Mask Detector with Python & TensorFlow: Build & Deploy

External: Coursera Courses ↗ · Coursera

Open Course on External: Coursera

Free to audit · Opens on External: Coursera

Mask Detector with Python & TensorFlow: Build & Deploy

Coursera · Intermediate ·🧬 Deep Learning ·4mo ago

Key Takeaways

Teaches learners how to build and deploy a mask detector using Python and TensorFlow

Original Description

By the end of this course, learners will be able to analyze images with OpenCV, build and train deep learning models with TensorFlow, design interactive applications, and deploy AI solutions on AWS. This hands-on project-based course is designed for learners who want to move beyond theory and apply machine learning to a real-world challenge: COVID-19 mask detection. Starting with the fundamentals of image handling, resizing, and annotation, learners progress into face detection techniques using Haar Cascades and explore deep learning with Convolutional Neural Networks. The course emphasizes practical skills, guiding participants step by step from data preprocessing to building a functional mask detection app. A unique feature of this course is its end-to-end workflow: not only will learners train an efficient MobileNetV2 model, but they will also integrate it into an interactive front-end application and deploy it to AWS for global accessibility. This complete journey—from concept to cloud—ensures learners gain both technical knowledge and professional deployment skills. Whether you’re an aspiring data scientist, AI enthusiast, or developer aiming to add practical deep learning projects to your portfolio, this course provides a comprehensive, real-world learning experience.
AI explanation not available for this lesson yet
This lesson is still being prepared for the AI tutor. In the meantime, explore lessons that are ready.
Browse explainer-ready lessons →

Related Reads

📰
Deep Learning Scientists — Claude Cowork: The Deep Learning Scientist’s New Lab Partner
Meet Claude Cowork, a new tool for deep learning scientists to optimize their workflow and reduce the scarcity of compute and attention resources
Medium · Data Science
📰
Why Qwen3.8 27B Looked Brilliant in Testing but Failed to Ship My AI Newspaper
Learn why a high-performing AI model like Qwen3.8 27B failed to deliver in real-world application and how to avoid similar pitfalls
Medium · Deep Learning
📰
The 91% Model: What August’s Benchmarks Reveal About the Real Cost of Staying at the Frontier
The 91% model reveals the real cost of staying at the frontier of deep learning performance, questioning whether the last 9% is worth the investment
Medium · Deep Learning
📰
Nemotron 3.5 vs Qwen 3.6 vs Muse: I Thought Qwen Was Done. My Experiments Said Something Else.
Compare performance of Nemotron 3.5, Qwen 3.6, and Muse on a DGX Spark with 13 trick questions and a pressure test
Medium · Data Science
Up next
how to run ablation in pretraining?
Deep Learning with Yacine
Watch →