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

Running a PyTorch model in C++

Python can sometimes be limiting, or we might be unable to run machine learning models trained using PyTorch and Python. In this section, we will use the serialized TorchScript model objects (using tracing and scripting) that we exported in the previous section to run model inferences inside C++ code.

Note

Basic working knowledge of C++ is assumed for this section. You can read up on C++ basics here [22]. This section specifically talks a lot about C++ code compilation. You can get a refresher on C++ code compilation concepts here [23].

For this exercise, we need to install CMake, following the steps mentioned in [24], to be able to build the C++ code. After that, we will create a folder named cpp_convnet in the current working directory and work from that directory:

  1. Let’s get straight into writing the C++ file that will run the model inference pipeline. The full C++ code is available here in our GitHub repository...