You are on page 1of 3

Note:

The Deep Learning hands on session will be done using Python 3

Step 1:

Download and install Anaconda (Windows). While installing for windows leave it to
settings to defaults

https://repo.continuum.io/archive/Anaconda3-4.2.0-Windows-x86_64.exe

Download and install Anaconda (Ubuntu/Linux). While installing it will ask whether
to add path, please type yes

https://repo.continuum.io/archive/Anaconda3-4.2.0-Linux-x86_64.sh

#If you miss to add the environment variable during instalation on


Linux/Ubuntu. Please enter the below command

#Add the environment variable to make anaconda work everytime

export PATH=~/anaconda3/bin:$PATH

Download 64 bit python 3.5 version for windows/Ubuntu based on your OS.

Step 2:

Go to start and open Anaconda Promt and do the following

#To check the version


conda -V

#Please check list of packages installed, so that you will have some idea
about what libraries are already installed
conda list

#Update conda
conda update conda

#Update conda packages, to have the latest libraries


conda update --all

Step 3:(Optional)

Install git, which will be helpful to clone sone examples from github

conda install git


Step 4:

Install openCV and scikit learn


conda install -c menpo opencv3 (conda install -c conda-forge opencv)

conda install -c anaconda scikit-learn

Step 5:

Install TensorFlow. In the below command if pip3 doesn't work use pip inplace of
pip3

pip3 install --upgrade tensorflow

(pip install --upgrade tensorflow)

or

pip install --ignore-installed --upgrade


https://storage.googleapis.com/tensorflow/windows/cpu/tensorflow-1.2.1-cp35-cp35m-
win_amd64.whl

Validation:

Invoke python from your shell as follows:

python

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 install Keras Deep
Learning Framework:

Hello, TensorFlow!

Just type

exit()

Step 6:

Install Keras

(conda create -n tensorflow python=3.5 numpy scipy matplotlib spyder)

pip install keras

Validation:

Just type

python

import keras
If the system outputs "using Tensorflow Backend", then the installation is
sucessful.

Just type

exit()

Note:

To check whether jupyter notebook is working or not, just type

jupyter notebook

It will open jupyter notebook in your default browser. When you open it for the
first time, some systems ask you enter the token, which you can get from the
Anaconda CMD Promt
Where you have typed jupyter notebook. Just read what is displayed and copy the
token and paste it.

You might also like