Dataset and Model Weights for: Neural Networks for Predicting Permeability Tensors of 2D Porous Media: Comparison of Convolution- and Transformer-based Architectures

This is the dataset and the corresponding model weight needed to reporduce the results for our paper "Neural Networks for Predicting Permeability Tensors of 2D Porous Media: Comparison of Convolution- and Transformer-based Architectures". With the GitHub Repository put the files in the corresponding folders: - data/ - images.npy - images_filles.npy - train_and_val.npy - test_images.npy - test_images_filled.npy - test_k.npy - models/ - ConvNeXtTiny_500_epochs.pth - ConvNeXtSmall_400_epochs.pth - ResNet50_500_epochs.pth - ResNet101_400_epochs.pth - ViT_S16.pth - ViT-T16.pth - results/ - all_models_similarity_filled.npz