This is a PyToch re-implementation of "Real-time Scene Text Detection with Differentiable Binarization".(This paper.) Most part of the code is inherited from DB repo.
The original projection is too heavy and not easy for us to use it. So this repo is to simplify it
- Release code
- Trained models
- Document for Installation
- Document for testing and training
- Evaluation
- Demo script
- re-organize and clean the parameters