Windows 10 and YOLOV2 for Object Detection Series
- Introduction to YoloV2 for object detection
- Create a basic Windows10 App and use YoloV2 in the camera for object detection
- Transform YoloV2 output analysis to C# classes and display them in frames
- Resize YoloV2 output to support multiple formats and process and display frames per second
Today’s post is the first one in a series where I’ll explain the steps needed to use YOLO object recognition model in a Windows 10 application. You Only Look Once (YOLO) is a pretty popular model, you only need to check the next trailer ti burn in desire to try the model
This model is a real-time neural network for object detection that detects 20 different classes. It is made up of 9 convolutional layers and 6 max-pooling layers and is a smaller version of the more complex full YOLOv2 network.
Now that we can use ONNX models in Windows 10, we can take advantage of the same. The first thing we must do is convert the model to ONNX format. We can use the ONNX tools, or download the already converted model from the Azure Artificial Intelligence Gallery:
Now we only need Windows 10 and the latest Visual Studio 2017 version. In the Next Post Comment on the steps necessary to use YoloV2 in a Windows App 10.
Greetings @ Burlington
- YOLO: Real-time object detection
- YOLO9000: Better, Faster, Stronger by Joseph Redmon and Ali Farhadi (2016)
- ONNX Tools
- Azure AI Gallery, Tiny YOLO V2