A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model.
active 2023-08-16 → 2026-02-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 913 days from 2023-08-16 to 2026-02-13. Pushes: 16 total, peak 4 in a day. Pull requests: 13 total, peak 3 in a day. Issues: 7 total, peak 1 in a day. Comments: 27 total, peak 5 in a day. Stars: 364 total, peak 13 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 |
|---|---|---|---|---|
| xuyxu | 33 | 10 | 6 | 17 |
| allcontributors[bot] | 12 | 6 | 3 | 3 |
| desertSniper87 | 4 | 0 | 0 | 2 |
| wubizhi | 2 | 0 | 0 | 2 |
| maxwell1386 | 2 | 0 | 0 | 1 |
| nguyentr17 | 2 | 0 | 0 | 1 |
| TIMEXue | 1 | 0 | 0 | 0 |
| fatcatZF | 1 | 0 | 0 | 0 |
| johnny12150 | 1 | 0 | 0 | 1 |
| dependabot[bot] | 1 | 0 | 1 | 0 |
| Malephilosopher | 1 | 0 | 1 | 0 |
| h2soheili | 1 | 0 | 1 | 0 |
| antonioo-c | 1 | 0 | 0 | 0 |
| AtiqurRahmanAni | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#170fatcatZF2025-05-21 07:59How can I save the ensemble which has best validation loss during training?
- Issue comment#169nguyentr172024-12-06 01:33question about expected speedup when using parallelization via joblib
- Issue comment#169xuyxu2024-12-05 12:42question about expected speedup when using parallelization via joblib
- Issue#169nguyentr172024-12-04 14:51question about expected speedup when using parallelization via joblib
- Issue comment#168xuyxu2024-09-26 01:23can not fine-tuning after reload the model weights
- Issue comment#168wubizhi2024-09-26 00:52can not fine-tuning after reload the model weights
- Issue comment#168xuyxu2024-09-26 00:42can not fine-tuning after reload the model weights
- Issue comment#168wubizhi2024-09-25 14:54can not fine-tuning after reload the model weights
- Issue comment#168xuyxu2024-09-25 14:51can not fine-tuning after reload the model weights
- Issue comment#149xuyxu2024-06-26 14:37How to ues the result "ckpt.pth"
- Issue comment#149johnny121502024-06-22 03:24How to ues the result "ckpt.pth"
- Pull request#167xuyxu2024-06-16 13:18
- Pull request#166xuyxu2024-06-16 13:18
- Issue comment#166xuyxu2024-06-16 13:17fix bug in doubling estimators_ if model loaded from save_dir + feature for having callback after each epoch
- Issue comment#166allcontributors[bot]2024-06-16 13:17fix bug in doubling estimators_ if model loaded from save_dir + feature for having callback after each epoch
- Pull request#167allcontributors[bot]2024-06-16 13:17
- Issue comment#166xuyxu2024-06-16 13:17fix bug in doubling estimators_ if model loaded from save_dir + feature for having callback after each epoch
- Pull request#166h2soheili2024-06-14 13:16
- Issue comment#165desertSniper872024-04-23 12:53Getting Embeddings from the base model
- Issue#165desertSniper872024-04-23 12:53Getting Embeddings from the base model
- Issue comment#165xuyxu2024-04-23 10:53Getting Embeddings from the base model
- Issue comment#165desertSniper872024-04-22 03:32Getting Embeddings from the base model
- Issue comment#165xuyxu2024-04-22 01:34Getting Embeddings from the base model
- Releasexuyxu2024-04-22 01:27v0.2.0
- Issue#165desertSniper872024-04-19 18:22Getting Embeddings from the base model
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 364 stars here means stars gained during the window, not the repo's star count.