Using SAM3 for forest images
Python · active 2025-11-19 → 2026-07-31 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 255 days from 2025-11-19 to 2026-07-31. Pushes: 28 total, peak 4 in a day. Pull requests: 50 total, peak 6 in a day. Issues: 123 total, peak 11 in a day. Comments: 294 total, peak 15 in a day. Stars: 3,167 total, peak 578 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 |
|---|---|---|---|---|
| meta-cla[bot] | 50 | 0 | 14 | 36 |
| meta-codesync[bot] | 26 | 24 | 0 | 2 |
| heyoeyo | 13 | 0 | 0 | 13 |
| alcinos | 12 | 0 | 0 | 6 |
| BahMoh | 8 | 0 | 0 | 6 |
| zeyadmahmoudd | 7 | 0 | 0 | 6 |
| yhy258 | 6 | 0 | 0 | 6 |
| quangkmhd | 6 | 0 | 0 | 3 |
| Joeycho | 6 | 0 | 1 | 4 |
| tqwei05 | 6 | 0 | 0 | 6 |
| keejkrej | 5 | 0 | 0 | 5 |
| provos | 5 | 0 | 2 | 3 |
| O-J1 | 5 | 0 | 0 | 4 |
| rishi1134 | 4 | 0 | 0 | 4 |
| JuiceCoffe | 4 | 0 | 0 | 1 |
| jlee-detect | 4 | 0 | 0 | 2 |
| ibrahere123 | 4 | 0 | 0 | 4 |
| JasonShen-SH | 4 | 0 | 0 | 3 |
| mattiagaggi | 4 | 0 | 0 | 4 |
| aniket-professional2025 | 4 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Pull request#565arpitjain0992026-05-31 01:21
- Issue comment#216muhammad-fiaz2026-05-16 06:00numpy 2 support?
- Issue comment#403muhammad-fiaz2026-05-16 05:52Migrate to NumPy 2.x.x and raise minimum Python version to 3.10
- Issue comment#299OrangeSodahub2026-05-15 05:36Segmentation Mask Scores
- Pull request#547haleyaaron2026-05-12 21:47
- Issue comment#528Howevercreat2026-04-30 03:14Abnormal floating masks when using SAM 3.1 for MOT, leading to oversized bounding boxes
- Issue#534lenn-arts2026-04-25 23:40SAM3.1. size assert error during compile
- Pull request#533amier27752026-04-25 07:39
- Issue#531amier27752026-04-24 05:04recondition_masklets` encoded memory is overwritten by `_tracker_update_memories
- Issue comment#353jaydeepradeJD2026-04-23 20:07build_sam3_image_model() doesn't work; sam3 always "found 0 objects"
- Issue comment#314amirkhalidkadi2026-04-23 12:24Fine-tuning tutorial for image segmentation & video segmentation
- Issue comment#179heyoeyo2026-04-20 13:14No module named 'triton' on Mac
- Issue comment#476heyoeyo2026-04-18 12:07Relationship of GPU Memory and number of Classes & category_chunk_size
- Issue comment#476abhiagwl42622026-04-18 01:33Relationship of GPU Memory and number of Classes & category_chunk_size
- Issue comment#520patri9ck2026-04-13 10:51Running SAM 3 on ROCm
- Issue comment#519meta-cla[bot]2026-04-13 04:16docs: clarify predictor request flow and box formats
- Issue comment#507manuelcristianceferinoorue2026-04-12 05:57RuntimeError: mat1 and mat2 must have the same dtype, but got BFloat16 and Float during image inference
- Pull request#518Joeycho2026-04-10 16:18
- Issue comment#511Xpangz2026-04-09 06:22sam3.1: CUDA out of memory
- Issue#514zhaohengyin2026-04-09 00:47Restore Original SAM3 Huggingface Space
- Issue comment#511fschvart2026-04-07 09:45sam3.1: CUDA out of memory
- Issue comment#511karlygach481-rgb2026-04-05 13:25sam3.1: CUDA out of memory
- Issue#511Xpangz2026-04-03 08:05sam3.1: CUDA out of memory
- Issue comment#507Wenju-Huang2026-04-03 03:23RuntimeError: mat1 and mat2 must have the same dtype, but got BFloat16 and Float during image inference
- Issue comment#509GeoLuchenchen2026-04-02 13:44Questions about addmm_act function.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3,167 stars here means stars gained during the window, not the repo's star count.