YOLO
YOLO is a family of single-stage object-detection models that predict object classes and locations directly from an image in one inference pass.
Deep Learning with R, Third Edition
You Only Look Once is a family of single-stage object detection models that predict object locations and categories in a single network evaluation.
- How it is used
- Locates and classifies objects in images in one step, particularly where real-time detection matters.
- How deep it goes
- Builds and trains a simplified original-style detector, including grid targets and custom loss; uses one box per cell rather than the original multiple boxes.
- Examples
- Uses COCO images, a pretrained ResNet backbone, R/Keras prediction code, and visualized boxes with a confidence cutoff.
- What you can do after
- Build it from scratch as a simplified YOLO detector using R/Keras, COCO grid targets, and a custom box loss.
Read how Deep Learning with R, Third Edition explains YOLO →
Deep Learning with Python, Third Edition
A family of single-stage object-detection models that predict bounding boxes and classes directly from an image in one forward pass.
- How it is used
- Deploys object detection when predicting locations and labels efficiently in one step matters.
- How deep it goes
- Explains grid outputs, confidence, backbone choice, preprocessing, and a prediction head, but not complete training losses or inference postprocessing.
- Examples
- Uses COCO images, normalized annotations, a 6 × 6 grid, 91 classes, and a Keras prediction-head implementation.
- What you can do after
- Build it from scratch with Keras and KerasHub by attaching a YOLO-style head to a pretrained ResNet backbone.
Read how Deep Learning with Python, Third Edition explains YOLO →
Machine Learning Platform Engineering
YOLO is a family of real-time object-detection models that predict object classes and locations from an image in a single inference pass.
- How it is used
- Deploys object detection within reproducible Kubeflow and ML pipeline workflows.
- How deep it goes
- Explains dataset setup, training, evaluation, and pipeline integration, but leaves model internals and customization details largely open.
- Examples
- Uses an ID card detector with labeled image splits and a Kubeflow pipeline.
- What you can do after
- Apply YOLO through Ultralytics to configure datasets, train an object detector, and evaluate it inside a modular pipeline.
Read how Machine Learning Platform Engineering explains YOLO →
Related concepts
- single-stage detectorkind of · An object-detection architecture that predicts object locations and class labels directly in one integrated model pass without a separate region-proposal stage.
- object detection modelkind of · An object detection model is a computer-vision model that identifies object instances and predicts their classes and spatial locations in visual data.
- bounding boxuses · A bounding box is an axis-aligned rectangular or hyperrectangular region defined by coordinate limits that encloses or localizes an object, area, or set of points.
- foundational modeluses · A base or foundation model is a pretrained model that provides learned parameters or capabilities as a starting point for reuse or adaptation to downstream tasks.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.