Fuji apple dataset for on-tree apple detection and measurment containing 3925 images annotated with modal and amodal segmentation masks and fruit diameter ground truth. This dataset was used to train the deep learning architecture published at https://github.com/GRAP-UdL-AT/Amodal_Fruit_Sizing. The resulting trained model is available by downloading in the file: model_000999.pth This dataset was partly funded by the Spanish Ministry of Science, Innovation and Universities. Grant RTI2018-094222-B-I00 [PAgFRUIT project] by MCIN/AEI/10.13039/501100011033 and by “ERDF, a way of making Europe”, by the European Union.