Dataset used to train a Convolutional Neural Network dedicated to skin pore detection and classification

This data note pertains to the dataset used during the training of a neural network dedicated to the classification of facial skin based on pore condition. The dataset comprises a total of 3086 images categorized into 5 folders, thereby defining a total of 5 classes for facial skin categorization. The folders are labeled as numbers: 1, 2, 3, 4, and 5, corresponding to the categories of facial skin: very good, good, normal, poor, very poor. All images are in "jpg" format with a resolution of 224x224 pixels. On the this way prepared dataset, without any additional processing, is accepted as input by functions from the Keras library within the TensorFlow development environment.