def train_model_mnist(single_model, is_verify=False):
############################################################################
# FUNCTION DESCRIPTION: main function to train MNIST dataset
############################################################################
file = MAIN_FILE
global INDEX_MODEL
is_complete_model = check_complete_model(single_model)
if not is_complete_model:
single_model = get_latest_model_list(single_model, file)
model_name = single_model[0]
cur_model_num = get_current_model_number(model_name)
INDEX_MODEL = get_new_model_number(cur_model_num)
temp_single_model = make_data_global(single_model)
mnist, train_data, train_labels, eval_data, eval_labels = load_data_mnist()
mnist_classifier = implement_cnn(is_verify)
logging_hook = set_up_logging()
train_the_model(mnist_classifier, train_data, train_labels, logging_hook)
eval_results = evaluate_model(mnist_classifier, eval_data, eval_labels)
print(eval_results)
if not is_verify:
save_trained_model_in_csv(file, temp_single_model, eval_results)
print(temp_single_model)
reset_global_data()
INDEX_MODEL += 1
return eval_results['accuracy']
def train(single_model):
file = MAIN_FILE
global model_index
is_complete_model = check_complete_model(single_model)
if not is_complete_model:
single_model = get_latest_model_list(single_model, file)
model_name = single_model[0]
cur_model_num = get_current_model_number(model_name)
model_index = get_new_model_number(cur_model_num)
print("________________ single_model: ", single_model)
temp_single_model = make_data_global(single_model)
mnist, train_data, train_labels, eval_data, eval_labels = load_data_mnist()
mnist_classifier = implement_cnn()
logging_hook = set_up_logging()
train_the_model(mnist_classifier, train_data, train_labels, logging_hook)
eval_results = evaluate_model(mnist_classifier, eval_data, eval_labels)
print(eval_results)
file_name = "fixed_model_dict.csv"
save_to_file(temp_single_model, file_name, eval_results)
print(temp_single_model)
reset_global_data()
model_index += 1
return eval_results['accuracy']
def train_model_cifar10( single_model, is_verify = False):
############################################################################
# FUNCTION DESCRIPTION: main function to train CIFAR-10 dataset
############################################################################
file = MAIN_FILE
is_complete_model = check_complete_model(single_model)
if not is_complete_model:
single_model = get_latest_model_list(single_model,file)
model_name = single_model[0]
cur_model_num = get_current_model_number(model_name)
model_index = get_new_model_number(cur_model_num)
print("single_model: ",single_model)
(x_train, y_train), (x_test, y_test) = load_data_cifar10()
y_train, y_test = convert_class_vec2matrix(y_train,y_test)
model = Sequential()
tmp_single_model = get_topology_only(single_model)
num_layer = count_model_layer(tmp_single_model)
model = cnn_model_fn(model,num_layer,single_model)
# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)
# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
x_train, x_test = format_data(x_train,x_test)
if not DATA_AUGMENTATION:
no_data_augmentation(model,x_train,x_test,y_train,y_test)
else:
data_augmentation(model,x_train,x_test,y_train,y_test)
if not is_verify:
save_model_keras_cifar10(model,single_model)
# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
loss = scores[0]
accuracy = scores[1]
print("Model ", single_model)
if not is_verify:
save_trained_model_in_csv(file,single_model,scores)
print('\n')
clear_session()
return accuracy
def train_model_svhn(single_model):
file = MAIN_FILE_SVHN
is_complete_model = check_complete_model(single_model)
if not is_complete_model:
single_model = get_latest_model_list(single_model, file)
print("single_model: ", single_model)
# (x_train, y_train), (x_test, y_test) = load_data_cifar10()
# y_train, y_test = convert_class_vec2matrix(y_train,y_test)
x_train, y_train, x_test, y_test = load_data_svhn()
model = Sequential()
tmp_single_model = get_topology_only(single_model)
num_layer = count_model_layer(tmp_single_model)
model = cnn_model_fn(model, num_layer, single_model)
# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)
# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
# x_train, x_test = format_data(x_train,x_test)
if not data_augmentation:
no_data_augmentation(model, x_train, x_test, y_train, y_test)
else:
data_augmentation(model, x_train, x_test, y_train, y_test)
save_model_keras_svhn(model, single_model)
# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])
loss = scores[0]
accuracy = scores[1]
print("Model ", single_model[:-2])
file_name = MAIN_FILE_SVHN
save_trained_model_in_csv(file_name, single_model, scores)
print('\n')
clear_session()
return accuracy