experiments = experiments[400:]
print("{} experiments about to run.".format(len(experiments)))
for experiment in experiments:
augment, batch_size, keep_prob, filters, ksize, config = experiment
start_time = time.time()
network = NN(epochs=5, batch_size=batch_size, learning_rate=0.001)
features = np.concatenate([X_train, aug_X
]) if augment == 'True' else X_train
labels = np.concatenate([y_train, aug_y]) if augment == 'True' else y_train
network.add_train_data(features, labels)
network.add_test_data(X_test, y_test)
network.add_validation_data(X_valid, y_valid)
network.add_configuration(create_network_config(config, filters, ksize),
input_size=input_size)
network.build(num_labels=num_labels)
print(
"Training model with hyperparameters: augmented: {}, batch_size: {}, keep_prob: {}, filters: {}, ksize: {}, config: {}"
.format(augment, batch_size, keep_prob, filters, ksize,
network.get_string()))
validation_accuracy = network.train(keep_prob=keep_prob)
end_time = time.time()
stat_values = [
end_time - start_time, validation_accuracy, augment, batch_size,
keep_prob, filters, ksize,
network.get_string()
]
{ 'type': 'relu' },
{ 'type': 'flatten' },
{ 'type': 'fc', 'units': 128 },
{ 'type': 'dropout' },
{ 'type': 'relu' },
{ 'type': 'fc', 'units': 43 }
]
start_time = time.time()
network = NN(epochs=50, batch_size=int(batch_size), learning_rate=0.001)
features = np.concatenate([X_train, aug_X]) if augment == 'True' else X_train
labels = np.concatenate([y_train, aug_y]) if augment == 'True' else y_train
network.add_train_data(features, labels)
network.add_test_data(X_test, y_test)
network.add_validation_data(X_valid, y_valid)
network.add_configuration(architecture, input_size=input_size)
network.build(num_labels=num_labels)
validation_accuracy = network.train(keep_prob=keep_prob, save_name="test" + str(idx))
end_time = time.time()
test_accuracy = network.test(save_name="test" + str(idx))
try:
stats = pd.read_csv('top_5_stats.csv')
except:
stats = pd.DataFrame()
stat_values = [end_time - start_time, validation_accuracy, test_accuracy, augment, filters, ksize, batch_size, keep_prob, architecture_name]
stat_entry = pd.Series(stat_values, index=stat_labels)
