Tensorflow-Problem-Sheet

Module: Emerging Technologies / 4th Year
Lecturer: Dr Ian McLoughlin
Problem set: Tensorflow

These problems relate to the Python package Tensorflow. We will again use the famous iris data set. Download Iris data set here

Need Components:

• Tensorflow
• Keras
• Jupyter
• Numpy
• Iris data set

Installing Tensorflow

In order to install Tensorflow, your system must contain one of the following Python versions:

• Python 2.7
• Python 3.X

Use pip to install Tensorflow:

• $ pip install tensorflow
• $ pip3 install tensorflow

Validate your installation:

Start a terminal(for mac, windows enter your cmd or cmder). If you installed through Anaconda, activate your Anaconda environment. Invoke python from your terminal as follows:

$ python

Enter the following short program inside the python interactive shell:

>>> import tensorflow as tf
>>> hello = tf.constant('Hello, TensorFlow!')
>>> sess = tf.Session()
>>> print(sess.run(hello))

If the system outputs the following, then you are ready to begin writing TensorFlow programs:

Hello, TensorFlow!

Installing Keras

Before installing Keras, please install one of its backend engines: TensorFlow, Theano, or CNTK. We recommend the TensorFlow backend.

Install Keras from PyPI (recommended):

• sudo pip install keras

If you are using a virtualenv, you may want to avoid using sudo:

• pip install keras

If you want using a Anaconda Navigator:

1. Open Anaonda Navigator
2. Click Environments
3. Change installed to All
4. Enter keras in the search package
5. Select keras and click Apply