What's new in Tensorflow 2?

-
I will highlight some of the key changes with the latest version of Tensorflow 2.0 compared to earlier versions:
  • Now Keras users who use multi-backend Keras with the TensorFlow backend are needed switch to tf.keras in TensorFlow 2.0. As it’s going to be better maintained.
  • By default Tensorflow 2.0 will be having Eager execution that evaluates operations immediately, without building graphs. You can obviously switch to the style of building graphs, as it was in Tensorflow earlier as well
  • It is now having a full lower-level API, which allows it to use for having custom training loops(which is needed by researchers a lot)
  • With tf.GradientTape you can now do automatic differentiation
  • One of the other features of Tensorflow is experimental support for mixed precision on GPUs and Cloud TPUs
  • A clear consistent, intuitive, syntax across various APIs
  • Tensorflow 2.1 bought support for TPU training in a simple and intuitive way which makes it’s a favourite for Kagglers like me
  • Internals operations are now accessible by tf.raw_ops
  • Inheritable interfaces for variables, checkpoints, layers

Comments

Post a Comment

Popular posts from this blog

Skillset Every Data Scientist Should Have!

-
Image
  Non-Technical Skills These skills won’t require as much technical training or formal certification, but they’re foundational to the rigorous application of data science to business problems. Even the most technically skilled data scientist needs to have the following soft skills to thrive today.
Read more

Advice to Newbies in Data Science.

-
Image
  1. Pick the brain of an expert. There are myriads of ways to learn data science. You can read articles, watch videos, enroll in onli n e courses, turn up at meetups, etc. But one thing that you cannot “learn” is the  experience . That you have to gain throughout years of working in the field. There is much to learn from Data science experts, their experience in managing end-to-end machine learning and deep learning projects, their philosophy when constructing a data science team from scratch,
Read more