CRNN model in Tensorflow using Estimators
Implementation of the Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition tasks, such as scene text recognition and OCR. Original paper http://arxiv.org/abs/1507.05717 and code https://github.com/bgshih/crnn
This version uses the tf.estimator.Estimator
to build the model and tf.data
module to handle input data.
tf_crnn
make use of tensorflow-gpu
package (so CUDA and cuDNN are needed).
You can install it using the environment.yml
file provided and use it within an environment, or install and run it with Docker.
See the docs for the installation procedures and how to use it.