1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.
active 2023-08-16 → 2026-01-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 881 days from 2023-08-16 to 2026-01-12. Pushes: 9 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 17 total, peak 3 in a day. Comments: 30 total, peak 17 in a day. Stars: 169 total, peak 24 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 |
|---|---|---|---|---|
| blackfeather-wang | 32 | 9 | 0 | 18 |
| liaochuanlin | 6 | 0 | 0 | 4 |
| Osilly | 3 | 0 | 0 | 1 |
| yuncheng97 | 3 | 0 | 0 | 1 |
| whalien-902 | 3 | 0 | 0 | 3 |
| Cheng-lg | 2 | 0 | 0 | 1 |
| iminfine | 2 | 0 | 0 | 1 |
| ericyq | 1 | 0 | 0 | 1 |
| cpy0029 | 1 | 0 | 0 | 0 |
| Wuismeya | 1 | 0 | 0 | 0 |
| 13213085 | 1 | 0 | 0 | 0 |
| Fischer-pixel | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#12Wuismeya2025-05-07 06:34On inverse Fourier transform in frequency clipping
- Issue comment#11iminfine2024-06-19 23:06Command script bugs
- Issue#11blackfeather-wang2024-06-18 16:55Command script bugs
- Issue comment#11blackfeather-wang2024-06-18 12:06Command script bugs
- Issue comment#11blackfeather-wang2024-06-18 11:55Command script bugs
- Issue#11iminfine2024-06-18 11:50Command script bugs
- Issue#10blackfeather-wang2024-06-04 03:14about RandAug
- Issue comment#10blackfeather-wang2024-06-04 03:14about RandAug
- Issue#10liaochuanlin2024-06-03 08:39about RandAug
- Issue comment#9Cheng-lg2024-06-01 17:44Can i use your method in nlp task such as glue?
- Issue#9Cheng-lg2024-06-01 17:43Can i
- Issue#8Fischer-pixel2024-06-01 07:21how to use it in yolo training like yolov8?
- Issue#7blackfeather-wang2024-05-30 15:45关于训练流程的疑问
- Issue#6blackfeather-wang2024-05-30 14:15About low-pass filtering
- Issue#7132130852024-05-30 08:13关于训练流程的疑问
- Issue comment#6blackfeather-wang2024-05-29 11:41About low-pass filtering
- Issue comment#6whalien-9022024-05-29 07:03About low-pass filtering
- Issue comment#6whalien-9022024-05-29 07:03About low-pass filtering
- Issue comment#6blackfeather-wang2024-05-29 02:54About low-pass filtering
- Issue comment#6whalien-9022024-05-28 16:44About low-pass filtering
- Issue comment#3blackfeather-wang2024-05-28 15:41about code
- Issue comment#3liaochuanlin2024-05-28 12:51about code
- Issue comment#3blackfeather-wang2024-05-28 12:38about code
- Issue comment#3blackfeather-wang2024-05-28 12:30about code
- Issue comment#3blackfeather-wang2024-05-28 12:29about code
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 169 stars here means stars gained during the window, not the repo's star count.