← All tutorials
Skill Zuno · skillzunos.com · AI
Computer Vision tutorial
Learn Computer Vision on Skill Zuno. This Computer Vision tutorial covers New, Easy, Medium, Hard, and Diff levels so you can study practical Computer Vision problems on skillzunos.com.
Open Computer Vision on Skill ZunoAlso see the Computer Vision interview questions.
Computer vision is the field of AI that lets machines understand images and video. Core tasks include image classification, object detection, segmentation, tracking and image generation, built today on CNNs and vision transformers. Interviews cover these tasks and their metrics, detectors such as YOLO, data augmentation, vision transformers and libraries such as OpenCV and torchvision.
Computer Vision topics covered
- Image basics and preprocessing — Pixels, channels, colour spaces, resizing and normalisation with OpenCV.
- Image classification — Training CNNs and vision transformers to label whole images.
- Object detection — Bounding boxes, YOLO and two-stage detectors, IoU and non-max suppression.
- Segmentation — Semantic, instance and panoptic segmentation, U-Net and Segment Anything.
- Data augmentation — Flips, crops, colour jitter, mixup and other ways to stretch limited data.
- Vision transformers — Treating image patches as tokens, and models such as ViT and CLIP.
What you can learn
- Computer Vision tutorial for beginners and experienced developers
- Level-based practice: New, Easy, Medium, Hard, and Diff
- AI topics alongside Computer Vision on skillzunos.com