herraiz.org | Blog

Main | Blog | Research papers | PhD thesis | GnuPG (PGP)

 Subscribe to this blog in a reader

First steps in Deep Learning (workshop @ KSchool)

Although I am not the highest fan of notebooks for data science projects, it is undoubtedly a great tool for purposes like teaching, or delivering a talk.

In fact, yesterday I delivered a small workshop at KSchool on making your first baby steps on deep learning, using Google Colab, the Python notebooks tool of Google.

Google Colab works like Jupyter, except that several people can work on the same notebook at once, à-la Google Docs. But it comes with even nicer things: you can use a K80 Tesla GPU with Tensorflow and Keras, to have lightning-fast training even when dealing with large datasets. For free, just with your Google account.

In the workshop yesterday, we used a small dataset, the famous MNIST handwritten digits set. But I have tried working with much larger images in Colab (loading them from Google Drive!), and it works like a charm.

If you are curious about Deep Learning, or about using a GPU entirely for free, have a look at the Keras notebook I prepared for the workshop yesterday:

If you don't have a Google account, grab the notebook from this open link, you can downwload it anonymously and run it locally using Jupyter (with Python 3 and Keras).

You can download it and use it locally with Jupyter, or copy it to your Google Drive to run it in your environment at Google Colab.

The notebook includes detailed explanations of every step we did at the workshop, and links to external materials and videos, just in case you want to extend on some of the details.

Written on Feb 09 2018 | Tags: #datascience, #deep learning
blog comments powered by Disqus