Walk-through : Getting started with Keras, using Kaggle

Walkthrough: Starting with Kegel, using Kegel

This is a short post - the real substance is in the screencast below, where I go through the code!

If you’re just starting out in the world of machine learning (and let it be real here, who isn’t?), Tooling seems to be getting better and better. Keras has been a major tool for some time and is now integrated into the TensorFlow. Good together, right? And it just so happens that it has never been easier to get started with Keras.

But wait, what exactly is Keras, and how can you use it to start building your own machine learning models? Today, I want to show you how to get started with bananas in the fastest possible way.

Canara is not only built on TensorFlow via TensorFlow.Caras, you don't have to install or configure anything if you use tools like the Kegel kernel.

Introduction to Kaggle Kernel

Find out what Keggel kernels are and how to get started. While not there ...

Playing around with Keras

All you need to do is create your Kaggle account if needed, and sign in. Then you have access as a carousel offer.

It is worth noting that Keras also exists as a standalone library, Kerasio., While the TensorFlow version has exactly the same API, and some additional features.

Let's go to my Kaggal kernel, where I will show you how to start using bananas now.

Screencast showing how to go with Keras, in Kagal!

Closing thoughts

Keras has an amazing community and many specimens, which when combined with Kagle's community, give you a perfect epic resource to get you started, the right way.

This integration with TensorFlow means you can train Keras models in the Google Cloud ML Engine. There are also ways to export and convert models between bananas and TensorFlow, so you can measure your predictions as well. If you want to know more about it, let me know in the comments, and I'll try to put a few examples!

Get started with Keras → http://bit.ly/2vTMPXt