[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
Jupyter Notebook · active 2025-04-29 → 2026-04-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 354 days from 2025-04-29 to 2026-04-17. Pushes: 3 total, peak 2 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 11 total, peak 2 in a day. Comments: 14 total, peak 4 in a day. Stars: 448 total, peak 72 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 |
|---|---|---|---|---|
| rozeappletree | 4 | 0 | 0 | 3 |
| chongzhou96 | 3 | 3 | 0 | 0 |
| NielsRogge | 2 | 0 | 0 | 1 |
| annamalai-19 | 2 | 0 | 0 | 1 |
| chenweisomebody126 | 1 | 0 | 0 | 1 |
| cl3m3nt | 1 | 0 | 0 | 0 |
| fahadskhan | 1 | 0 | 0 | 1 |
| meta-cla[bot] | 1 | 0 | 1 | 0 |
| Lightning-Lion | 1 | 0 | 0 | 1 |
| mikel-brostrom | 1 | 0 | 0 | 0 |
| yinnengzhong | 1 | 0 | 0 | 1 |
| georgebaknis | 1 | 0 | 0 | 0 |
| sourav-bz | 1 | 0 | 0 | 1 |
| tyretitans25 | 1 | 0 | 0 | 1 |
| ksk2023 | 1 | 0 | 0 | 0 |
| huucuong1503 | 1 | 0 | 0 | 0 |
| DjKesu | 1 | 0 | 0 | 0 |
| BaophanN | 1 | 0 | 0 | 1 |
| zsz00 | 1 | 0 | 0 | 0 |
| ogencoglu | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#14chenweisomebody1262026-04-17 04:04Adding CoreML Export Support - Looking for Feedback
- Issue comment#14tyretitans252026-02-01 03:47Adding CoreML Export Support - Looking for Feedback
- Issue comment#11sourav-bz2025-12-21 21:17Run in Streaming Mode
- Issue comment#14yinnengzhong2025-12-12 06:51Adding CoreML Export Support - Looking for Feedback
- Pull request#22meta-cla[bot]2025-12-06 18:00
- Issue#21cl3m3nt2025-11-22 14:25coreML export config path and validate option
- Issue comment#20rozeappletree2025-11-17 23:24[Gradio] `ImportError: cannot import name 'HfFolder' `
- Issue comment#10Lexmark-chad2025-11-17 15:22list index out of range
- Issue comment#20rozeappletree2025-11-17 00:06[Gradio] `ImportError: cannot import name 'HfFolder' `
- Issue comment#20rozeappletree2025-11-17 00:02[Gradio] `ImportError: cannot import name 'HfFolder' `
- Issue#20rozeappletree2025-11-16 23:56[Gradio] `ImportError: cannot import name 'HfFolder' `
- Issue comment#14Lightning-Lion2025-11-09 03:59Adding CoreML Export Support - Looking for Feedback
- Issue#17ksk20232025-10-01 11:48Why does the spatial perceiver need to be repeated 2 times?
- Issue comment#15annamalai-192025-08-28 07:29View size not compatible with input tensors - Multiple object detection
- Issue comment#15dilwolf2025-08-27 02:32View size not compatible with input tensors - Multiple object detection
- Issue comment#2fahadskhan2025-08-21 19:03CoreML | Compiled representation
- Issue#15annamalai-192025-08-06 07:45View size not compatible with input tensors - Multiple object detection
- Issue#14DjKesu2025-07-27 01:27Adding CoreML Export Support - Looking for Feedback
- Issue#12georgebaknis2025-07-11 22:44Inference time spikes
- Issue#9mikel-brostrom2025-06-18 17:15Bug when objects with different `frame_idx` are added using `predictor.add_new_points_or_box`
- Issue#8zsz002025-06-18 07:24Hope to open-source the training code
- Issue#7ogencoglu2025-06-17 21:01ONNX export
- Issue#5huucuong15032025-05-18 13:31Tensorrt version ?
- Issue comment#3BaophanN2025-05-16 02:25Request for .tflite Model Export for EdgeTAM
- Issue comment#4NielsRogge2025-05-03 08:08Improve HF integration
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 448 stars here means stars gained during the window, not the repo's star count.