gnn_microscopy_segment

This repository contains the source code for the publication "Memory Efficient Semantic Segmentation of Large Microscopy Images Using Graph-based Neural Networks". Currently it contains the code required to create graphs, train a Graph Neural Network (GNN), and test a GNN. Trained models for the 3D hiPSC and 2D hESC datasets used in the publication are also included.

Requirements

Pytorch = 1.9.0

Pytorch Geometric = 2.0.3

Numpy >= 1.21.1

Scikit Image >= 0.16.2

Scikit Learn

GPUtils (for GPU usage metrics)