¿Cómo entrenar OCR con Keras, TensorFlow y aprendizaje profundo?

How to train OCR with Keras, TensorFlow, and deep learning?

In this section, we are going to train our OCR model using Keras, TensorFlow, and a PyImageSearch implementation of the very popular and successful deep learning architecture, ResNet. Remember to save your model for next week, when we will implement a custom solution for handwriting recognition.

In this tutorial, you will learn how to perform OCR handwriting recognition using OpenCV, Keras, and TensorFlow. This post is Part 2 in our two-part series on Optical Character Recognition with Keras and TensorFlow: Part 2: Basic handwriting recognition with Keras and TensorFlow (today’s post)

The first part of the post shows how to easily create a Keras model that is using TensorFlow. The next part covers how to train the model and convert it to TensorFlow Lite. The last part covers building a simple Android app that runs the model. It is easy to find materials on how to create only a model or only a mobile app.

With there now being more phones than people this is an excellent strategy to get your neural network literally into the hands of those who need it. One of those most popular libraries for running neural networks on Android phones is Tensorflow Lite. To use it you will need to convert that Keras .h5 file to a Tensorflow .tflite file.

Part 2: Basic handwriting recognition with Keras and TensorFlow (next week’s post) For now, we’ll primarily be focusing on how to train a custom Keras/TensorFlow model to recognize alphanumeric characters (i.e., the digits 0-9 and the letters A-Z ).

It’s an adaptation of the Convolutional Neural Network that we trained to demonstrate how sparse categorical crossentropy loss works. Today’s one works for TensorFlow 2.0 and the integrated version of Keras; hence, I’d advise to use this variant instead of the traditional keras package.

The standard MNIST dataset is built into popular deep learning frameworks, including Keras, TensorFlow, PyTorch, etc. A sample of the MNIST 0-9 dataset can be seen in Figure 1 (left ). The MNIST dataset will allow us to recognize the digits 0-9. Each of these digits is contained in a 28 x 28 grayscale image.