PyTorch Essential Training: Deep Learning
1h 22mIntermediate2024-04-15
Authors
Terezija Semenski
Software Developer, Mathematician, Writer, and Learner
Course details
PyTorch is the most flexible and expressive library for deep learning, and offers simple Python API, GPU support, and flexibility. It’s designed to load data, apply transforms, and build deep learning models with just a few lines of code. Many machine learning developers and researchers use PyTorch to accelerate deep learning research, experimentation, and prototyping. In this course, software developer Terezija Semenski teaches you the important features of PyTorch with a hands-on approach to help you develop the skills you need to dive into your deep learning projects.
Skills covered
PyTorchNeural Networks and Deep LearningPythonEssential TrainingArtificial Intelligence (AI)Open Source
Concepts
Introduction
- Deep learning with PyTorch
- What you should know
- Tour of CoderPad
PyTorch Overview and Introduction to Google Colaboratory
- Introduction to deep learning
- Why should you use PyTorch
- Google Colaboratory basics
Tensors
- Introduction to tensors
- Creating a tensor CPU example
- Creating a tensor GPU example
- Moving tensors between CPUs and GPUs
Creating Tensors
- Different ways to create tensors
- Tensor attributes
- Tensor data types
- Creating tensors from random samples
- Creating tensors like other tensors
- Solution - Create tensors
Manipulate Tensors
- Tensor operations
- Mathematical functions
- Linear algebra operations
- Automatic differentiation (Autograd)
- Solution - Split tensors to form new tensors
Developing a Deep Learning Model
- Introduction to the DL training process
- Data preparation
- Data loading
- Data transforms
- Data batching
- Model development and training
- Validation and testing
Conclusion
- Next steps