Skip to content

2nd Place Solution for Low-resolution TikTok ID Recognition Competition held by ByteDance

Notifications You must be signed in to change notification settings

eshoyuan/TikTok_OCR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

af2f2e6 · Feb 20, 2024

History

21 Commits
Sep 8, 2022
Aug 24, 2022
Sep 8, 2022
Sep 8, 2022
Sep 8, 2022
Sep 8, 2022
Feb 20, 2024
Aug 24, 2022
Sep 8, 2022
Aug 22, 2022
Aug 22, 2022
Feb 20, 2024
May 10, 2023
Sep 8, 2022
Sep 8, 2022
Sep 8, 2022

Repository files navigation

TikTok OCR

This is SEU_309's Solution for Low-resolution TikTok ID Recognition Competition held by ByteDance.

Usage

  1. Install PaddlePaddle.

    You can refer to https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_en/quickstart_en.md#1-installation.

  2. Install third-party libraries.

    pip install -r requirements.txt

  3. Prepare the dataset.

    Unzip archive in ./data/. Your directory & file structure should look like this,

    Tiktok_OCR 
    │
    └───data
    │   │   train.txt
    │   │   eval.txt
    │   │
    │   └───train_set_random
    │   |   │   v0d00fg10000cb9gacjc77u3gp5qggd0_0_.jpg
    │   |   │   ...
    │   │
    │   └───test_set_random
    │       │   v0d00fg10000cb9gacjc77u3gp5qggd0_2_.jpg
    │   	│   ...
    
    
  4. Execute the shell script.

    sh run.sh

Details

More details can be found in our report (English)/(Chinese).

About

2nd Place Solution for Low-resolution TikTok ID Recognition Competition held by ByteDance

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages