def test_delaunay():
adj, nf, labels = delaunay.generate_data('numpy')
correctly_padded(adj, nf, None)
assert adj.shape[0] == labels.shape[0]
# Test that it doesn't crash
delaunay.generate_data('networkx')
def test_delaunay():
adj, nf, labels = delaunay.generate_data(return_type='numpy',
classes=[0, 1, 2])
correctly_padded(adj, nf, None)
assert adj.shape[0] == labels.shape[0]
# Test that it doesn't crash
delaunay.generate_data(return_type='networkx')
from keras.callbacks import EarlyStopping from keras.layers import Input, Dense from keras.models import Model from keras.optimizers import Adam from keras.regularizers import l2 from sklearn.model_selection import train_test_split from spektral.datasets import delaunay from spektral.layers import GraphConv, GlobalAttentionPool from spektral.utils import localpooling_filter from spektral.utils.logging import init_logging # Load data adj, x, y = delaunay.generate_data(return_type='numpy', classes=[0, 5]) # Parameters N = x.shape[-2] # Number of nodes in the graphs F = x.shape[-1] # Original feature dimensionality n_classes = y.shape[-1] # Number of classes l2_reg = 5e-4 # Regularization rate for l2 learning_rate = 1e-3 # Learning rate for Adam epochs = 200 # Number of training epochs batch_size = 32 # Batch size es_patience = 10 # Patience fot early stopping log_dir = init_logging() # Create log directory and file # Preprocessing fltr = localpooling_filter(adj.copy()) # Train/test split fltr_train, fltr_test, \