def improve_prediction_model(self, epochs=5):
# Load Data Set
print("Loading data set.")
X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_practice_dataset(
)
# Show some images (optional of course : ) )
# show_some_images(X_train_orig, X_test_orig)
test_model = DeepNeuralNetwork(X_train_orig, Y_train_orig, X_test_orig,
Y_test_orig, classes)
for i in range(epochs):
parameters, accuracies = test_model.train(num_epochs=epochs,
print_cost=True)
new_model = PredictionModel(parameters, accuracies)
if new_model > self:
print(
"\n\tNew model is better... Displaying accuracies and updating files.. "
)
self = new_model
print(self)
self.save_model()
else:
print("Previous model is superior or equivalent.")
print(self)
def main():
# Load Data Set
print("Loading practice data set.")
X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_practice_dataset()
# Show some images (optional of course : ) )
# show_some_images(X_train_orig, X_test_orig)
test_model = DeepNeuralNetwork(X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes)
for i in range(5):
parameters, accuracies = test_model.train(num_epochs = 1500, print_cost = True)
new_model = PredictionModel(parameters, accuracies)
parameters, accuracies = load_model()
previous_model = PredictionModel(parameters, accuracies)
if new_model > previous_model :
print("\n\tNew model is better... Displaying accuracies and updating files.. ")
print(new_model)
save_model(new_model.parameters, new_model.accuracies)
else:
print("Previous model is superior.")
parameters, accuracies = load_model()
best_model = PredictionModel(parameters, accuracies)
print(best_model)
def test_query():
layers = [28 * 28, 100, 10]
learning_rate = 0.2
dnn = DeepNeuralNetwork(layers, learning_rate)
training_data_list = dataset.get_data_list(
"mnist_dataset/mnist_train_100.csv")
for record in training_data_list[0:4]:
label, inputs = dataset.get_scaled_data(record)
targets = dataset.get_targets_data(layers[-1], label)
outputs = dnn.layer_query(inputs, targets)
def test_dnn():
layers = [28 * 28, 200, 100, 50, 10]
learning_rate = 0.2
dnn = DeepNeuralNetwork(layers, learning_rate)
# 开始测试训练
print("start to train")
# 训练方法1：用数据训练，采用较小的训练数据集
training_data_list = dataset.get_data_list(
"mnist_dataset/mnist_train.csv")[:] # 测试全部数据
size = len(training_data_list) # 用于打印进度
for index, record in enumerate(training_data_list):
label, inputs = dataset.get_scaled_data(record)
targets = dataset.get_targets_data(layers[-1], label)
dnn.layer_train(inputs, targets)
# 打印进度
print_process(index, size)
# 开始测试
print("start to test")
test_data_list = dataset.get_data_list(
"mnist_dataset/mnist_test.csv")
scorecard = [] # 记分牌，保存每个测试数据的测试结果
right = 0 # 正确总数
size = len(test_data_list) # 用于打印进度
for index, record in enumerate(test_data_list):
label, inputs = dataset.get_scaled_data(record)
result = dnn.layer_query_result(inputs)
# 对比神经网络预测结果和标签
if label == result:
scorecard.append(1)
right += 1
else:
scorecard.append(0)
# 打印进度
print_process(index, size)
# 打印正确率
print("right rate=", right / len(test_data_list) * 100, "%")
pass
def test_kdd_CICIDS():
# 设置初始化参数，采用的是mnist数据集，为28*28的手写数字图像，隐含层100，输出层10代表0~9的数字，学习率初始设为0.2
layers = [78, 40, 2]
learning_rate = 0.5
n = DeepNeuralNetwork(layers, learning_rate)
# labels_count = [0, 0, 0, 0, 0]
# 第一步：开始训练
print("start to train")
train = True
if train is True:
# 训练方法1：用数据训练，采用较小的训练数据集
_, training_data_list = dataset.get_kdd_CICIDS_data(
"kdd/Friday-WorkingHours-Afternoon-DDos.pcap_ISCX.csv")
training_data_list = random.sample(training_data_list,
int(0.1 * len(training_data_list)))
# training_data_list = dataset.get_data_list(
# "kdd/KDDTest-21-normalization.txt.csv")
size = len(training_data_list) # 用于打印进度
for index, record in enumerate(training_data_list):
label, inputs = get_kdd_data_CICIDS(record)
targets = numpy.zeros(layers[-1]) + 0.01
targets[label] = 0.99
# targets = numpy.zeros(output_nodes)
# targets[label] = 1
n.layer_train(inputs, targets)
# 打印进度
print_process(index, size)
# 统计标签数
# labels_count[label] += 1
else:
print("load data done")
# 训练方法2：直接导入训练的结果（适用于已经有训练结果，即权值矩阵）
n.load("w_input_hidden_kdd.txt", "w_hidden_output_kdd.txt")
# 第二步：开始测试训练后的神经网络
print("start to test")
_, test_data_list = dataset.get_kdd_CICIDS_data(
"kdd/Monday-WorkingHours.pcap_ISCX.csv")
test_data_list = random.sample(test_data_list,
int(0.1 * len(test_data_list)))
# test_data_list = dataset.get_data_list(
# "kdd/KDDTrain+_22Percent-normalization.txt.csv")
scorecard = [] # 记分牌，保存每个测试数据的测试结果
right = 0 # 正确总数
count = 0 # 用于打印进度
size = len(test_data_list) # 用于打印进度
for index, record in enumerate(test_data_list):
label, inputs = get_kdd_data_CICIDS(record)
result = n.layer_query_result(inputs)
# 对比神经网络预测结果和标签
if label == result:
scorecard.append(1)
right += 1
else:
scorecard.append(0)
# 打印进度
print_process(index, size)
# print(labels_count)
# 打印正确率
print("right rate=", right / len(test_data_list) * 100, "%")