Skip to content

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

active 2023-08-152026-06-22 (UTC)

Complete coverage26,745 / 26,745 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
1.2K
Pushes
30
Pull requests
4
Issues
111
Stars
855
Forks
60

Activity over time

Daily event counts in the loaded window

Line chart, 1043 days from 2023-08-15 to 2026-06-22. Pushes: 30 total, peak 8 in a day. Pull requests: 4 total, peak 2 in a day. Issues: 111 total, peak 7 in a day. Comments: 116 total, peak 13 in a day. Stars: 855 total, peak 19 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

Recent activity

Latest issues, pull requests and releases

  • Issue#92croviatrust2026-03-29 07:05
    📋 Documentation Enhancement Suggestion
  • Issue#89xryami2025-11-08 11:59
    关于预训练参数的问题。
  • Issue#87hilaryliang2025-10-31 02:08
    export onnx
  • Issue comment#80puyiwen2025-05-07 06:46
    Why no bn after 1x1 dw-conv?
  • Issue comment#80Journey73312025-05-05 19:17
    Why no bn after 1x1 dw-conv?
  • Issue#80Journey73312025-05-05 19:17
    Why no bn after 1x1 dw-conv?
  • Issue comment#49qjjshsh2025-04-26 05:50
    Does the repvit classification experiment only have training sets and test sets, no val sets?
  • Issue#83chairman-lu2025-04-09 08:34
    关于使用xcode测试模型在iphone上推理速度的问题
  • Issue comment#55Amiaooo2025-01-14 07:11
    working environment
  • Issue comment#39seermer2024-12-26 20:59
    Question about "Convert a training-time RepViT into the inference-time structure" with replace_batchnorm.
  • Issue comment#59wydxry2024-12-25 14:23
    How to detect a single image
  • Issue comment#39dlml2024-12-25 10:37
    Question about "Convert a training-time RepViT into the inference-time structure" with replace_batchnorm.
  • Issue#82dlml2024-12-25 10:35
    When using "repalce_batchnorm", the result of converting to onnx format is inconsistent
  • Issue#81Phoenix82152024-12-05 11:17
    🚀Contribution: TensorRT Inference Implementation for RepViT
  • Issue comment#78Phoenix82152024-12-05 11:09
    模型可以转换为tensorrt,进行gpu推理么
  • Issue#80Journey73312024-11-25 19:40
    Why no bn after 1x1 dw-conv?
  • Issue#7822wei222024-11-04 14:23
    模型可以转换为tensorrt,进行gpu推理么
  • Issue comment#56Epiee2024-10-30 08:43
    typeError: repvit_m0_9() got an unexpected keyword argument 'pretrained_cfg'
  • Issue#7722wei222024-10-27 06:42
    有延时在RepViT-M1.1-1.5之期的模型权重和结构么?
  • Issue comment#54Epiee2024-10-25 03:12
    MMCV version
  • Issue#76HanGuangXin2024-10-16 09:04
    could not find Figure 4.(d) in repvit.py
  • Issue#75virtuoso1082024-10-11 02:25
    training on Imagenet data is not working
  • Issue#7418222why2024-10-10 01:23
    Does repvit support transfer learning?
  • Issue#73hyz-xmaster2024-08-23 07:53
    Why not perform layer fusion in the downstream models?
  • Issue comment#56Kaze8162024-08-23 06:16
    typeError: repvit_m0_9() got an unexpected keyword argument 'pretrained_cfg'

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 855 stars here means stars gained during the window, not the repo's star count.