A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.
active 2023-08-15 → 2026-04-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 980 days from 2023-08-15 to 2026-04-20. Pushes: 7 total, peak 6 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 3 total, peak 1 in a day. Comments: 7 total, peak 2 in a day. Stars: 293 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 |
|---|---|---|---|---|
| zanshuxun | 6 | 6 | 0 | 0 |
| sosixyz | 2 | 0 | 0 | 2 |
| LebranceBW | 2 | 0 | 0 | 1 |
| Ringokohi123 | 2 | 0 | 0 | 1 |
| Tiandooo | 1 | 0 | 0 | 1 |
| lowenhu | 1 | 0 | 0 | 1 |
| HighingLIN | 1 | 0 | 0 | 1 |
| zhuchenxi | 1 | 0 | 0 | 0 |
| shenweichen | 1 | 1 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Releaseshenweichen2026-04-18 05:14v0.3.2
- Issue comment#106LebranceBW2025-02-26 07:30这个 deepmatch.utils.sampledsoftmaxloss 的实现是有意为之吗？还是说仅仅是个错误
- Issue comment#106Tiandooo2025-02-26 05:23这个 deepmatch.utils.sampledsoftmaxloss 的实现是有意为之吗？还是说仅仅是个错误
- Issue comment#93sosixyz2025-02-23 03:39utils.py的inner product实现有问题
- Issue comment#66sosixyz2025-02-23 03:18关于create_embedding_dict里面embedding_name 重复的问题
- Issue#106LebranceBW2025-01-27 07:53这个 deepmatch.utils.sampledsoftmaxloss 的实现是有意为之吗？还是说仅仅是个错误
- Issue comment#104Ringokohi1232024-05-28 06:25预估生成user_embedding时，提取YoutubeDNN模型结构报错
- Issue#104Ringokohi1232024-05-28 06:16预估生成user_embedding时，提取YoutubeDNN模型结构报错
- Issue comment#99lowenhu2023-12-07 08:55dssm模型保存报错
- Issue#101zhuchenxi2023-10-15 14:21当对DSSM模型设置sample_weight会报错
- Issue comment#29HighingLIN2023-09-01 05:32How to load saved SDM weights properly to reproduce embeddings？
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 293 stars here means stars gained during the window, not the repo's star count.