Technical requirements
This chapter covers a practical example of monitoring metrics and setting up alerts, leveraging the code from the previous tutorial in Chapter 15, Deploying Deep Learning Models in Production. This tutorial requires you to have a Linux machine with an NVIDIA GPU device ideally in Ubuntu with Python 3.10 and the nvidia-docker tool installed. Additionally, we will require the following Python libraries to be installed:
numpytransformers==4.21.3nvidia-tensorrt==8.4.1.5torch==1.12.0transformers-deployTritonclient
The code files are available on GitHub: https://github.com/PacktPublishing/The-Deep-Learning-Architect-Handbook/tree/main/CHAPTER_16.
