Cloudmask

MLCommons Science Cloudmask benchmark

The scientific objective of CloudMask is to develop a segmentation model for classifying the pixels in satellite images. This classification allows to determine whether the given pixel belongs to a cloud or to a clear sky. The benchmark can be considered as both training and inference focused, where the science metric is same as the classification accuracy — number of pixels classified correctly. The performance metric, can be inference timing and scalability on the training across a number of GPUs.

Participants and Collaborators

• Gregor von Laszewski laszewski@gmail.com
• Sergey Samsonau ss13638@nyu.edu
• Varshitha Chennamsetti vc2209@nyu.edu
• Ruochen Gu rg3515@nyu.edu
• Laiba Mehnaz lm4428@nyu.edu
• Shengyao Tang st4761@nyu.edu

Deliverables

• Working code that can run benchmarks in parallel
• Report
• Submission of the benchmark to MLCommons

References

1. https://github.com/mlcommons/science/tree/main/benchmarks/cloudmask