Chevron Left
Back to Foundations and Core Concepts of PyTorch

Learner Reviews & Feedback for Foundations and Core Concepts of PyTorch by Packt

3.9
stars
10 ratings

About the Course

In this comprehensive course, you'll embark on a journey through the foundational elements and core concepts of PyTorch, one of the most
popular deep learning frameworks. Starting with a detailed overview and system setup, you'll be guided through installing and configuring your
environment to ensure a smooth learning experience. The course then transitions into the basics of machine learning and artificial intelligence,
laying the groundwork for more advanced topics. As you delve deeper, you'll explore the intricacies of deep learning, including model
performance, activation and loss functions, and optimization techniques. Each module builds on the last, gradually increasing...
...

Top reviews

Filter by:

1 - 4 of 4 Reviews for Foundations and Core Concepts of PyTorch

By Alex G

•

Jan 19, 2025

Great course for someone who already has some background in ML and python and want a quick introduction to pytorch (my situation). I really appreciated the structure of the course, such as how the coding assignments build on each other, and how they transitioned from building everything from scratch initially to using pytorch's tools to automate many parts of the process. That being said, I do NOT think this course is appropriate for someone learning ML for the first time. The concepts are covered much too quickly and with insufficient detail if you're seeing them for the first time. The coding lectures are deceptively easy: you just watch the teacher implement the code in the recordings and move on. There isn't much opportunity to think deeply about the concepts, and you can easily find yourself just copying/running the code without knowing what you're doing. The multiple choice tests help test your understanding somewhat, but I often found them more annoying than useful. The questions were often carelessly worded and unclear. For example, is parameter initialization part of the training loop? I said no, as you initialize parameters before the part that is actually being *looped* (i.e., forward pass, calculating loss, calculating gradients, updating weights). I don't mind being wrong, but I don't feel like the course content explained this distinction well enough, and this kind of situation arose in EVERY test. Another very annoying detail was that in the recordings the code was implemented using an IDE that automatically suggests/completes syntax. Because of this, there were times where an important line of code was entered automatically and the teacher did not explain that part of the code. To make matters worse, while the teacher was typing code into the IDE, suggestions/explanations would pop up on the screen and COVER UP the lines of text that were just entered in (so I would have to search through the video to find the split second where the relevant code was entered in and still visible).

By Julia S

•

Nov 4, 2024

Love the approach and explanation. This is a really high quality course!

By Anastasios T

•

Dec 6, 2024

It was useful

By Georg H

•

Dec 18, 2024

The required packages are not available for Macs with Apple Silicon, so I can't do this course.