Pregunta de entrevista de HyperVerge

They asked me to classify a given image dataset into 9 classes using deep learning. Initially, I had to train a model on the labeled dataset, and then use the trained model to predict the labels for an unlabeled dataset. They specifically mentioned using ResNet-18 as the base model for this task. This tested my ability to handle data preprocessing, model training, inference, and proper evaluation—especially for real-world multi-class image classification problems.