Verified project record

DataTalksClub/machine-learning-zoomcamp

machine-learning-zoomcamp is a free, hands-on course that teaches the complete machine learning engineering path, from framing a problem and preparing data to training, evaluating, and deploying a model as a production service. It covers ten modules using Python, scikit-learn, TensorFlow, and PyTorch, plus deployment with FastAPI and Docker.

Project overview

It is a free course that covers the full path from an ML problem to a deployed production service, including turning a trained model into a web service with FastAPI, packaging it with Docker, and deploying it to a cloud platform.

Project type: Model Development · Model Runtime · Infrastructure · Learning Resources
Use cases: Learning & Education
Deployment: Refer to project documentation
License: License pending

Best for

Learners with programming experience who want a free, structured, hands-on course covering the full ML engineering path from problem framing to deployed service.

Key capabilities

Ten modules teaching regression, classification, evaluation metrics, tree-based models, and deep learning with Python, scikit-learn, TensorFlow, and PyTorch.
A module teaching how to turn a trained model into a web service with FastAPI, package it with Docker, and deploy it to a cloud platform.
Midterm and capstone projects where learners build end-to-end ML services; the certificate requires two projects and peer review during a live cohort.

Limitations and risks

Certificates are available only through a live cohort, not self-paced; earning one requires two projects and peer review.

Getting started

Follow the course materials in the repository, watch the lectures in the YouTube playlist, and complete the homework and build an end-to-end project. A laptop with an internet connection is sufficient — no powerful computer or local GPU is required, since the deep learning modules use cloud resources, and no paid service is required.

Evidence and sources

GitHub project description: Learn ML engineering for free in 4 months! Register here 👇🏼
README: Frame the problem, prepare the data, train and evaluate the model, expose it through an API, package it, and deploy it.
README: Expose predictions through a FastAPI service. - Package the service with Docker. - Deploy the service to a cloud platform.
README: You choose a dataset, define the prediction task, develop and evaluate a model, and deploy it as a web service.
README: A powerful computer or local GPU. The deep learning modules use cloud resources for more intensive computation.

Source updated at: 2026-10-15T19:37:19Z

Open original GitHub project