TensorFlow is an open-source machine learning software built by Google to train neural networks. TensorFlow’s neural networks are expressed in the form of stateful dataflow graphs. Each node in the graph represents the operations performed by neural networks on multi-dimensional arrays. These multi-dimensional arrays are commonly known as “tensors”, hence the name TensorFlow.
TensorFlow is a deep learning software system. TensorFlow works well for information retrieval, as demonstrated by Google in how they do search ranking in their machine-learning artificial intelligence system, RankBrain. TensorFlow can perform image recognition, as shown in Google’s Inception, as well as human language audio recognition. It’s also useful in solving other problems not specific to machine learning, such as partial differential equations.
The TensorFlow architecture allows for deployment on multiple CPUs or GPUs within a desktop, server or mobile device. There are also extensions for integration with CUDA, a parallel computing platform from Nvidia. This gives users who are deploying on a GPU direct access to the virtual instruction set and other elements of the GPU that are necessary for parallel computational tasks.
In this tutorial, you’ll install TensorFlow’s “CPU support only” version. This installation is ideal for people looking to install and use TensorFlow, but who don’t have an Nvidia graphics card or don’t need to run performance-critical applications.
You can install TensorFlow several ways. Each method has a different use case and development environment:
In this tutorial, you’ll install TensorFlow in a Python virtual environment with
virtualenv. This approach isolates the TensorFlow installation and gets things up and running quickly. Once you complete the installation, you’ll validate your installation by running a short TensorFlow program and then use TensorFlow to perform image recognition.
Before you begin this tutorial, you’ll need the following:
One Ubuntu 16.04 server with at least 1GB of RAM set up by following the Ubuntu 16.04 initial server setup guide, including a sudo non-root user and a firewall. You’ll need at least 1GB of RAM to successfully perform the last example in this tutorial.
Python 3.3 or higher and
virtualenv installed. Follow How to Install Python 3 on Ubuntu 16.04 to configure Python and
Git installed, which you can do by following How To Install Git on Ubuntu 16.04. You’ll use this to download a repository of examples.
In this step we are going to create a virtual environment and install TensorFlow.
First, create a project directory called
- mkdir ~/tf-demo
Navigate to your newly created
- cd ~/tf-demo
Then create a new virtual environment called
tensorflow-dev. Run the following command to create the environment:
- python3 -m venv tensorflow-dev
This creates a new
tensorflow-dev directory which will contain all of the packages that you install while this environment is activated. It also includes
pip and a standalone version of Python.
Now activate your virtual environment:
- source tensorflow-dev/bin/activate
Once activated, you will see something similar to this in your terminal:
Now you can install TensorFlow in your virtual environment.
Run the following command to install and upgrade to the newest version of TensorFlow available in PyPi:
- pip3 install --upgrade tensorflow
TensorFlow will install:
Downloading tensorflow-1.4.0-cp36-cp36m-macosx_10_11_x86_64.whl (39.3MB)
100% |████████████████████████████████| 39.3MB 35kB/s
Successfully installed bleach-1.5.0 enum34-1.1.6 html5lib-0.9999999 markdown-2.6.9 numpy-1.13.3 protobuf-3.5.0.post1 setuptools-38.2.3 six-1.11.0 tensorflow-1.4.0 tensorflow-tensorboard-0.4.0rc3 werkzeug-0.12.2 wheel-0.30.0
If you’d like to deactivate your virtual environment at any time, the command is:
To reactivate the environment later, navigate to your project directory and run
Now, that you have installed TensorFlow, let’s make sure the TensorFlow installation works.
To validate the installation of TensorFlow, we are going to run a simple program in TensorFlow as a non-root user. We will use the canonical beginner’s example of “Hello, world!” as a form of validation. Rather than creating a Python file, we’ll create this program using Python’s interactive console.
To write the program, start up your Python interpreter:
You will see the following prompt appear in your terminal
This is the prompt for the Python interpreter, and it indicates that it’s ready for you to start entering some Python statements.
First, type this line to import the TensorFlow package and make it available as the local variable
ENTER after typing in the line of code:
- import tensorflow as tf
Next, add this line of code to set the message “Hello, world!”:
- hello = tf.constant("Hello, world!")
Then create a new TensorFlow session and assign it to the variable
- sess = tf.Session()
Note: Depending on your environment, you might see this output:
Output2017-06-18 16:22:45.956946: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-18 16:22:45.957158: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-18 16:22:45.957282: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-06-18 16:22:45.957404: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-06-18 16:22:45.957527: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
This tells you that that you have an instruction set that has the potential to be optimized for better performance with TensorFlow. If you see this, you can safely ignore it and continue.
Finally, enter this line of code to print out the result of running the
hello TensorFlow session you’ve constructed in your previous lines of code:
You’ll see this output in your console:
This indicates that everything is working and that you can start using TensorFlow to do something more interesting.
Exit the Python interactive console by pressing
Now let’s use TensorFlow’s image recognition API to get more familiar with TensorFlow.
Now that TensorFlow is installed and you’ve validated it by running a simple program, let’s look at TensorFlow’s image recognition capabilities.
In order to classify an image you need to train a model. Then you need to write some code to use the model. To learn more about these concepts, you can take a look at An Introduction to Machine Learning.
TensorFlow provides a repository of models and examples, including code and a trained model for classifying images.
Use Git to clone the TensorFlow models repository from GitHub into your project directory:
- git clone https://github.com/tensorflow/models.git
You will see the following output as Git checks out the repository into a new folder called
OutputCloning into 'models'...
remote: Counting objects: 8785, done.
remote: Total 8785 (delta 0), reused 0 (delta 0), pack-reused 8785
Receiving objects: 100% (8785/8785), 203.16 MiB | 24.16 MiB/s, done.
Resolving deltas: 100% (4942/4942), done.
Checking connectivity... done.
Switch to the
- cd models/tutorials/image/imagenet
This directory contains the
classify_image.py file which uses TensorFlow to recognize images. This program downloads a trained model from
tensorflow.org on its first run. Downloading this model requires that you have 200MB of free space available on disk.
In this example, we will classify a pre-supplied image of a Panda. Execute this command to run the image classifier program:
- python classify_image.py
You’ll see output similar to this:
Outputgiant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca (score = 0.89107)
indri, indris, Indri indri, Indri brevicaudatus (score = 0.00779)
lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens (score = 0.00296)
custard apple (score = 0.00147)
earthstar (score = 0.00117)
You have classified your first image using the image recognition capabilities of TensorFlow.
If you’d like to use another image, you can do this by adding the
-- image_file argument to your
python3 classify_image.py command. For the argument, you’d pass in the absolute path of the image file.
You’ve installed TensorFlow in a Python virtual environment and validated that TensorFlow works by running a couple of examples. You now possess tools that make it possible for you to explore additional topics including Convolutional Neural Networks and Word Embeddings.
TensorFlow’s programmer’s guide is a great resource and reference for TensorFlow development. You can also explore Kaggle, a competitive environment for practical application of machine learning concepts that pit you against other machine learning, data science, and statistics enthusiasts. They have an excellent wiki where you can see and share solutions, some of which are on the cutting edge of statistical and machine learning techniques.
Thanks for learning with the DigitalOcean Community. Check out our offerings for compute, storage, networking, and managed databases.
Working on improving health and education, reducing inequality, and spurring economic growth? We'd like to help.