MachineX: Welcome to TensorFlow 2.0

Reading Time: 3 minutes
This image has an empty alt attribute; its file name is 1sxlcjm7_azqb7kdtcwhhxa.png

With the release of Tensorflow 2.0 we have taken another step towards machine dominating human dysphoria. Just kidding!!, this debate is for big people like Elon Musk, Mark Juckerberg or Jack Ma. We are just happy that Tensorflow 2.0 has been released and it will make our life a lot easier as 2.0 is being improved with consideration of freedbacks from its users. As part of the release blog Tensorflow tells that “TensorFlow 2.0 provides a comprehensive ecosystem of tools for developers, enterprises, and researchers who want to push the state-of-the-art in machine learning and build scalable ML-powered applications.”

Tensorflow has invested heavily on improving the low level api. It is now allowing us to build onto the internals of TensorFlow without having to rebuild TensorFlow. As Python becomes the favourite language for machine learning, Tensorflow 2.0 brings better experience with pythonic function execution. 

This image has an empty alt attribute; its file name is y6XmeNIu3n71ub5bBlFEPRsa4yv7ySX4lleyI8YNPw8HQhegUgr9LaizMSqjL6vZnN9pI3iIuentDoP_L2u5mZCLnicqJdjAQiYNvIRtjhgxouhEdNUKk95IkVoSWnesxk5svRyY

What about coding with TensorFlow 2.0

With TensorFlow 2.0, we can easily develop our Ml application. It is giving tight integration of Keras into TensorFlow, eager execution by default and if you are an Python developer , it will makes the experience of developing applications as familiar as possible for you.

Moreover, TensorFlow’s low-level API will allows you to build onto the internals of TensorFlow without having to rebuild TensorFlow.

This image has an empty alt attribute; its file name is tenserflow2.0.png

Model deployment with TensorFlow 2.0

TensorFlow 2.0 let you to run your ML model on a variety of runtimes, it may be web, browser, or mobile as they standardized on the SavedModel file format.

You can deploy your models with TensorFlow Serving, for mobile and embedded system TensorFlow Lite , if you want to train and run it in browser or Node.js , there is TensorFlow.js.

GPU support

Kari Briski, Senior Director of Accelerated Computing Software Product Management at NVIDIA once said that : “Machine learning on NVIDIA GPUs and systems allows developers to solve problems that seemed impossible just a few years ago,”. TensorFlow 2.0 is packed with many great GPU acceleration features. Will great to see the amazing AI applications, the community will create with these updated tools.

Some other features

  • when building models in TensorFlow, access for training and validation data is paramount. Tensorflow Introduced TensorFlow Datasets, datasets containing a variety of data types such as images, text, video, and more.
  • The main API is now non-other than the Keras: The fluid layer of Keras is now integrated on top of the raw TensorFlow code make it simple and easy to use. This would help bring a lot of progress and productivity in the field of Machine Learning and AI
  • Eager Command-line : This simple command line helps us to execute operation immediately without using command.
  • Integration of tf.contrib into separate repositories.
  • Improved TPU and TPU support and distributed computation support and support for the same up to v3.
  • TensorFlow optimization for Android.
  • TensorFlow Integration for Swift and IOS based applications.
  • Domain-Specific Community Support.
  • Extra Support for Model Validation and Reuse.
  • End-to-End ML Pipelines and Products available at TensorFlow Hub.


Written by 

Shubham Goyal is a Data Scientist at Knoldus Inc. With this, he is an artificial intelligence researcher, interested in doing research on different domain problems and a regular contributor to society through blogs and webinars in machine learning and artificial intelligence. He had also written a few research papers on machine learning. Moreover, a conference speaker and an official author at Towards Data Science.