Size: 14.63 GiB (15708384467 Bytes) | Uploaded by: Metodone | Seeders: 10 | Leechers: 3
Release year: 8/2026
Udemy
Author: Felipe Tambasco
Duration: 22h 12m
Type of distributed material: Video tutorial
Language: English
Description: This course teaches computer vision through 30 hands-on projects, taking you from foundational image processing to advanced concepts while working with core libraries and frameworks including OpenCV, Scikit-learn, YOLO, and Detectron2. You build practical skills in object detection, image classification, segmentation, and pose estimation, with the structure progressing from fundamental image processing operations to machine learning and deep learning methods for more complex visual recognition tasks.
Beyond model building, you gain experience integrating computer vision into real applications: deploying models to the cloud with AWS, building web apps with Streamlit and Langchain, creating APIs, and running inference on edge devices. You also work with tools like AWS Rekognition and explore combining vision models with LLMs to create more capable systems, while developing the ability to evaluate and compare different approaches and understand trade-offs between models and how much data is needed for reliable performance. By the end, you'll be able to design, train, and deploy computer vision systems across a wide range of practical use cases, with a stronger understanding of feature extraction, model training, and dataset preparation. The instructor also welcomes Q&A feedback if any referenced resource becomes unavailable or content becomes outdated.
Sample files: not provided
Video format: MP4
Video: AVC, 1280x720, 16:9, 30fps, 1217kbps
Audio: AAC, 44.1Hz, 128kbps, stereo