YOLO and Detection Basics
17 articles
Anchor-Free vs Anchor-Based Object Detectors
Anchor-free vs anchor-based detectors: what anchors are, why newer YOLO versions dropped them, and what the change means for training and deployment.
Nano, Small, Medium: How to Choose a YOLO Model Size
Choosing a YOLO model size and input resolution: a method that starts from your hardware budget and accuracy needs, not a guess at nano, small or medium.
Classification vs Detection vs Segmentation: Pick the Right Task
Classification vs detection vs segmentation: how to choose the right task for your project, with a decision guide, cost trade-offs and examples.
Comparing Two Detectors Fairly
Before calling one detector better, hold data, settings and training budget equal, and check the gap is larger than test-set and seed noise.
Confidence Thresholds: Tuning a Detector to Cut False Alarms
Tuning a confidence threshold for a detector: read the precision-recall curve, tune per class, and cut false alarms without missing real events.
Why a Detector's Confidence Is Not a Probability
A box scored 0.8 is not right 80% of the time. What confidence scores are, why they shift between models and classes, and what that means for thresholds.
Input Resolution or Model Size: Which to Increase for Small Objects
When a detector misses small objects, a bigger model and a bigger input both cost compute. Why input size usually helps more, and when it does not.
IoU and Non-Maximum Suppression, Explained with Examples
Intersection over Union and non-maximum suppression explained step by step, with worked examples, code, and typical threshold choices for detectors.
mAP, Precision and Recall: How to Read Detection Results
Learn how to read precision, recall, mAP50 and mAP50-95 in object detection results, and which metric matters most for your own use case and camera setup.
Single-Class or Multi-Class: When to Merge or Split Detection Classes
Should car, van and truck be one class or three? How to decide a detector's classes, and why labelling fine and training coarse keeps options open.
Preprocessing Mismatches That Silently Cost Accuracy
A model only works on inputs prepared the way it was trained. Resize method, colour order, normalisation and padding mismatches, and how to catch them.
What Is YOLO? Object Detection Explained Without the Math
What is YOLO? A plain explanation of how it finds objects in a single pass, what its output means, and where it fits in a project.
What mAP Hides: Seven Things a Single Score Won't Tell You
mAP is a useful summary, but it hides the operating threshold, object size, error types and how the number was computed. Here is what to check next to it.
YOLO Licenses Explained: AGPL, GPL and Commercial Use
YOLO licenses explained: what AGPL-3.0 and GPL-3.0 mean for YOLO projects, options for commercial products and safe habits. Not legal advice.
YOLO27 Announced: What to Check Before You Switch
Ultralytics announced YOLO27 in September 2026. What was actually said, what is still unknown, and how to evaluate it on your own data when it ships.
YOLOv5 vs YOLOv8 vs YOLO11: Which Should You Use?
YOLOv5 vs YOLOv8 vs YOLO11 compared in practice: workflow, accuracy and speed trade-offs, export support and licence, plus a simple way to decide.
How YOLOv7 Gets Real-Time Speed with Re-parameterization
How YOLOv7 uses re-parameterization: training-time and inference-time structure, how layers merge, and what it means when you export and deploy the model.