import numpy as np import torch import torch.nn as nn import torch.nn.functional as F from torch.optim import SGD import matplotlib.pyplot as plt

training_inputs = torch.tensor(np.load("inputs_training.npy")).float() training_targets = torch.tensor(np.load("targets_training.npy")).float() test_inputs = torch.tensor(np.load("inputs_test.npy")).float() test_targets = torch.tensor(np.load("targets_test.npy")).float()

adj = np.load("adjmat.npy") # first, we get the number of vertices n_vert = adj.shape[0] # D is a diagonal matrix, where the ith diagonal entry is given by the sum of the ith row xor ith column of adj D = np.diag(adj.sum(axis=1)) # sans normalization, we have that L = D - adj