我正在学习如何使用 Keras，并且使用 Chollet 的Python 深度学习中的示例，我在标记数据集方面取得了相当大的成功。数据集是约 1000 个时间序列，长度为 3125，具有 3 个潜在类别。
我想超越基本的Dense层，这给了我大约 70% 的预测率，本书继续讨论 LSTM 和 RNN 层。
所有示例似乎都为每个时间序列使用具有多个特征的数据集，因此我正在努力弄清楚如何实现我的数据。
例如，如果我有 1000x3125 时间序列，我如何将其输入到 SimpleRNN 或 LSTM 层之类的东西中？我是否缺少有关这些层功能的一些基本知识？
当前代码：
import pandas as pd
import numpy as np
import os
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM, Dropout, SimpleRNN, Embedding, Reshape
from keras.utils import to_categorical
from keras import regularizers
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
def readData():
# Get labels from the labels.txt file
labels = pd.read_csv('labels.txt', header = None)
labels = labels.values
labels = labels-1
print('One Hot Encoding Data...')
labels = to_categorical(labels)
data = pd.read_csv('ts.txt', header = None)
return data, labels
print('Reading data...')
data, labels = readData()
print('Splitting Data')
data_train, data_test, labels_train, labels_test = train_test_split(data, labels)
print('Building Model...')
#Create model
model = Sequential()
## LSTM / RNN goes here ##
model.add(Dense(3, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print('Training NN...')
history = model.fit(data_train, labels_train, epochs=1000, batch_size=50,
validation_split=0.25,verbose=2)
results = model.evaluate(data_test, labels_test)
predictions = model.predict(data_test)
print(predictions[0].shape)
print(np.sum(predictions[0]))
print(np.argmax(predictions[0]))
print(results)
acc = history.history['acc']
val_acc = history.history['val_acc']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and Validation Accuracy')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()