Computer vision¶
Computer vision teaches machines to interpret images: what is in them, where it is, and — at the finest grain — which pixel belongs to what. This chapter covers the tasks (classification, detection, segmentation, and their relatives), the architectures that solve them (CNNs → ResNet → U-Net → Vision Transformers), the metrics that judge them (IoU, mAP, Dice), the training recipes that make them work on realistic data budgets (transfer learning, self-supervised pretraining, augmentation), and the production concerns that turn a notebook model into a served system (formats, quantization, drift). …
🔒 La suite est en accès freemium — lecture complète 100 % gratuite
Tu lis ici l'aperçu libre. Le reste du chapitre (code, schémas, maths, exercices) fait partie du livre complet : crée un compte gratuit (30 secondes, aucun paiement) pour tout lire.