Linear Regression 예제 스크립트

Linear Rgression Architecture



import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import SGD.Adam
from tensorflow.keras.layers import Flatten, Dense
import numpy as np

# 모델 생성
x_data = np.array([[..], [..], ..., [..]])
t_data = np.array([..])

# 모델 구축
model = Sequential()
model.add(Dense(1, input_shape(3,), activation = 'linear'))

# 모델 컴파일
model.compile(optimizer = SGD(learning_rate = 1e-2), loss = 'mse')
model.summary()

# 모델 학습
hist = model.fit(x_data, t_data, epochs = 1000)

# 모델 평가 및 예측
test_data [[...], [...], ..., [...]]
ret_val = [2*data[0] - 3*data[1] + 2*data[2] for data in test_data]
prediction_val = model.predict(np.array(test_data))

# 모델 입력
print(model.input)
# 모델 출력
print(model.output)
# 모델 가중치
print(model.weight)

# matplotlib를 이용한 시각화
import matplotlib.pyplot as plt

plt.title('Lostt Trend')
plt.xlabel('epochs')
plt.ylabel('loss')
plt.grid()

plt.plot(hist.history['loss'], label = 'trend loss')
plt.legend(loc = 'best')
plt.show()