Computer Vision Masterclass

A 6-term, fully professional path to becoming a computer vision specialist: from digital image processing and OpenCV to convolutional neural networks (CNN), YOLO algorithms, vision transformers (ViT), video processing systems and generative AI.

What skills will this course give you?

  • Mastering fundamental image processing algorithms and techniques with OpenCV and NumPy
  • Designing and training convolutional neural networks (CNN) for image classification in PyTorch
  • Implementing real-time object detection and tracking systems with the YOLO and DeepSORT algorithm families
  • Image segmentation with U-Net and Mask R-CNN networks for medical and industrial uses
  • Mastering modern Vision Transformer (ViT) architectures and multimodal models such as CLIP
  • Deploying computer vision projects on edge hardware (Edge AI) and optimizing speed with TensorRT

How classes run and are supported

This course runs both in person, in a fully equipped space, and online (live). Each student also gets a dedicated project mentor who provides support whenever issues come up.