ABSTRACT
This chapter presents an object detection case study problem using deep learning. It uses an open-source car dataset to detect or identify cars on the streets. A deep learning model is trained on this dataset for correctly detecting cars from images. The chapter covers some fundamental aspects of deep learning training in a practical scenario, such as setting default configurations (batch size, learning rate, or the number of training epochs, etc.) and defining the dataset class and its attributes to structure and handle the dataset effectively. The chapter discusses variations of the case study problem for using different hyperparameters, learning schedulers, and pre-trained models. The trained object detection model is also tested using outside images for inference in the context of real-world applications.
