This repository contains a comprehensive set of data designed for training and testing deep learning algorithms in plant species identification and abundance estimation. The material is structured as follows: "Image_Dataset" Folder: This main folder contains all data subsets and relevant documentation for the project. "TrainDataset" Folder: "Original_Images": A collection of original drone photographs used to derivate the training data. "Segmented_Labelled_Images": Contains segmented and labelled portions of the original images, serving as the training set for the deep learning algorithm. "TestDataset" Folder: Includes images from various study areas used as the test set to evaluate the effectiveness and accuracy of the trained algorithm in real-world scenarios. "Expert_Plant_Abundance_Estimates.xlsx": An Excel file with expert botanical estimations of plant species abundance related to the test images. These detailed estimates are crucial for validating the algorithm's performance in species identification and abundance estimation.