Hint: You can adjust the default video playback speed in your account settings.
Hint: You can set your subtitle preferences in your account settings.
Sorry! Looks like there’s an issue with video playback 🙁 This might be due to a temporary outage or because of a configuration issue with your browser. Please refer to our video player troubleshooting guide for assistance.

Python Deep Learning: PyTorch vs Tensorflow (Overview)

PyTorch vs TensorFlow: What’s the difference? Both are open source Python libraries that use graphs to perform numerical computation on data. Both are used extensively in academic research and commercial code. Both are extended by a variety of APIs, cloud computing platforms, and model repositories.

If they’re so similar, then which one is best for your project?

In this video course, you’ll learn:

  • What the differences are between PyTorch and TensorFlow
  • What tools and resources are available for each
  • How to choose the best option for your specific use case

You’ll start by taking a close look at both platforms, beginning with the slightly older TensorFlow, before exploring some considerations that can help you determine which choice is best for your project. Let’s get started!

Download

Course Slides (.pdf)

6.1 MB
Download

Sample Code (.zip)

1.8 KB

00:00 Welcome to the PyTorch versus TensorFlow course. I’m Nagar with Real Python, and I’ll be your guide.

00:07 When you’re starting to work on a machine learning project, one of the first choices you have to make is whether to create your model using TensorFlow or PyTorch.

00:16 This course will help you decide which one of the two works better for your project, how In the next few lessons, you’ll grasp the fundamentals of tensors, which are the backbone of both of the frameworks.

00:29 You’ll explore the general features of TensorFlow and PyTorch. You’ll become familiar with their coding style and explore a few code snippets. You’ll delve into Torch and Keras frameworks.

00:42 You’ll see what Torch is and how Keras makes TensorFlow a lot more convenient to use.

00:48 And finally, you’ll be acquainted with the ecosystems of TensorFlow and PyTorch. For example, you’ll get to know tools and websites that offer pre-trained models and built-in datasets and so on.

01:02 Before you start with the next lessons, refresh your memory with the following tutorials and courses. The first one is an excellent NumPy tutorial that covers the basics of NumPy arrays, which you’ll be using later.

01:17 And the second one is object-oriented programming in Python, which is both a tutorial and a course, you’ll need them later. Since some of the code snippets you’ll explore, use the concepts of classes and methods in this video course.

01:32 I’ll give you an overview about TensorFlow, PyTorch, and surrounding concepts, while I will show some code examples here and there. There won’t be any live coding.

01:43 If you want, grab yourself a notebook and take some notes, or just lean back while I present to you the pros, cons, similarities, and differences of TensorFlow and PyTorch.

01:57 Next up is understanding Tensors.

Become a Member to join the conversation.