Automatic mixed precision and distributed data-parallel training for satellite image classification using CNN
Published in Fifteenth International Conference on Machine Vision (ICMV 2022), 2023
This work proposed the implementation of distributed data parallelism (DDP) and automatic mixed precision (AMP) to minimize the memory usage and optimizing usability of GPUs while improving the accuracy of Artificial Neural Network (ANN) model in classifying earth terrains from satellite images.
In this research, I had collaboration with with 2 professors from Curtin University Sarawak, Malaysia (Dr. Wong Wei Kitt and Dr. Filbert H. Juwono), and also a geospatial data scientist, Gregory Olivierre, from OmegaCrop
Cite as: Nuwara. Y. (2020) Integration of Reservoir, Rock Physics, Seismic, and Geomechanical Modelling for CO2 Injection in Carbonate Reef Reservoir. 82nd EAGE Annual Conference & Exhibition Proceeding. Vol. 2020 p. 1-5.