Abstract: Systems or techniques that facilitate hybrid 3D-to-2D slice-wise object localization ensembles are provided. In various embodiments, a system can access at least one three-dimensional voxel array. In various aspects, the system can localize, via execution of a deep learning ensemble, an object depicted in the at least one three-dimensional voxel array. In various instances, the deep learning ensemble can receive as input the at least one three-dimensional voxel array. In various cases, the deep learning ensemble can produce as output a set of two-dimensional object location indicators respectively corresponding to a set of two-dimensional slices of the at least one three-dimensional voxel array.

Abstract: Methods, systems, and computer-readable storage media are provided. A computing device crawls all files and formats for respective data types in a source data path for data to be uploaded or ingested. After the crawling, a number of data volumes of the data types are output. One or more destinations of the data are received by the computing device. A service request for approval including the source data path is received. The computing device converts the number of the data volumes to a number of units of work and estimates a cost of the service request. Approval of the service request by a representative of the requesting entity is received. A user works on the service request after the receiving of the approval of the service request. The service request is marked as resolved upon completion.