Skip to content

SwinTransformer/Video-Swin-Transformer

View on GitHub ↗Related repositories →

[CVPR, 2022] : This is an official implementation for "Video Swin Transformers".

active 2023-08-152026-05-09 (UTC)

Complete coverage26,750 / 26,750 hourly files (100%) · 2 absent upstream2023-08-152026-09-02 (UTC)
Events
509
Pushes
0
Pull requests
0
Issues
12
Stars
437
Forks
38

Activity over time

Daily event counts in the loaded window

Line chart, 999 days from 2023-08-15 to 2026-05-09. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 12 total, peak 2 in a day. Comments: 22 total, peak 3 in a day. Stars: 437 total, peak 4 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 comment#21DAVID-Hown2025-05-31 08:58
    KeyError: "Recognizer3D: 'SwinTransformer3D is not in the models registry'"
  • Issue comment#84EgorT782025-04-15 07:20
    Missing keys in source state_dict: backbone.patch_embed.proj.weight, backbone.patch_embed.proj.bias, and so on.
  • Issue comment#5Raion-Shin2025-04-07 06:38
    Performance Reproducing of Swin-S
  • Issue comment#64Raion-Shin2025-04-07 03:29
    Results cannot be reproduced through training.
  • Issue#98Raion-Shin2025-04-07 03:27
    Cannot reproduce the pretraining experiment on K400 dataset
  • Issue#97Nagur-Basha12025-02-12 11:50
    FileNotFoundError: [Errno 2] No such file or directory: './models/table1/vatex/best-checkpoint/training_args.bin'
  • Issue comment#94asatpathy3142024-09-25 15:26
    Failed to run demo.
  • Issue comment#72pp-jia2024-08-22 02:48
    Error: av_read_frame failed with 1094995529
  • Issue#96sunqing-code2024-08-09 02:57
    Is anyone running successfully in a windows environment?
  • Issue comment#90May23332024-08-01 14:21
    Model weights for Swin-L
  • Issue comment#95pbhfcycssjlmm2024-07-01 10:52
    Question about Table 5. Ablation study on the temporal dimension of 3D tokens and temporal window size with Swin-T on K400 and SSv2
  • Issue#95pbhfcycssjlmm2024-07-01 10:21
    Question about Table 5. Ablation study on the temporal dimension of 3D tokens and temporal window size with Swin-T on K400 and SSv2
  • Issue comment#89innat-asj2024-05-27 13:03
    Steps to convert mmaction's video-swin-transformer to ONNX successfully
  • Issue comment#89adeljalalyousif2024-05-22 06:52
    Steps to convert mmaction's video-swin-transformer to ONNX successfully
  • Issue comment#94Tommy-shelby-github2024-04-02 07:13
    Failed to run demo.
  • Issue comment#89innat-asj2024-03-29 17:45
    Steps to convert mmaction's video-swin-transformer to ONNX successfully
  • Issue comment#89adeljalalyousif2024-03-25 14:07
    Steps to convert mmaction's video-swin-transformer to ONNX successfully
  • Issue#94fengjingchehu2024-03-15 07:58
    Failed to run demo.
  • Issue comment#93Uljibuh2024-02-23 12:14
    how to use pretrained model in simplest way?
  • Issue#93Uljibuh2024-02-23 11:54
    how to use pretrained model in simplest way?
  • Issue#92wanghao142024-02-23 08:45
    swin_transformer.py compute_mask doesn't have expected torch dtype
  • Issue#91bio-mlhui2024-01-10 08:06
    inconsistent patch size between swin_tiny.py and pretrained model
  • Issue#91bio-mlhui2024-01-10 05:31
    inconsistent patch size between swin_tiny.py and pretrained model
  • Issue#90abdullahjamal2023-12-26 12:49
    Model weights for Swin-L
  • Issue comment#52gigasurgeon2023-12-09 23:56
    ERROR: pytorch2onnx.py unpack error

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 437 stars here means stars gained during the window, not the repo's star count.