This is the code repository for Deep Learning Adventures with PyTorch [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
Are you ready to go on a journey into the world of deep learning? This course will be your guide through the joys and dangers of this new wave of machine learning method. Why? Because, let’s face it, getting started with deep learning is difficult.Things like choosing between multiple frameworks, understanding APIs and debugging code is not easy. Is there an another way? Yes. Meet PyTorch. Like Python, PyTorch has a clean and simple API which makes building neural networks faster with ease. It’s also modular and that makes debugging your code a breeze. This course will be one hell of an adventure into the world of deep learning! You will start by using Convolutional Neural Networks (CNN) to classify images. Recurrent Neural Network (RNN) to detect languages and then translate it using Long-Term-Short Memory (LTSM). Finally, you would channel your inner Picasso by using Deep Neural Network (DNN) to paint unique images. By the end of our adventure you will be ready to use Pytorch proficiently in your real-world projects.
- Intuitive ways to build neural networks using the PyTorch API to make this deep learning ride enjoyable
- Master PyTorch's unique features gradually as you work through projects that make PyTorch perfect for rapid prototyping
- Debug your PyTorch code using standard Python tools, so you can easily fix bugs
- Work with PyTorch and learn its advantages over other frameworks, and choose the right vehicle for your deep-learning ride
- Get practical, project-based experience with this popular and 7051 in-demand deep-learning library
To fully benefit from the coverage included in this course, you will need:
To fully benefit from the coverage included in this course, you will need:
• Working Python knowledge
• The basics of Machine Learning
This course has the following software requirements:
This course has the following software requirements:
• Python 3.6 (https://www.python.org/downloads/)
• Python Package Installer - pip command included with Python
• PyTorch
• Python packages: pytorch and unidecode (installed from command prompt using the following commands: “pip install pytorch unidecode)
• A code editor, author used Atom in the course
This course has been tested on the following system configuration:
• OS: macOS High Sierra
• Processor: 1,3 GHz Intel Core 5
• Memory: 4 GB
• Storage: 121 GB