You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Jupyter notebooks used to train and apply a mask R-cnn model to classify live maerl in imagery of the sea-bed obtained from drop-down cameras.
Originally based on https://github.com/matterport/Mask_RCNN Also see this repo for more examples (in samples folder) and explanation of config parameters.
Platform used in this instance : JupyterLab on MAGEOHub (massive online GPU for Earth Observation at Plymouth Marine Lab).
This is a binary classification of live maerl/ not live maerl.
Released under open government licence http://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/
Many thanks to Dan Simms (University of Cranfield) for code examples and Stephen Goult & Dan Clewley (Plymouth Marine Laboratory/ NEODAAS) for troubleshooting suggestions and use of MAGEO.