2024-04-25 11:22train failed when EMA mode is off
- Issue#53onlinehuazai2024-03-27 05:25每次加载训练好的模型，结果都不一样
- Issue#52wxqyyds2024-03-08 08:25RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'
- Issue comment#23cjc200003232024-01-10 08:06Using fixmatch to train on my dataset, LR = 0.03, batchsize = 64. When the unlabeled loss increases gradually, the model gets worse and worse, and the loss of training set will decrease, but the loss of verification set will increase, and the accuracy will decrease?
- Issue comment#50cjc200003232024-01-10 05:23why add a interleave before the input?
- Issue#50williamium30002024-01-10 05:22why add a interleave before the input?
- Issue comment#50williamium30002024-01-10 05:22why add a interleave before the input?
- Issue comment#50cjc200003232024-01-10 05:13why add a interleave before the input?
- Issue comment#42dahuaxiya2023-08-18 02:14train failed when EMA mode is off
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 151 stars here means stars gained during the window, not the repo's star count.