长短期记忆模型作回归分析的示例代码 python
包含内容: 源码,全套工具
作者QQ1420527913
from keras.models import Sequential
from keras.layers import LSTM, Dense,Dropout
import numpy as np
import matplotlib.pyplot as plt
data_dim = 16
timesteps = 8
num_classes = 1
model = Sequential()
model.add(LSTM(32, return_sequences=True,
input_shape=(timesteps, data_dim)))
model.add(Dropout(0.5))
model.add(LSTM(32, return_sequences=True))
model.add(Dropout(0.5))
model.add(LSTM(32))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='mae', optimizer='adam')
# Generate dummy training data
x_train = np.random.normal(2,0.5,size=(1000, timesteps, data_dim))
y_train = np.random.normal(2,0.5,size=(1000, num_classes))
# Generate dummy validation data
x_val = np.random.normal(2,0.5,size=(100, timesteps, data_dim))
y_val = np.random.normal(2,0.5,size=(100, num_classes))
history = model.fit(x_train, y_train,
batch_size=64, epochs=50,
validation_data=(x_val, y_val))
# #显示训练中的训练损失和测试损失
plt.plot(history.history['loss'], label='train')
plt.plot(history.history['val_loss'], label='test')
plt.legend()
plt.show()
下载Demo