TensorFlow is one of the most popular and widely used and famous open source software libraries released in 2015 by Google to make it easier for developers to design, build, and train deep learning models. It was developed by researchers and engineers working on Google Brain Team within Google Machine Intelligence Research Organization and Deep Neural Network , but the system is general enough to be applicable in a wide variety of other domains as well.

Google’s new TensorFlow 2.0 is easy, more powerful, and scalable. There are easier APIs with better code examples and documentation. Tensorflow 2.0 comes with a lot of new features. The main problem with Tensorflow 1.x was it was not easier for debugging. So for a newbie it would be very hard to understand/debug the code where some parts are unnecessary. With TensorFlow 2.0, you can debug like you are debugging a normal python code using pdb or good old prints.

TensorFlow 2.0 will focus on simplicity and ease of use, featuring updates like:

  • Easy model building with Keras and eager execution.
  • Robust model deployment in production on any platform.
  • Powerful experimentation for research.
  • Simplifying the API by cleaning up deprecated APIs and reducing duplication.

Newest TensorFlow 2.0 have a number of components, these will be packaged together into a comprehensive platform that supports machine learning workflows from training through deployment. Let’s take a look at the new architecture of TensorFlow 2.0 using a simplified, conceptual diagram as shown below

Source :