TF-CRNN : A TensorFlow implementation of Convolutional Recurrent Neural Network

• Quickstart
  • Installation
  • How to train a model
  • Using a saved model for prediction
• Reference guide
  • Data handling for input function
  • Config for training
  • Model
  • Loading exported model

A TensorFlow implementation of the Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition tasks, such as scene text recognition and OCR. Original paper and code.

This implementation uses tf.estimator.Estimator to build the model and tf.data modules to handle input data.

Indices and tables

• Index
• Module Index
• Search Page