Predicting Objects in the Image

YOLO v2 uses anchor boxes to detect classes of objects in an image. For more details, seeAnchor Boxes for Object Detection.The YOLO v2 predicts these three attributes for each anchor box:

The figure shows predefined anchor boxes (the dotted lines) at each location in a feature map and the refined location after offsets are applied. Matched boxes with a class are in color.

Transfer Learning

With transfer learning, you can use a pretrained CNN as the feature extractor in a YOLO v2 detection network. Use theyolov2Layersfunction to create a YOLO v2 detection network from any pretrained CNN, for exampleMobileNet v2. For a list of pretrained CNNs, seePretrained Deep Neural Networks(Deep Learning Toolbox)

You can also design a custom model based on a pretrained image classification CNN. For more details, seeDesign a YOLO v2 Detection Network.

Design a YOLO v2 Detection Network

You can design a custom YOLO v2 model layer by layer. The model starts with a feature extractor network, which can be initialized from a pretrained CNN or trained from scratch. The detection subnetwork contains a series ofConv,Batch norm, andReLulayers, followed by the transform and output layers,yolov2TransformLayerandyolov2OutputLayerobjects, respectively.yolov2TransformLayertransforms the raw CNN output into a form required to produce object detections.yolov2OutputLayerdefines the anchor box parameters and implements the loss function used to train the detector.

You can also use theDeep Network Designer(Deep Learning Toolbox)app to manually create a network. The designer incorporates Computer Vision Toolbox™ YOLO v2 features.

Train an Object Detector and Detect Objects with a YOLO v2 Model

To learn how to train an object detector by using the YOLO deep learning technique with a CNN, see theObject Detection Using YOLO v2 Deep Learningexample.

Code Generation

To learn how to generate CUDA^®code using the YOLO v2 object detector (created using theyolov2ObjectDetectorobject) seeCode Generation for Object Detection by Using YOLO v2.

Label Training Data for Deep Learning

You can use theImage Labeler,Video Labeler, orGround Truth Labeler(Automated Driving Toolbox)apps to interactively label pixels and export label data for training. The apps can also be used to label rectangular regions of interest (ROIs) for object detection, scene labels for image classification, and pixels for semantic segmentation. To create training data from any of the labelers exported ground truth object, you can use theobjectDetectorTrainingDataorpixelLabelTrainingDatafunctions. For more details, seeTraining Data for Object Detection and Semantic Segmentation.