return eer
if __name__ == '__main__':
# Determine path to configuration file. This path manipulation is
# here so that the script will run successfully regardless of the
# current working directory.
local_dir = os.path.dirname(__file__)
config_path = os.path.join(local_dir, 'neat.cfg')
train_loader = ASVDatasetshort(None, do_lfcc=True, index_list=index_train,
do_standardize=True)
test_loader = ASVDataset(None, is_train=False, is_eval=False, index_list=index_test,
do_lfcc=True, do_standardize=True)
winner, config, stats = run(config_path, n_generation, train_loader, spoofed_class)
make_visualize(winner, config, stats)
winner_net = neat.nn.RecurrentNetwork.create(winner, config)
train_eer = evaluate(winner_net, train_loader)
eer = evaluate(winner_net, test_loader)
print("\n")
print("**** training equal error rate = {} ****".format(train_eer))
print("\n")
print("**** equal error rate = {} ****".format(eer))
pickle.dump(winner, open('best_genome_eoc_class_2_lfcc', 'wb'))
use_gate=USE_GATE,
loading_bar=False)
dev_eer_list.append(eer)
dev_accuracy_list.append(accuracy)
eer, accuracy = evaluate_eer_acc(winner,
config,
evalloader,
backprop=backprop,
use_gate=USE_GATE,
loading_bar=False)
eval_eer_list.append(eer)
eval_accuracy_list.append(accuracy)
if i == 0:
make_visualize(winner, config, stats, topology=False)
print("\n")
print("DEV equal error rate", dev_eer_list)
print("accuracy", dev_accuracy_list)
print("\n")
array_eer = np.array(dev_eer_list)
print("DEV EER stats")
print("min =", array_eer.min())
print("max =", array_eer.max())
print("median =", np.median(array_eer))
print("average =", array_eer.mean())
print("std =", array_eer.std())