Over a million developers have joined DZone.

Getting Started With Tensorflow on IBM Bluemix [Video]

DZone's Guide to

Getting Started With Tensorflow on IBM Bluemix [Video]

I wanted to learn Tensorflow — which, to me, looks like the most popular Deep Learning library right now. This video was very helpful.

· Big Data Zone ·
Free Resource

Hortonworks Sandbox for HDP and HDF is your chance to get started on learning, developing, testing and trying out new features. Each download comes preconfigured with interactive tutorials, sample data and developments from the Apache community.

To learn Deep Learning, I’ve taken an Udacity course that I can highly recommend. One reason I took that course was because I also liked the Udacity Machine Learning courses. Another reason was because I wanted to learn Tensorflow — which, to me, looks like the most popular Deep Learning library right now.

Below is the YouTube playlist of the course. The assignments can be run locally via Docker.

Another good starting point to learn Tensorflow is the video Tensorflow and Deep Learning — Without a Ph.D. by Martin Görner.

To run Tensorflow on IBM Bluemix, you can use Docker. Alternatively, you can use Tensorflow in notebooks on IBM Data Science Experience. Check out the hello world sample how to install Tensorflow:

#!pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.9.0-cp27-none-linux_x86_64.whl
import tensorflow as tf
# Create TensorFlow object called hello_constant
hello_constant = tf.constant('Hello World!')
with tf.Session() as sess:
    # Run the tf.constant operation in the session
    output = sess.run(hello_constant)

Hope this helps!

Hortonworks Community Connection (HCC) is an online collaboration destination for developers, DevOps, customers and partners to get answers to questions, collaborate on technical articles and share code examples from GitHub.  Join the discussion.

big data ,tensorflow ,ibm bluemix

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}