A step-by-step tutorial to use Locust to load test a (pre-trained) image classifier model served using FastAPI. In my previous tutorial, we journeyed through building end-points to serve a machine learning (ML) model for an image classifier through an image classifier app, in 4 steps using Python and FastAPI. In this follow-up tutorial, we will focus on load/performance testing our end-points using Locust. If you have followed my last tutorial on serving a pre-trained image classifier model from TensorFlow Hub using FastAPI, then you can directly jump to Step 2 of this tutorial. In the app.py file, implement the /predict/tf/ end-point using FastAPI.

Automotive manufacturer Mahindra Heavy Engines Limited (MHEL) has been building powerful diesel engines for more than 70 years. But changing market demands forced this venerable company to face a 21st century dilemma. MHEL needed an extended quality testing program for internal combustion engines in order to reduce cost while accelerating the product manufacturing lifecycle. And there was no time to waste. But because of the technical resources required, and the fact that the data was staged in multiple stand-alone servers, the process was slow and costs high.

Artificial intelligence and machine learning (AI and ML) are so over-hyped today that I usually don't talk about them. But there are real and valid uses for these technologies in monitoring and performance management. Some companies have already been employing ML and AI with good results for a long time. VividCortex's own adaptive fault detection uses ML, a fact we don't generally publicize. AI and ML aren't magic, and I think we need a broader understanding of this.

Azure Machine Learning (Azure ML) is a fully managed cloud service that enables you to easily build, deploy and share predictive analytics solutions. Azure ML allows you to create a predictive analytic experiment and then directly publish that as a web service. The web service API can be used in two modes: "Request Response" and "Batch Execution". A Request-Response Service (RRS) is a low-latency, highly scalable web service used to provide an interface to stateless models that have been created and deployed from an Azure Machine Learning Studio experiment. It enables scenarios where the consuming application expects a response in real-time.