Skip to content

facebookresearch/perception_models

View on GitHub ↗Related repositories →

[MCHIGM's fork on the repo \\ State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

Jupyter Notebook · active 2025-04-172026-05-30 (UTC)

Complete coverage26,643 / 26,643 hourly files (100%) · 2 absent upstream2023-08-152026-08-29 (UTC)
Events
2K
Pushes
101
Pull requests
52
Issues
83
Stars
1.5K
Forks
92

Activity over time

Daily event counts in the loaded window

Line chart, 409 days from 2025-04-17 to 2026-05-30. Pushes: 101 total, peak 22 in a day. Pull requests: 52 total, peak 14 in a day. Issues: 83 total, peak 6 in a day. Comments: 140 total, peak 12 in a day. Stars: 1,542 total, peak 158 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

ContributorContributionsPushesPRsComments
dbolya5422720
shuminghu41111117
berniebear4119512
mmaaz603822312
janghyuncho191015
SeaOtocinclus160115
andreamad89521
PeizeSun7601
Kamichanw6004
hlh20232146003
VimukthiRandika19975004
cheongalc5004
Baiqi-Li5002
CoinCheung4002
JacksonHuang1274002
ssamt4002
rakomar4003
chaoleitan3001
dependabot[bot]3030
irfanrah3001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#89meta-cla[bot]2026-04-28 22:17
    fix ALL_TASKS string in training example
  • Pull request#126dependabot[bot]2026-04-13 21:42
  • Pull request#126dependabot[bot]2026-04-13 21:42
  • Issue comment#112saicoco2026-02-27 07:35
    mode weight mismatch
  • Issue#116chandrabhuma2026-01-25 11:27
    OOM issue in Colab with L4
  • Pull request#115dependabot[bot]2026-01-22 20:53
  • Issue comment#112George0828Zhang2026-01-12 02:18
    mode weight mismatch
  • Issue#112Limingxing002025-12-30 11:28
    mode weight mismatch
  • Issue#108Preet-Sojitra2025-12-20 02:21
    Query regarding Embedding Normalization and Similarity Score Range for PE-AV model
  • Pull request#106lematt19912025-12-16 15:57
  • Issue comment#105meta-cla[bot]2025-12-05 17:00
    fix(transforms): Turn image transform to rgb from lambda into top-level function
  • Pull request#105PeterOttoMoeller2025-12-05 17:00
  • Pull request#105PeterOttoMoeller2025-12-05 17:00
  • Issue#103dbolya2025-11-25 05:00
    How to use PE-Spatial-L14-448 model?
  • Issue comment#102meta-cla[bot]2025-11-20 22:12
    lower python req to 3.9
  • Issue comment#76futurev2025-10-07 05:44
    Distilled PE spatial model's performance on coco
  • Issue#95MSiam2025-09-22 07:50
    Region Captioning Eval on PLM-VideoBench
  • Pull request#94lematt19912025-09-16 15:34
  • Pull request#92andreamad82025-09-05 02:53
  • Pull request#91xwen992025-09-04 04:39
  • Pull request#91xwen992025-09-04 04:38
  • Pull request#90andreamad82025-09-02 20:38
  • Pull request#90SeaOtocinclus2025-09-02 20:30
  • Issue#88yuchenlichuck2025-08-23 00:09
    Anyone try to implement perception on segmentation tasks?
  • Issue#87JihwanEom2025-08-21 08:25
    Request for Additional Perception Encoder Variants (H and g)

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,542 stars here means stars gained during the window, not the repo's star count.