AI Workshop: Build a Neural Network with PyTorch Lightning (2023)
1h 31mIntermediate2023-12-08
Authors
Janani Ravi
Certified Google Cloud Architect and Data Engineer
Course details
If you’re looking for hands-on AI practice, this workshop-style coding course was designed for you. Join instructor Janani Ravi as she shows you how to build a neural network with PyTorch Lightning, the open-source library from Python that provides an interface for the popular deep learning framework PyTorch. Explore the core components of building a neural network with PyTorch, including setting up the virtual environment, loading and exploring data, preprocessing data for training, creating and training a simple neural network, setting up the Dataset and DataLoader, visualizing losses, and much more. Along the way, Janani covers the basics of using modules in PyTorch Lightning to build, train, and evaluate both regression and classification models.
Skills covered
PyTorchNeural Networks and Deep LearningArtificial Intelligence (AI)One-Off
Concepts
0. Introduction
- 01 - AI workshop - Build a neural network with PyTorch Lightning
- 02 - Prerequisites
- 03 - Quick overview of neural networks
1. Building a Neural Network with PyTorch
- 04 - Setting up the virtual environment
- 05 - Loading and exploring regression data
- 06 - Preprocessing data for training
- 07 - Creating a simple neural network
- 08 - Setting up the dataset and DataLoader
- 09 - Training a neural network using PyTorch
- 10 - Visualizing losses and evaluating models
- 11 - Building and training a more complex neural network
2. Using PyTorch Lightning to Build a Regression Model
- 12 - Encapsulating data using a LightningDataModule
- 13 - Encapsulating a model using a LightningModule
- 14 - Training the model using the PyTorch Lightning Trainer
3. Using PyTorch Lightning to Build a Classification Model
- 15 - Loading and exploring classification data
- 16 - Creating a LightningDataModule
- 17 - Creating a LightningModule
- 18 - Training a classification model and evaluating metrics
Conclusion
- 19 - Summary and next steps