remove background
Python · active 2025-03-07 → 2026-07-24 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 505 days from 2025-03-07 to 2026-07-24. Pushes: 24 total, peak 3 in a day. Pull requests: 4 total, peak 2 in a day. Issues: 74 total, peak 8 in a day. Comments: 175 total, peak 9 in a day. Stars: 646 total, peak 10 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 |
|---|---|---|---|---|
| ZhengPeng7 | 121 | 24 | 1 | 78 |
| pedroHuang123 | 11 | 0 | 0 | 7 |
| nx1 | 8 | 0 | 0 | 4 |
| zhenzi0322 | 8 | 0 | 0 | 6 |
| Soumya2564 | 6 | 0 | 0 | 4 |
| zgdaaa | 5 | 0 | 0 | 5 |
| hzx13249055 | 5 | 0 | 0 | 3 |
| lucasgblu | 4 | 0 | 0 | 4 |
| aichromator | 4 | 0 | 0 | 2 |
| Yionidas | 4 | 0 | 0 | 4 |
| RAE-CO | 3 | 0 | 0 | 3 |
| ShirasawaSama | 3 | 0 | 0 | 3 |
| Leonora-xy | 3 | 0 | 0 | 1 |
| Karllas | 3 | 0 | 0 | 1 |
| maomaoeatfish | 3 | 0 | 0 | 3 |
| Looki2000 | 3 | 0 | 0 | 1 |
| kparikh-tenup | 3 | 0 | 0 | 2 |
| imperatormk | 3 | 0 | 0 | 3 |
| poilly54 | 3 | 0 | 0 | 1 |
| pangxiaobin | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#262RChoukri032026-05-24 13:01How to improve segmentation accuracy for car side mirrors and background objects
- Issue comment#167ShirasawaSama2026-04-07 17:13Export dynamic batch size ONNX using ONNX's DeformConv
- Issue comment#298ZhengPeng72026-03-29 23:58404 Not Found huggingface link error
- Issue comment#299ZhengPeng72026-03-25 09:03[HELP] Official Onnx Weights - Tried community onnx but they dont support batching
- Issue#287ZhengPeng72026-03-24 14:09python3.13+Pytorch 2.10.0+cu130使用BiRefNet_ll报错
- Issue comment#167ShirasawaSama2026-03-03 19:14Export dynamic batch size ONNX using ONNX's DeformConv
- Issue comment#292ZhengPeng72026-03-01 12:35我把birefnet下载到了本地，我想要用它在vscode中批量抠图，如何配置呢？（我只会comfyui中使用）
- Issue comment#292hothotds2026-03-01 12:34我把birefnet下载到了本地，我想要用它在vscode中批量抠图，如何配置呢？（我只会comfyui中使用）
- Issue#282ZhengPeng72026-02-26 20:59多次调用backbone提取多尺度特征
- Issue#281ZhengPeng72026-02-26 20:58deformable卷积在高通芯片不支持npu推理
- Issue comment#273ZhengPeng72026-02-26 20:56关于dinov3的模型训练
- Issue comment#167ShirasawaSama2026-02-26 11:39Export dynamic batch size ONNX using ONNX's DeformConv
- Issue comment#291ZhengPeng72026-02-25 15:21有没有办法扣动漫视频素材
- Issue comment#216GICMan2026-02-15 18:56Module Import Syntax
- Issue comment#285ZhengPeng72026-02-13 07:25Incompatibility with transformers 5.x - "Tensor.item() cannot be called on meta tensors"
- Issue comment#285zlylupaf2026-02-13 07:11Incompatibility with transformers 5.x - "Tensor.item() cannot be called on meta tensors"
- Issue#289pedroHuang1232026-02-09 09:38background_color_synthesis=True时训练结果很差
- Issue#288zhoujunbo2026-02-07 14:22自训练模型在文字为主体的抠图效果不佳问题
- Issue comment#286pedroHuang1232026-02-07 10:24训练时的输入分辨率直接resize成1024*1024会出现变形，是不是该改成等比例resize比较好？
- Issue comment#286pedroHuang1232026-02-07 10:21训练时的输入分辨率直接resize成1024*1024会出现变形，是不是该改成等比例resize比较好？
- Issue comment#286ZhengPeng72026-02-07 10:20训练时的输入分辨率直接resize成1024*1024会出现变形，是不是该改成等比例resize比较好？
- Issue comment#286pedroHuang1232026-02-07 10:19训练时的输入分辨率直接resize成1024*1024会出现变形，是不是该改成等比例resize比较好？
- Issue comment#286ZhengPeng72026-02-06 10:34训练时的输入分辨率直接resize成1024*1024会出现变形，是不是该改成等比例resize比较好？
- Issue comment#285ZhengPeng72026-02-04 22:51Incompatibility with transformers 5.x - "Tensor.item() cannot be called on meta tensors"
- Issue comment#45Yionidas2026-02-03 21:28CoreML model
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 646 stars here means stars gained during the window, not the repo's star count.