Official implementation of SAMformer, a transformer leveraging Sharpness-Aware Minimization and Channel-Wise Attention for Time Series Forecasting.
active 2024-02-07 → 2026-01-16 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 710 days from 2024-02-07 to 2026-01-16. Pushes: 63 total, peak 14 in a day. Pull requests: 5 total, peak 2 in a day. Issues: 28 total, peak 6 in a day. Comments: 22 total, peak 4 in a day. Stars: 168 total, peak 6 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 |
|---|---|---|---|---|
| romilbert | 43 | 33 | 1 | 9 |
| ambroiseodt | 31 | 17 | 1 | 3 |
| AmbroiseOdonnat | 9 | 9 | 0 | 0 |
| erickmiller | 6 | 0 | 1 | 3 |
| Alsac | 5 | 0 | 0 | 1 |
| vfeofanov | 5 | 4 | 0 | 1 |
| fuyw | 3 | 0 | 0 | 1 |
| seunghan96 | 3 | 0 | 0 | 2 |
| unihe | 2 | 0 | 0 | 1 |
| kkiskkk | 2 | 0 | 0 | 1 |
| Elnur21 | 1 | 0 | 1 | 0 |
| ZYBOBO | 1 | 0 | 0 | 0 |
| lilyniu | 1 | 0 | 0 | 0 |
| hadaid | 1 | 0 | 0 | 0 |
| eltociear | 1 | 0 | 1 | 0 |
| DizhenLiang | 1 | 0 | 0 | 0 |
| rvandewater | 1 | 0 | 0 | 0 |
| Seham-Nasr | 1 | 0 | 0 | 0 |
| HuangZR-stu | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#19DizhenLiang2025-04-25 07:52Random Seed
- Issue#18hadaid2025-03-27 10:19The normalization issue in the PyTorch version of the code.
- Issue comment#15Alsac2025-01-12 03:26About model parameters.
- Issue comment#17seunghan962024-12-07 20:26Reproducibility issue
- Issue comment#17romilbert2024-12-07 20:23Reproducibility issue
- Issue comment#17seunghan962024-12-07 20:13Reproducibility issue
- Issue#17seunghan962024-12-07 18:42Reproducibility issue
- Issue comment#15romilbert2024-11-20 16:12About model parameters.
- Issue comment#14ambroiseodt2024-11-20 16:07Is this step function necessary? I didn't find any input for “closure”？
- Issue#14ambroiseodt2024-11-20 16:07Is this step function necessary? I didn't find any input for “closure”？
- Pull request#3ambroiseodt2024-11-20 15:49
- Issue#15ambroiseodt2024-11-20 15:25About model parameters.
- Issue#16ambroiseodt2024-11-20 15:15Adding models to "Time Series Library"
- Issue comment#16ambroiseodt2024-11-20 15:15Adding models to "Time Series Library"
- Issue#16rvandewater2024-09-30 09:50Adding models to "Time Series Library"
- Issue#13fuyw2024-09-28 12:34Question about the output shape?
- Issue#15Alsac2024-09-27 08:02About model parameters.
- Issue#14HuangZR-stu2024-09-16 18:54Is this step function necessary? I didn't find any input for “closure”？
- Issue comment#13fuyw2024-09-03 19:42Question about the output shape?
- Issue#13fuyw2024-09-03 19:30Question about the output shape?
- Issue#7ambroiseodt2024-08-30 11:27Training on time series datasets with different dimensions
- Issue#6ambroiseodt2024-08-30 11:26Using pytorch version for multivariate regression on variable length 1D output
- Issue#5ambroiseodt2024-08-30 11:25TypeError: save_additional_metrics() takes 5 positional arguments
- Issue#11ambroiseodt2024-08-30 11:24How to obtain the visualization results of attention?
- Issue#8ambroiseodt2024-08-30 11:24Training with GPU reports error tensorflow and cudnn version mismatch
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 168 stars here means stars gained during the window, not the repo's star count.