Fondamentaux de la Vision par Ordinateur avec Google Cloud

Aperçu

Computer Vision Fundamentals with Google Cloud teaches you how to develop and refine image-based machine learning solutions using Google Cloud tools and frameworks. Designed for professionals working with machine learning and visual data, this course builds practical knowledge of how different computer vision approaches apply to real-world use cases.

You’ll examine a range of methods, from pre-built APIs to fully custom model development, and understand how to select the right approach for a given problem. This course explores the key fundamentals of computer vision on Google Cloud, including:

Working with pre-built ML APIs and AutoML Vision, and progressing to custom image classification using DNN (deep neural network) and CNN (convolutional neural network) architectures Improving model performance through augmentation, feature extraction, and hyperparameter tuning Addressing challenges such as limited data availability and incorporating recent research into model design You’ll gain hands-on experience experimenting with multiple modeling approaches and techniques, learning how to evaluate performance and refine results across different scenarios.

The course also introduces strategies for balancing model complexity with practical constraints.

Programme

• Comprendre à un haut niveau les types de problèmes que la vision par ordinateur peut résoudre
• Comprendre certains des concepts clés et des architectures de modèles généralement utilisés en vision par ordinateur

---

Matières

Artificial Intelligence