Skin Lesions Dataset for 2-Class Object Segmentation (YOLO annotation)

This dataset contains images used in the monograph titled Computer Vision in Python. Practical Applications of Deep Learning (Computer vision w Pythonie. Praktyczne zastosowania uczenia głębokiego) to build the yolo11n-seg model. The full collection consists of 1150 image files showing 2 classes of objects: Melanoma Invasive and Nevus. Moreover, the dataset contains 150 images of healthy skin serving as background images. The dataset was randomly divided into a training set (60% of the full dataset) and validation and test sets (20% each). As a result, the training part contains 700 files, validation and test parts - 225. Images were annotated with polygons in the YOLO format, according to which the description of each file is contained in an TXT file with the same name. The dataset can be used to build other models for skin lesion segmentation.