Book Image

Mastering PyTorch - Second Edition

By : Ashish Ranjan Jha
4 (1)
Book Image

Mastering PyTorch - Second Edition

4 (1)
By: Ashish Ranjan Jha

Overview of this book

PyTorch is making it easier than ever before for anyone to build deep learning applications. This PyTorch deep learning book will help you uncover expert techniques to get the most out of your data and build complex neural network models. You’ll build convolutional neural networks for image classification and recurrent neural networks and transformers for sentiment analysis. As you advance, you'll apply deep learning across different domains, such as music, text, and image generation, using generative models, including diffusion models. You'll not only build and train your own deep reinforcement learning models in PyTorch but also learn to optimize model training using multiple CPUs, GPUs, and mixed-precision training. You’ll deploy PyTorch models to production, including mobile devices. Finally, you’ll discover the PyTorch ecosystem and its rich set of libraries. These libraries will add another set of tools to your deep learning toolbelt, teaching you how to use fastai to prototype models and PyTorch Lightning to train models. You’ll discover libraries for AutoML and explainable AI (XAI), create recommendation systems, and build language and vision transformers with Hugging Face. By the end of this book, you'll be able to perform complex deep learning tasks using PyTorch to build smart artificial intelligence models.
Table of Contents (21 chapters)
20
Index

Creating a model microservice

Imagine you know nothing about training machine learning models but want to use an already trained model without having to get your hands dirty with any PyTorch code. This is where a paradigm such as a machine learning model microservice [6] comes into play.

A machine learning model microservice can be thought of as a black box to which you send input data and it sends back predictions to you. Moreover, it is easy to spin up this black box on a given machine with just a few lines of code. The best part is that it scales effortlessly. You can scale a microservice vertically by using a bigger machine (more memory, more processing power) as well as horizontally, by replicating the microservice across multiple machines.

How do we go about deploying a machine learning model as a microservice? Thanks to the work done using Flask and PyTorch in the previous exercise, we are already a few steps ahead. We have already built a standalone model server using...