Skip to content

Seismic Facies Classification with the UNET Architecture (Deep Learning).

Notifications You must be signed in to change notification settings

marxprop/SEAM-AI-GPU-Hackathon

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

SEAM-AI-GPU-Hackathon

This repository contains the Rocky-AI teams first place Test 2 and third place Test 1 solution to the Parihaka Seismic Facies Identification Challenge in the SEAM/NVIDIA Applied Geoscience GPU Hackathon. The goal was a six-way classification of the Parihaka 3D seismic survey, with emphasis on interface and key facies. The U-Net architecture of the EfficientNet-B0 pretrained network with Pytorch was used which achieved 95% test accuracy in the validation test.

Image 1110x588 Image 117088566 1118x590

About

Seismic Facies Classification with the UNET Architecture (Deep Learning).

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •