Skip to content

Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)

active 2024-01-262026-05-29 (UTC)

Partial coverage17,636 / 22,645 hourly files (78%) · 2 absent upstream · 5,008 failed, retryable2024-01-112026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
208
Pushes
10
Pull requests
4
Issues
17
Stars
119
Forks
25

Activity over time

Daily event counts in the loaded window

Line chart, 855 days from 2024-01-26 to 2026-05-29. Pushes: 10 total, peak 8 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 17 total, peak 2 in a day. Comments: 31 total, peak 3 in a day. Stars: 119 total, peak 2 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#164sh1man9992025-11-24 13:03
    how to export model to dynamic batch size
  • Issue#163Tryefold2025-08-16 03:45
    China can't use zhe pretrained model!!
  • Issue comment#159owmo-20002025-05-10 11:31
    Can't recognize Chinese characters at all?
  • Issue comment#159owmo-20002025-05-10 11:30
    Can't recognize Chinese characters at all?
  • Issue comment#155LZeroCode2025-03-19 05:10
    After converting the PyTorch model to ONNX with dynamic batch size, if the input image quality is low, the eos_id cannot be retrieved.
  • Issue comment#162tommy-aiteam2025-03-09 10:37
    The inference results using ONNX differ when loading images with cv2 and PIL.Image
  • Issue#162TruongNoDame2025-03-09 10:29
    The inference results using ONNX differ when loading images with cv2 and PIL.Image
  • Issue comment#112baudm2025-03-02 02:38
    Retrieving character segmentation results
  • Issue comment#112qiubinyang2025-03-01 22:02
    Retrieving character segmentation results
  • Issue comment#159AlanFranklin2582025-01-15 01:13
    Can't recognize Chinese characters at all?
  • Issue#159AlanFranklin2582025-01-10 02:56
    Can't recognize Chinese characters at all?
  • Pull request#34baudm2025-01-04 05:49
  • Issue comment#9Tawheed-tariq2025-01-02 12:43
    Recommendation for training on new language ?
  • Pull request#158cgrx2024-12-26 12:11
  • Issue#157ir27182024-11-30 21:01
    Script for the dataset setup
  • Issue#156fuzheng12092024-11-17 06:31
    stops at Validation sanity check
  • Issue comment#108GIN-zhao2024-10-26 14:37
    ONNX and Torch inference outputs are not the same
  • Issue comment#134GIN-zhao2024-10-26 13:15
    ONNX inference issue
  • Issue#151ninadchobe2024-10-13 10:02
    How to test on custom dataset
  • Issue comment#97baudm2024-09-07 08:54
    My val_acc is 99+ but my testing accuracy is around 40%. I do not understand what I am doing wrong.
  • Issue comment#97ceyxasm2024-09-07 07:51
    My val_acc is 99+ but my testing accuracy is around 40%. I do not understand what I am doing wrong.
  • Issue comment#97rewolfdliw2024-09-07 07:14
    My val_acc is 99+ but my testing accuracy is around 40%. I do not understand what I am doing wrong.
  • Issue#149rewolfdliw2024-09-02 19:31
    Multi GPU training issue
  • Issue#147preethamp01972024-08-16 04:57
    Finetune on a trained model
  • Issue#146AnanasPizzaMigliore2024-08-08 21:20
    how to convert to torchscript using script method. using trace method cause the model cannot handle the dynamic input.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 119 stars here means stars gained during the window, not the repo's star count.