利用掩码图像预训练实现高效的通用分割
active 2023-12-05 → 2026-05-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 896 days from 2023-12-05 to 2026-05-18. Pushes: 76 total, peak 43 in a day. Pull requests: 17 total, peak 2 in a day. Issues: 92 total, peak 5 in a day. Comments: 203 total, peak 16 in a day. Stars: 2,272 total, peak 175 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 |
|---|---|---|---|---|
| yformer | 106 | 18 | 2 | 73 |
| balakv504 | 64 | 54 | 0 | 10 |
| sulaimanvesal | 8 | 0 | 0 | 7 |
| colinator | 7 | 0 | 0 | 4 |
| klightz | 6 | 4 | 0 | 2 |
| silinsi | 5 | 0 | 0 | 4 |
| Yy4441867 | 5 | 0 | 0 | 0 |
| carlosuc3m | 5 | 0 | 0 | 2 |
| feivellau | 5 | 0 | 0 | 4 |
| ghm666 | 4 | 0 | 0 | 1 |
| MrPeterJin | 4 | 0 | 0 | 2 |
| liutongkun | 4 | 0 | 0 | 4 |
| duxuan11 | 4 | 0 | 0 | 2 |
| WanBenLe | 4 | 0 | 0 | 4 |
| ccy610 | 4 | 0 | 0 | 2 |
| UyeYwb | 4 | 0 | 0 | 4 |
| CurryKd7 | 4 | 0 | 0 | 3 |
| xinli2008 | 3 | 0 | 0 | 2 |
| SoTosorrow | 3 | 0 | 2 | 1 |
| xwhkkk | 3 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Pull request#81Abbsalehi2026-01-04 19:20
- Issue#80Feng-Rui2025-08-11 06:57Does the EfficientSAM works for segmentation without box or point prompts?
- Issue comment#1sun-yue20022025-04-02 03:59How to perform "segment everything" and "salient instance segmentation"??
- Issue#79510zsj2025-02-19 09:33About segment everything
- Issue#78NTUZZH2025-01-23 07:17Fine-tunning the original model to new tasks with few-shot adaption
- Issue comment#55NTUZZH2025-01-13 15:38how to train our dataset？thanks for your answer
- Issue comment#65fnwkqwan2024-12-10 10:16When there are multiple points as prompts (for example, more than five points), some point areas cannot be segmented.
- Issue comment#47dingshengqin2024-12-06 06:00torch.onnx.errors.UnsupportedOperatorError: Exporting the operator 'aten::tile' to ONNX opset version 17 is not supported.
- Issue comment#51dingshengqin2024-12-06 04:52SqueezeSAM
- Issue comment#15rentainhe2024-12-05 07:03grounded-efficient-sam demo support
- Issue comment#64kexul2024-12-05 03:45how to use background point
- Issue comment#77yformer2024-12-04 23:14how to ensure the iou prediction between zero and one?
- Issue comment#16yformer2024-12-04 23:03Title: Query on EfficientSAM's Adaptability for Low-Resource Environments
- Issue comment#1yformer2024-12-04 22:59How to perform "segment everything" and "salient instance segmentation"??
- Issue comment#19yformer2024-12-04 22:52Integration to segment_anything package?
- Issue comment#15yformer2024-12-04 22:47grounded-efficient-sam demo support
- Issue comment#68yformer2024-12-04 22:39pre-trained parameters
- Issue comment#76yformer2024-12-04 22:37Feature extraction of image encoder
- Issue comment#64yformer2024-12-04 22:34how to use background point
- Issue comment#69yformer2024-12-04 22:31Why is it slow to segment everything？ Is there a good solution？
- Issue comment#75yformer2024-12-04 22:30Why is it running slow and segment-anything is not giving good results?
- Issue comment#74yformer2024-12-04 22:25Will you integrate with SAM2?
- Issue comment#69CurryKd72024-09-14 04:38Why is it slow to segment everything？ Is there a good solution？
- Issue comment#69silinsi2024-09-13 12:05Why is it slow to segment everything？ Is there a good solution？
- Issue comment#69CurryKd72024-09-13 06:27Why is it slow to segment everything？ Is there a good solution？
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2,272 stars here means stars gained during the window, not the repo's star count.