Skip to content

Development of segmentation and regression deep learning models for ABoVE Shrubs project

License

Notifications You must be signed in to change notification settings

nasa-nccs-hpda/above-shrubs.pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ABoVE-Shrubs Pytorch Project

The main objective of this work is to test different foundation model programs for the modeling of canopy heights and land cover segmentation.

Getting Started

  1. SSH to ADAPT Login
ssh adaptlogin.nccs.nasa.gov
  1. SSH to GPU Login
ssh gpulogin1
  1. Clone above-shrubs repository

Clone the github

git clone https://github.com/nasa-nccs-hpda/above-shrubs.pytorch

Dependencies

singularity build --sandbox above-shrubs.pytorch docker://nasanccs/above-shrubs.pytorch:latest

Setup step

In this step we select the data from a pool of GeoTIFFs and convert them to NumPy files for faster training and easier storage.

singularity exec --env PYTHONPATH="/explore/nobackup/people/jacaraba/development/above-shrubs.pytorch" --nv -B $NOBACKUP,/explore/nobackup/people,/explore/nobackup/projects /lscratch/jacaraba/container/above-shrubs.pytorch python /explore/nobackup/people/jacaraba/development/above-shrubs.pytorch/above_shrubs/view/chm_pipeline_cli.py --config-file /explore/nobackup/people/jacaraba/development/above-shrubs.pytorch/projects/chm/configs/above_shrubs_chm.yaml --step setup

Authors

About

Development of segmentation and regression deep learning models for ABoVE Shrubs project

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published