https://github.com/sun1638650145/crnn

An AutoML for CRNN, you can perform captcha recognition with just a few lines of code.
https://github.com/sun1638650145/crnn

captcha-solver crnn ctc keras ocr pipeline tensorflow

Last synced: about 6 hours ago
JSON representation

An AutoML for CRNN, you can perform captcha recognition with just a few lines of code.

• Host: GitHub
• URL: https://github.com/sun1638650145/crnn
• Owner: sun1638650145
• License: apache-2.0
• Created: 2020-09-18T02:35:31.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2023-01-03T03:17:09.000Z (almost 2 years ago)
• Last Synced: 2023-03-06T19:09:54.458Z (over 1 year ago)
• Topics: captcha-solver, crnn, ctc, keras, ocr, pipeline, tensorflow
• Language: Python
• Homepage:
• Size: 50.8 KB
• Stars: 14
• Watchers: 2
• Forks: 2
• Open Issues: 3
• Metadata Files:
  • Readme: README-zh.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# CRNN

一个关于CRNN的AutoML, 你可以使用三四行代码就可以进行验证码的识别, 阅读其他语言版: [English](https://github.com/sun1638650145/CRNN/blob/master/README.md)

## 流水线

这是一个非常简短的例子(入门推荐).

```python

from CRNN import CRNNPipeline

pipeline = CRNNPipeline('./captcha_images_v2/')

pipeline.run()

```

例子中使用的数据集在这里[点击](https://github.com/AakashKumarNain/CaptchaCracker/raw/master/captcha_images_v2.zip).

## 自定义

如果你希望更高的准确率和更高的效率, 可以使用自定义模式(针对有经验的开发者).

1. 你可以使用`model API`和`tools API`构建你自己的模型.

2. 欢迎和作者联系/交流.