def main(argv):
# config the CPU/GPU in TF, assume only one GPU is in use.
# For multi-gpu setting, please refer to
# https://www.tensorflow.org/guide/gpu#using_multiple_gpus
gpus = tf.config.experimental.list_physical_devices('GPU')
if len(gpus) == 0 or FLAGS.gpu_id is None:
device_id = "/device:CPU:0"
else:
tf.config.experimental.set_visible_devices(gpus[FLAGS.gpu_id], 'GPU')
device_id = '/device:GPU:0'
A_mat, X_mat, z_vec, train_idx, val_idx, test_idx = load_data_planetoid(
FLAGS.dataset)
An_mat = preprocess_graph(A_mat)
# N = A_mat.shape[0]
K = z_vec.max() + 1
with tf.device(device_id):
gcn = GCN(An_mat, X_mat, [FLAGS.hidden1, K])
gcn.train(train_idx, z_vec[train_idx], val_idx, z_vec[val_idx])
test_res = gcn.evaluate(test_idx, z_vec[test_idx], training=False)
# gcn = GCN(An_mat_diag, X_mat_stack, [FLAGS.hidden1, K])
# gcn.train(train_idx_recal, z_vec[train_idx], val_idx_recal, z_vec[val_idx])
# test_res = gcn.evaluate(test_idx_recal, z_vec[test_idx], training=False)
print("Dataset {}".format(FLAGS.dataset),
"Test loss {:.4f}".format(test_res[0]),
"test acc {:.4f}".format(test_res[1]))
with open("fixed_lapl.pkl", "rb") as pkl:
fxd = pickle.load(pkl)
plt.figure()
smooth_plot(fxd['train_losses'], label='Fixed Train Loss')
smooth_plot(lrnd['train_losses'], label='Learned Train Loss')
smooth_plot(fxd['val_losses'], fmt="-.", label='Fixed Val Loss')
smooth_plot(lrnd['val_losses'], fmt="-.", label='Learned Val Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.title('Loss Cora')
plt.legend()
plt.figure()
smooth_plot(fxd['train_accuracies'], label='Fixed Train Accuracy')
smooth_plot(lrnd['train_accuracies'], label='Learned Train Accuracy')
smooth_plot(fxd['val_accuracies'], fmt="-.", label='Fixed Val Accuracy')
smooth_plot(lrnd['val_accuracies'], fmt="-.", label='Learned Val Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.title('Accuracy Cora')
plt.legend()
test_res = gcn.evaluate(test_idx, z_vec[test_idx], training=False)
# gcn = GCN(An_mat_diag, X_mat_stack, [FLAGS.hidden1, K])
# gcn.train(train_idx_recal, z_vec[train_idx], val_idx_recal, z_vec[val_idx])
# test_res = gcn.evaluate(test_idx_recal, z_vec[test_idx], training=False)
print("Dataset {}".format(FLAGS.dataset),
"Test loss {:.4f}".format(test_res[0]),
"test acc {:.4f}".format(test_res[1]))