Skip to content

Latest commit

 

History

History
14 lines (11 loc) · 544 Bytes

README.md

File metadata and controls

14 lines (11 loc) · 544 Bytes

Tensorflow 2 Captcha Reader

Download dataset here

Data preprocessing

  • Training set: 100000 labeled captchas.
  • Validation set: 20000 labeled captchas.
  • Testing set: 20000 unlabeled captchas.
  • All captchas are resized to 50 x 100.

Encoder

Convolutional Neural Network encodes captcha images into simpler representation.

Decoder

Output from attention layer is fed into GRU cells followed by FC layers to convert encoded captchas into strings.