Data, machine learning and deep learning
Computer vision with AI course
Teaching machines to see: inspection, counting, reading documents and more.
Computer vision lets machines inspect parts, count products, read documents or monitor processes continuously. It is one of the AI applications with the clearest return in manufacturing, logistics and retail.
In this course you will learn to solve the typical vision problems: classification, object detection, segmentation and anomaly detection, with special attention to the most underestimated part, the data (capture, labelling and defects that almost never appear). We also see when a multimodal model already solves the problem without training anything, and how to deploy at the edge.
What you will learn
- Understand the vision tasks and when to apply each one
- Label images and prepare datasets
- Train detection and segmentation models
- Use multimodal models to understand images and documents
- Deploy models on servers and devices
Syllabus
8 modules, from the fundamentals to the final project.
-
Computer vision in business
- Quality inspection, logistics, retail, security and documents
- Camera, lighting and data requirements
-
Fundamentals
- Images as data and OpenCV
- Convolutional networks and vision transformers
-
Data
- Capture and labelling
- Data augmentation
- Imbalanced datasets (few defects)
-
Classification and detection
- Transfer learning for classification
- Object detection with the YOLO family
- Detection metrics
-
Segmentation and anomalies
- Instance segmentation
- Anomaly detection for inspection
-
Documents and images with multimodal models
- OCR and data extraction
- Language models with vision
- When a multimodal model replaces a trained model
-
Deployment
- Inference on servers and at the edge
- Optimisation and export
- Real-time video
-
Privacy and regulation
- Images of people and GDPR
- Biometric uses and the AI Act
Tools you will practise with
- Python
- OpenCV
- PyTorch and torchvision
- Ultralytics YOLO
- Label Studio
- ONNX
Hands-on project
You develop a vision system for an industrial or business case (for example, detecting defects in parts or counting products in an image), from labelling to a deployed model that processes new images.
Requirements
- Fluent Python.
- Machine learning knowledge; deep learning recommended.
Other courses
-
AI for data analysis course (no data science needed)
Draw conclusions from your data with AI, even if you are not a data scientist.
- Duration: 8 hours
- Level: Beginner
-
Deep learning with PyTorch course
Understand and build modern neural networks, from tensors to transformers.
- Duration: 30 hours
- Level: Advanced
-
Demand forecasting and time series course
Anticipate demand, sales or consumption with models you can explain.
- Duration: 16 hours
- Level: Intermediate
Where it is applied
-
AI visual quality inspection
A camera and a computer vision model check every part, pack or label and set aside the defective ones, without tiring at the end of the shift.
Want this course for your team?
We adapt the content, length and format to your company.