Deep Learning with PyTorch Lightning

Build, train, and deploy deep learning models quickly and accurately to improve your productivity using PyTorch Lightning Wrapper

Key Features

• Become well-versed with PyTorch Lightning and learn how to implement it in various applications
• Speed up your research using PyTorch Lightning by creating new loss functions, and architectures
• Train and build new DL applications for images, audio, video, structured and unstructured data

Book Description

What you will learn

• Customize models that are built for different datasets, model architectures
• Understand a variety of DL models from image recognition, NLP to time series
• Create advanced DL models to write poems (Semi-Supervised) or create fake images (GAN)
• Learn to train on unlabelled images using Self-Supervised Contrastive Learning
• Learn to use pre-trained models using transfer learning to save compute
• Make use of out-of-the-box SOTA model architectures using Lightning Flash
• Explore techniques for model deployment & scoring using ONNX format
• Run and tune DL models in a multi-GPU environment using mixed-mode precisions

Who this book is for

If you’re a data scientist curious about deep learning but don't know where to start or feel intimidated by the complexities of large neural networks, then this book is for you. Expert data scientists making the transition from other DL frameworks to PyTorch will also find plenty of useful information in this book, as will researchers interested in using PyTorch Lightning as a reference guide. To get started, you’ll need a solid grasp on Python; the book will teach you the rest