To create value in the real world, engineers and organizations need to be able to deploy Machine Learning (ML) models in a production environment. However, the unfortunate reality is that most models never make it to production. Even if they do, the deployment process takes much longer than necessary.
In addition, the first obstacle to overcome is to have the right skills to deploy the models in the first place.
In the words of Omdena´s Head of Projects Harini Suresh, “the deployment is something that mostly comes with practice by implementing it in a project (courses don’t do justice to deployment but only provide a starting point)”.
Therefore, successfully deploying a machine learning model does not stop but it requires domain-specific upkeep that can create new engineering and operations challenges. Because of this, a proper MLOps implementation streamlines the process of developing and deploying ML models.
Below are two recent real-world case studies from Omdena AI Challenges and at the end of the article you find a list of more than 30 exciting projects including the deployment of machine learning models.
1. Deploying an AutoML Model Using Streamlit
Firstly, you will find a step-by-step Streamlit tutorial on displaying the predicted safety ratings of roads to prevent road crashes and save lives.
2. Deploying a Model Using Docker in a Mobile App
The article shows steps for deploying a model with flask and creating a Docker container so that it can be easily deployed in the cloud. In addition, you will find a case study on creating an offline pathology mobile app. The app can be used in places without a stable internet connection (e.g. in some developing countries).
(Course) MLOps for AI Engineers and Data Scientists
In this OmdenaSchool course on MLOps an Omdena instructor teaches you theoretical concepts in combination with a real-world case study, For example, estimating daily solar energy generated. It will be implemented using a Machine Learning and Deep Learning FrameWork.
30+ Case Studies on Model Deployment in Production
From raw data to visualization
Omdena teams spend significant time on cleaning and wrangling data in order to extract valuable insights. Next, our teams build highly contextual dashboards to visualize insights and drive value.
Interactive dashboards deployed on the web with data analysis, map visualizations, and different views. All models and predictions appear live on the website.
Visualizing data and models’ predictions on Tableau, with different views and slides.
Deploying the models on Android based web applications using Flask.
Showing the data collected, the analysis, and different models’ results in an interactive way.