Vision Models: Train and Evaluate

This short course gives you practical experience training and evaluating computer vision models. You’ll learn how to build image preprocessing pipelines, apply data augmentation, and train deep learning models such as CNNs and Vision Transformers. You’ll also learn to evaluate performance using metrics such as mean Average Precision (mAP), Intersection over Union (IoU), precision, and recall, and to use error analysis to understand failure patterns. Through short videos, focused readings, hands-on labs, and guided coaching, you’ll practice real job tasks such as writing TensorFlow data loaders, training a Vision Transformer on plant-disease images, computing per-class AP and mAP, and comparing results across IoU thresholds. By the end, you’ll have a complete workflow you can adapt to your own projects and use to demonstrate your skills

• Build image preprocessing pipelines and apply data augmentation
• Train deep learning models such as CNNs
• Train Vision Transformers for image analysis
• Evaluate model performance using metrics like mAP and IoU
• Use error analysis to identify failure patterns
• Practice applied tasks including data loader coding and model training

• Basic familiarity with common terminology and concepts in machine learning and computer vision
• Readiness to practice through applied exercises or case-based work