This is a university project.
The project is based on the PyTorch implementation of RNN and CasRNN.
These models are described in the following articles Deep Recurrent Neural Networks for Hyperspectral Image Classification and Cascaded Recurrent Neural Networks for Hyperspectral Image Classification.
The focus of this work is to investigate the influence of hyperparameters. The hyperparameters which yield the best results are used to compare the aforementioned networks in terms of accuracies (overall accuracy, average accuracy, and cohen's kappa) and processing time (training and inference) as well as to produce classification maps.