视觉检测模型
Jupyter Notebook · active 2025-08-14 → 2026-08-10 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 362 days from 2025-08-14 to 2026-08-10. Pushes: 30 total, peak 3 in a day. Pull requests: 56 total, peak 6 in a day. Issues: 186 total, peak 15 in a day. Comments: 358 total, peak 25 in a day. Stars: 5,273 total, peak 1,275 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 |
|---|---|---|---|---|
| patricklabatut | 86 | 12 | 16 | 32 |
| cijose | 65 | 11 | 10 | 23 |
| MichaelRamamonjisoa | 21 | 2 | 2 | 7 |
| baldassarreFe | 21 | 0 | 1 | 17 |
| JohnMBrandt | 17 | 0 | 0 | 17 |
| meta-cla[bot] | 17 | 0 | 3 | 14 |
| mseitzer | 12 | 0 | 1 | 6 |
| se-yi | 12 | 3 | 1 | 6 |
| aselimc | 11 | 0 | 2 | 8 |
| zhenghuanghe | 6 | 0 | 0 | 5 |
| oopsRookie | 5 | 0 | 0 | 1 |
| sehunfromdaegu | 5 | 0 | 0 | 4 |
| sovit-123 | 5 | 0 | 0 | 2 |
| NanCheng2001 | 5 | 0 | 0 | 2 |
| goutamyg | 5 | 0 | 0 | 2 |
| Dhia-naouali | 4 | 0 | 3 | 1 |
| litengfeigithub | 4 | 0 | 0 | 2 |
| CoinCheung | 4 | 0 | 0 | 2 |
| qasfb | 4 | 0 | 0 | 4 |
| librety123z | 4 | 0 | 0 | 4 |
Recent activity
Latest issues, pull requests and releases
- Pull request#354littleshy134232026-08-03 08:10
- Pull request#342meta-cla[bot]2026-05-24 23:41
- Issue comment#308felix-br252026-05-04 21:46Lightweight Semantic Segmentation
- Issue comment#336se-yi2026-04-23 16:01Request for access to facebook/dinov3-vit7b16-pretrain-lvd1689m
- Issue#336cc84182026-04-07 12:51Request for access to facebook/dinov3-vit7b16-pretrain-lvd1689m
- Pull request#334jetolan-fb2026-03-27 00:02
- Issue comment#328KBodolai2026-03-12 10:28Download link for CHMv2 weights not working
- Pull request#329se-yi2026-03-11 17:20
- Pull request#327meta-cla[bot]2026-03-10 23:03
- Issue comment#258NyquistBodeTu2026-03-01 11:13About the pretrained weight of foreground classification network in fg_classiffier.pkl
- Issue#319ayhmdalila2026-02-25 17:08[ACTION NEEDED] Make DinoV3 available for users in Syria
- Issue comment#244aalekseev12026-02-19 10:20RuntimeError: Error(s) in loading state_dict for DinoVisionTransformer
- Issue comment#208MichaelRamamonjisoa2026-02-11 23:04Request for Code Release: 3D Correspondence Estimation (Section 6.1.3)
- Issue comment#309Elijah-Yi2026-02-11 06:14pretrain on imagenet，The training results are inconsistent with the repo results
- Issue#311eshasadia2026-02-06 13:28finetuning on custom dataset
- Issue comment#23Mercurydust122026-02-03 08:50How to Fine-Tune DINOv3 on Custom Dataset with Self-Supervised Learning Locally
- Issue comment#232CZ-Wu2026-02-02 07:53Compatibility of Lighter Backbones with ADE20k Segmentation Head (Embedding Size Mismatch)
- Issue comment#310se-yi2026-01-30 14:13Replicating geobench results
- Issue#308ovunctuzel-bc2026-01-26 22:06Lightweight Semantic Segmentation
- Issue comment#298cijose2026-01-22 09:15Step-wise loss descent correlates with do_test frequency; removing do_test leads to loss stagnation
- Issue comment#133LeBron-Jian2026-01-21 08:52How to do few-shot detection based on dinov3
- Issue#305YWliu0401202026-01-19 03:21how to get high-resolution feature?
- Issue#177patricklabatut2026-01-16 13:30Missing segmentation head training code
- Issue comment#8patricklabatut2026-01-16 13:12Download model error
- Issue#301patricklabatut2026-01-16 13:10Do you have any plans to release a smaller distillation model?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 5,273 stars here means stars gained during the window, not the repo's star count.