作者: Allan Hanbury , Henning Müller , Georg Langs , Bjoern H. Menze
DOI: 10.1007/978-3-642-38082-2_9
关键词:
摘要: The VISCERAL project is building a cloud-based evaluation framework for evaluating machine learning and information retrieval algorithms on large amounts of data. Instead downloading data running evaluations locally, the will be centrally available cloud to evaluated programmed in computing instances cloud, effectively bringing This approach allows performed Terabytes without needing consider logistics moving or storing local infrastructure. After discussing challenges benchmarking big data, design system presented, concentrating components coordinating participants benchmark managing ground truth creation. first two benchmarks run segmentation 3D medical images.