Please note, that the classification approach shown here is legacy from HALCON 19.11 on. With HALCON 19.11, classification is done using the same operators and workflow as the deep learning methods object detection and semantic segmentation. Get more information here.
In this video, you learn how to train a deep-learning-based classifier that can be used to classify objects and defects with MVTec HALCON 18.05. Using the preprocessed image data from the first tutorial, you learn about splitting the data into training, validation and test subsets. Then, we check out different parameters that influence the training, like the batch size and the learning rate.
You can download the HDevelop example used in this video below.