What you'll Learn
-
Understand the essentials of model deployment and why FastAPI is a preferred framework.
-
Train an XGBoost model and serve it using FastAPI with proper validation and testing.
-
Explore how to package and deploy the application using Docker for real-world deployment readiness.
-
Gain hands-on experience building and running APIs with minimal setup.
Who Should Enroll?
-
Professionals: Ideal for machine learning engineers and data scientists looking to bring models into production. Learn how to build robust, fast, and scalable APIs using FastAPI and Docker.
-
Aspiring Students: Great for learners exploring model deployment workflows. Understand real-world practices and gain skills in building production-ready APIs with ease.
About the Instructor
Priyanka Asnani, Senior Machine Learning Engineer at Fidelity Investments
Priyanka is a Senior Machine Learning Engineer at Fidelity Investments with over 7 years of experience. She specializes in building end-to-end machine learning pipelines, focusing on recommender and ranking systems. Her expertise spans large language models, deep learning, and time-series forecasting. Priyanka excels at applying machine learning techniques to solve complex problems across industries. She is an active community contributor who shares her knowledge through public speaking, webinars, and technical content, helping aspiring data scientists stay updated with industry trends.
FAQ's
-
What is FastAPI, and why use it for model deployment?
FastAPI is a modern web framework for building APIs with Python. It's known for speed, simplicity, and great developer experience, making it ideal for ML model deployment.
-
Will I learn how to containerize the project?
Yes, you will build a Docker image, run the container, and expose the FastAPI endpoint using Docker.
-
Will I receive a certificate upon completing the course?
Yes, the course provides a certification upon completion.
-
Will there be hands-on projects?
Yes! This is a practical, project-based course where you'll train a real ML model and deploy it using FastAPI and Docker through step-by-step hands-on videos.
-
What programming languages and tools will be used?
You’ll work with Python, TensorFlow/PyTorch (for DistilBERT), Apache Airflow, and Streamlit to build the sentiment classification pipeline.