Unofficial implementation of "(ICCV'23) Learning to Upsample by Learning to Sample"
active 2024-02-13 → 2026-04-04 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 782 days from 2024-02-13 to 2026-04-04. Pushes: 5 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 13 total, peak 5 in a day. Comments: 14 total, peak 3 in a day. Stars: 82 total, peak 2 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 |
|---|---|---|---|---|
| poppuppy | 19 | 5 | 0 | 7 |
| honghess | 3 | 0 | 0 | 1 |
| AliasChenYi | 3 | 0 | 0 | 2 |
| Prown666 | 2 | 0 | 0 | 0 |
| Zhangyucong0210 | 2 | 0 | 0 | 2 |
| swjtunb | 1 | 0 | 0 | 1 |
| 2001luo | 1 | 0 | 0 | 0 |
| kk2565 | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#22poppuppy2025-08-21 14:04fix a bug
- Issue#11poppuppy2025-03-12 04:17Is there a version for 3D images?
- Issue#14poppuppy2025-03-12 04:17Change feature dim
- Issue comment#19kk25652025-03-12 02:30The results of each run are inconsistent
- Issue comment#19swjtunb2025-03-09 02:52The results of each run are inconsistent
- Issue comment#17poppuppy2024-11-08 02:14Why do I replace the deconvolution of the decoder with Dysample(lp) during training? The GPU memory overhead is even greater，From the original 17GB to 22GB
- Issue#15Prown6662024-11-08 02:11Can feature scale upsampling be singular before and after, such as x1=(1, 64, 80, 45) x2=(1, 64, 40, 23)
- Issue comment#15poppuppy2024-11-03 08:55Can feature scale upsampling be singular before and after, such as x1=(1, 64, 80, 45) x2=(1, 64, 40, 23)
- Issue#162001luo2024-10-29 02:11提问
- Issue#15Prown6662024-10-20 07:46Can feature scale upsampling be singular before and after, such as x1=(1, 64, 80, 45) x2=(1, 64, 40, 23)
- Issue comment#14poppuppy2024-09-04 02:12Change feature dim
- Issue comment#13poppuppy2024-08-19 05:17Can this method be included when converting the model to ONNX format and running it on OpenCV?
- Issue#10poppuppy2024-06-29 14:26The model structure is inconsistent with the code description
- Issue#8poppuppy2024-06-29 14:25Hi, I am getting the following error after I introduced DySample to the network and would like to hear from you.
- Issue#7poppuppy2024-06-29 14:25dysample channel
- Issue#6poppuppy2024-06-29 14:25pl和lp
- Issue#5poppuppy2024-06-29 14:25onnx export
- Issue comment#10poppuppy2024-06-21 11:27The model structure is inconsistent with the code description
- Issue comment#10AliasChenYi2024-06-21 06:02The model structure is inconsistent with the code description
- Issue comment#10AliasChenYi2024-06-21 06:00The model structure is inconsistent with the code description
- Issue#10AliasChenYi2024-06-21 06:00The model structure is inconsistent with the code description
- Issue#9honghess2024-04-22 02:00（pl+8）速度确实比双线性插值快
- Issue comment#9honghess2024-04-21 09:51（pl+8）速度确实比双线性插值快，但是对精度的损害太高了，所需显存和3d性能也有少量和大量的增幅
- Issue#9honghess2024-04-21 09:26（pl+8）速度确实比双线性插值快，但是对精度的损害太高了，所需显存和3d性能也有少量和大量的增幅
- Issue comment#8poppuppy2024-04-03 06:49Hi, I am getting the following error after I introduced DySample to the network and would like to hear from you.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 82 stars here means stars gained during the window, not the repo's star count.