Practical PyTorch

Deep Learning has emerged as one of the most powerful Machine Learning techniques in recent times and has produced groundbreaking results across various applications ranging from self-driving cars to artistic creations such as generating paintings or composing music. And PyTorch is one of the most popular deep learning frameworks which enables fast and efficient development of all kinds of deep learning models. The best way to learn PyTorch is to learn by coding. This course is developed in a learning-by-coding format and will help you gain the practical and the necessary theoretical skills needed to develop deep learning models using PyTorch.

The course will first introduce the customer to Pytorch. It will explain what advantages it has compared to other popular deep learning frameworks like Tensorflow and why it is becoming increasingly popular in use. From there we will explore what Deep Learning is and how it fits in as a branch of Machine Learning, as well as its practical uses today. We will then explore core principles of Machine Learning and relate those principles to fundamental classification methods in Deep Learning. Before we are ready to dive into projects, we will learn about PyTorch’s relationship to Numpy, what goes into building a framework, and implement a custom Deep Learning framework built-in Numpy.

The following sections are all project-based lessons that engage the customer with the ‘learning by coding’ technique along with lectures that explain how the notebooks work with code along with videos. These projects will focus on Computer Vision, first introducing the customer to DCNN followed by different techniques, practices, and types of modeling. The last two projects will expose the customer to sequence models and walk through how an image can be classified with a sequence model as well as expose the student to Natural Language Processing.

By the end of this course, you will have a working knowledge of the deep learning concepts and how they relate to traditional machine learning. You will have an in-depth understanding of the PyTorch library, how it works and why it is an efficient deep learning framework. Most importantly, you will get a rich hands-on experience of building complex deep learning models using PyTorch thanks to the various projects covered in the second half of the course. After completing this course, you will be able to extend your practical knowledge of PyTorch to build your own deep learning models and work on more advanced deep learning projects.