Teaching machines to see: from pixels to object detection.
Python
PyTorch
OpenCVAn image is a table of numbers, and computer vision is the craft of pulling meaning out of it. Start with pixels and convolution filters — slide the kernel and watch edges appear — then image classification with CNNs, transfer learning, object detection, segmentation and vision transformers.
Read a free lesson: How Computers See ImagesEvery module and lesson in this track. Lessons marked free are open to everyone; the rest open once you own the track.
Every lesson in this track, with summariesImages as numbers, convolution as a sliding weighted sum, and why a CNN learns its own filters.
Building a CNN in PyTorch, transfer learning from pretrained models, and evaluating a classifier honestly.
Bounding boxes, IoU, one-stage detectors like YOLO, and how to read mAP.
Classification per pixel: semantic and instance segmentation, U-Net, and general segmentation models.
ViT, CLIP and vision-language models — when images and text share one embedding space.
Models on edge and mobile devices, real-time camera latency, and a capstone project.
The real one, from a lesson — it runs in your browser. No account needed.
This track is part of a larger path. Buy the whole path as a bundle and every track in it costs 40% less.
