Image recognition in Python with TensorFlow and Keras

Click for: original source

One of the most common utilizations of TensorFlow and Keras is the recognition/classification of images. If you want to learn how to use Keras to classify or recognize images, this article will teach you how.

TensorFlow is an open source library created for Python by the Google Brain team. TensorFlow compiles many different algorithms and models together, enabling the user to implement deep neural networks for use in tasks like image recognition / classification and natural language processing.

In terms of Keras, it is a high-level API (application programming interface) that can use TensorFlow’s functions underneath (as well as other ML libraries like Theano). Keras was designed with user-friendliness and modularity as its guiding principles.

In the article you will find:

  • Image Recognition (Classification)
  • Feature Extraction
  • How Neural Networks Learn to Recognize Images
  • The Machine Learning Workflow
  • Image Recognition with a CNN

Small example with the code is also provided so you can create and implement your first image recognition network in Keras. You can play around with the model and see how changing its parameters affects its performance. Nice one!

[Read More]

Tags python big-data data-science