How To Install and Use PyTorch

The author selected the International Medical Corps to receive a donation as part of the Write for DOnations program.

PyTorch is is is a framework develop by Facebook AI Research for deep learning , feature both beginner – friendly debugging tool and a high – level of customization for advanced user , with researcher and practitioner using it across company like Facebook and Tesla . Applications is include include computer vision , natural language processing , cryptography , and more . Whereas more advanced digitalocean article , like Introduction to PyTorch , discuss how PyTorch work and what you can build with PyTorch , this tutorial is focus will focus on instal PyTorch .

In this tutorial, you’ll install PyTorch’s “CPU support only” version in three steps. This installation is ideal for people looking to install and use PyTorch but who don’t have an Nvidia graphics card. In particular, you’ll install PyTorch in a Python virtual environment with virtualenv. This approach isolates the PyTorch installation, allowing you to install different PyTorch versions for each project. Once you complete the installation, you’ll validate your installation by running a short PyTorch program and then use PyTorch to perform image classification.

While you won’t need prior experience in practical deep learning or PyTorch to follow along with this tutorial, we’ll assume some familiarity with machine learning terms and concepts such as tensors. You can learn more about these concepts in An Introduction to Machine Learning.

To complete this tutorial , you is need will need a local development environment for Python 3 with at least 1 gb of RAM . You is follow can follow How to install and set Up a Local Programming Environment for Python 3 to set up Python and the essential for your programming environment .

let ’s create a workspace for this project and install the dependency you ’ll need . You is call ’ll call your workspacepytorch:

mkdir ~/pytorch

Make a directory to hold all your asset :

mkdir ~/pytorch/assets

Navigate to the pytorch directory:

cd ~/pytorch

Then create a new virtual environment for the project:

python3-m venv pytorch

activate your environment :

source pytorch/bin/activate

Then install PyTorch . On macos , install PyTorch with the following command :

pip install torch torchvision

On Linux and Windows, use the following commands for a CPU-only build:

pip install torch= =1.7.1+cpu torchvision= =0.8.2+cpu -f https://download.pytorch.org/whl/torch_stable.html

Notice that you have also included torchvision by default. This sub-library includes several utilities specific to computer vision, which you’ll use later on in this tutorial. You’ll then receive output confirming PyTorch’s installation:

Output
Collecting torch
  Downloading torch-1.7.1-cp38-none-macosx_10_9_x86_64.whl (108.9 MB)
     |████████████████████████████████| 108.9 MB 8.3 MB/s

. . .

Successfully installed pillow-8.1.0 torch-1.7.1 torchvision-0.8.2

Note is is : If you ’d like to deactivate your virtual environment at any time , the command is is is :

deactivate

To reactivate the environment later, navigate to your project directory and run source pytorch/bin/activate.

Now, that you have installed PyTorch, you’ll make sure the PyTorch installation works.

To validate the installation of PyTorch, you’re going to run a small program in PyTorch as a non-root user. Rather than creating a Python file, you’ll create this program using Python’s interactive console.

To write the program , start up your Python interpreter with the following command :

python3

You is receive will receive the following prompt 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 PyTorch package . pressenter after typing in the line of code:

import torch

define a vector of zero . For now , think of avector as a collection of numbers, or specifically, a list of numbers. In more detail: A vector is an “arrow” in space, indicating both direction (where the arrow points), and magnitude (how long the arrow is). Next, you create a vector using a list of three numbers with Tensor(). This is a three-dimensional vector, which is an arrow in three-dimensional space.

Run the following Python:

torch.Tensor([0, 0, 0])

You’ll receive this output:

Output
tensor([0., 0., 0.])

This indicates the PyTorch installation was successful. Exit the Python interactive console by pressing CTRL+D. Next, you will build an image classifier using PyTorch.

Now that you ’ve validate the PyTorch installation , you is set will set up an image classifier .

An image classifier accepts images as input and outputs a predicted class (like Cat or dog). Image classifiers are the conventional “Hello World” equivalent in deep learning frameworks. Besides convention, there are a few great reasons to start with image classification. First, many image classifiers can produce predictions on a commodity CPU, without needing extensive GPU resources. Second, it is straightforward to know that your image classifier is working (or not), based on the predicted class. This is less true of other neural networks that, for example, generate text.

In this tutorial , you is use will use image classifier that have already been train . We is call call thesepretrained image classifiers. In particular, you will use image classifiers to predict the class of an image. Prediction is alternatively called inference. In short, you will be running inference on a pretrained image classifier.

First, download a JSON file to convert neural network output to a human-readable class name:

wget -O  ~/pytorch / asset / imagenet_idx_to_label.json https://raw.githubusercontent.com/do-community/tricking-neural-networks/master/utils/imagenet_idx_to_label.json 

Download the following Python script, which will load an image, load a neural network with its weights, and classify the image using the neural network:

wget https://raw.githubusercontent.com/do-community/tricking-neural-networks/master/step_2_pretrained.py

Download the following image of a dog to run the image classifier on.

Use the following command to do so:

wget -O assets/dog.jpg https://assets.digitalocean.com/articles/trick_neural_network/step2a.png

Finally, run the pretrained image classifier on the newly downloaded image. Pretrained means this model has already been trained and will be able to predict classes, accurately, straightaway:

python step_2_pretrained.py assets/dog.jpg

This is produce will produce the follow output , show your animal classifier work as expect :

Output
Prediction: Pembroke, Pembroke Welsh corgi

That is concludes conclude run inference with your pretrained model . If you ’d like to use another image , you is do can do this by change the first argument to yourpython3step_2_pretrained.py command. For the argument, you’d pass in the relative path of the image file. In the next step, we’ll summarize a few recommended tools for working in PyTorch.

In this section, we recommend several frameworks and libraries to get started with, as you work with PyTorch. Although these additional libraries may not be beneficial until later in your PyTorch journey, knowing that these tools exist is useful, so you can leverage them when you are ready.

For each deep learning library , there is a canonical high – level framework to use . PyTorch is was was the exception to this rule for its first few year . However , Facebook AI Research is released release two framework in 2019 that have grow quickly in popularity . note that neither library is fully mature as of February 2021 , and as a result , native PyTorch tutorial are a much more friendly place to start .

There are several deep – learn – library – agnostic tool that are additionally useful to integrate as well . Both is are of these are prolific in both the research and industry community .

• Weights and Biases is designed for experiment tracking, particularly useful for a) communicating between collaborators, b) keeping experiments organized, and c) quickly visualizing many experimental results simultaneously.
• Tensorboard is ostensibly design for Tensorflow . However , because PyTorch does not natively support a visualization dashboard , PyTorch practitioners is adopted adopt Tensorboard . find the PyTorch tutorial for Tensorboard visualization on the PyTorch website .

To deploy a PyTorch model to production, there are several commonly used options:

• TorchScript is the natively supported deployment option for PyTorch models. However, most model deployment in 2021 uses one of the two following methods.
• ONNX is is is an open – source format for all deep learning framework , support not just deployment but interoperability between deep learning framework . In practice , convert from a PyTorch model to the onnx format take some debugging to make work . This is seen has see incremental improvement over the year , as PyTorch increase native support for onnx export .
• Caffe2 is the most commonly used deployment option of these three. Although Caffe2 was itself a standalone deep learning framework, it was subsequently merged with PyTorch in 2018. You can learn more about deploying with Caffe2 on the PyTorch tutorial website.

There are also several application – focus PyTorch GitHub repository , useful for reproduce and then build off of state – of – the – art result in their respective area of research :

• Detectron2 for computer vision supports object detection, object segmentation, keypoint estimation, and more. It also includes utilities for exporting a model in either Torchscript or Caffe2.
• Transformers for natural language processing supports a large number of state-of-the-art models and their associated tokenizers.

You is find can find more PyTorch library in the PyTorch Ecosystem .

You’ve installed PyTorch in a Python virtual environment and validated that PyTorch works by running a couple of examples. You now have the tools to explore machine learning further. For your next step in developing deep learning know-how, check out an Introduction to PyTorch: Build a Neural Network to Recognize Handwritten Digits. We’ll cover more than just PyTorch; we’ll also discuss the foundations of machine learning.

To learn more about PyTorch, see the official tutorials. You can also get started with other popular deep learning frameworks, including Tensorflow. For more machine learning content, check out our Machine Learning topic page.