수치입력 이진분류모델 레시피 (깊은 다층퍼셉트론 신경망 모델)

# 1. 사용할 패키지 불러오기

import numpy as np
import random
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense

%matplotlib inline

# 2. 데이터 생성하기
x_train = np.random.random((1000, 12))
y_train = np.random.randint(2, size = (1000, 1))
x_test = np.random.random((100, 12))
y_test = np.random.randint(2, size = (100, 1))

# 3. 모델 구성하기
model = Sequential()
model.add(Dense(input_dim = 12, output_dim = 64, activation = "relu"))
model.add(Dense(input_dim = 64, output_dim = 64, activation = "relu"))
model.add(Dense(input_dim = 64, output_dim = 1, activation = "sigmoid"))

# 4. 모델 학습과정 설정하기
model.compile(optimizer = 'rmsprop', loss = 'binary_crossentropy', metrics = ['accuracy'])

# 5. 모델 학습시키기
hist = model.fit(x_train, y_train, epochs = 1000, batch_size = 64)

# 6. 학습과정 살펴보기
fig, loss_ax = plt.subplots()
acc_ax = loss_ax.twinx()

loss_ax.set_ylim([0.0, 1.0])
acc_ax.set_ylim([0.0, 1.0])

loss_ax.plot(hist.history["loss"], "yellow", label = "train loss")
acc_ax.plot(hist.history["acc"], "blue", label = "train accuracy")

loss_ax.set_xlabel("epoch")
loss_ax.set_ylabel("loss")
acc_ax.set_ylabel("accuracy")

loss_ax.legend(loc = "upper left")
acc_ax.legend(loc = "lower left")

plt.show()

# 7. 모델 평가하기
loss_and_metrics = model.evaluate(x_test, y_test, batch_size = 32)
print("loss_and_metrics : " + str(loss_and_metrics))

[출처] 블록과 함께하는 파이썬 딥러닝 케라스, 김태영 지음, DigitalBooks, p197~198