Skip to main content

Installing Tensorflow 1.3 on Windows 10 Machine in 3 simple steps

TensorFlow is an open-source software library for machine learning across a range of tasks. It is a system for building and training neural networks to detect and decipher patterns and correlations, analogous to (but not the same as) human learning and reasoning. It is used for both research and production at Google,‍ often replacing its closed-source predecessor, DistBelief.

The latest version of TensorFlow is version 1.3. In this tutorial I will show you how to install tensorflow on a Windows 10 Machine.

Step 1: Install Python 3.6

Python 3.6 is the latest stable release of python language interpreter. To install python 3.6 first download self executable python installer and install it on your Windows 10 machine. Remember to put the python home directory in the PATH variable. You can download the python 3.6.* from this URL https://www.python.org/downloads/


Step 2: Install Dependency libraries

Once you installed python and set the environment path, you can invoke the pip command in the command prompt. Pip is the best way to install python libraries. Numpy is a python library for numerical processing. Install numpy by invoking the following command in the command prompt.

C:>pip install numpy

Step 3: Install Tensorflow

After installing all the required libraries you can install the tensorflow by invoking the following command in the command prompt.
C:>pip install tensorflow

Validate your installation

Start a command prompt.
Invoke python from your cmd as follows:
C:> 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!
 
CONGRATULATIONS! YOU HAVE SUCCESSFULLY INSTALLED Tensorflow on Windows.