深入挖掘LSTM Keras

我正在使用LSTM框架对具有四列的传感器数据运行回归问题 . 我还没有使用任何正规化 .

我在下面指定的代码;

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import math
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
from keras import callbacks
from keras.layers import Flatten

# load the dataset
gbx_data = pd.read_csv('/home/prm/Downloads/aggregated_vibration.csv', usecols=[4,5,6,7])
dataset = gbx_data.values
dataset = dataset.astype('float32')

scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)


train_size = int(len(dataset) * 0.63)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
print(len(train), len(test))

def create_dataset(dataset, look_back):
  dataX, dataY = [], []
  for i in range(len(dataset)-look_back-1):
    a = dataset[i:(i+look_back), :]
    dataX.append(a)
    dataY.append(dataset[i + look_back, :])
  return np.array(dataX), np.array(dataY)


look_back = 10
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

trainX = trainX.reshape(trainX.shape[0], look_back, trainX.shape[2])    # model input shape & model output shape will be same always #
testX = testX.reshape(testX.shape[0], look_back, testX.shape[2])

batch_size = 120

class LossHistory(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.losses = []

    def on_epoch_end(self, epoch, logs={}):
        self.losses.append(logs.get('loss'))


model=Sequential()
model.add(LSTM(10, return_sequences=True, input_shape=(look_back, 4), activation='relu'))
model.add(Dropout(0.2))
model.add(LSTM(12, return_sequences=True, input_shape=(look_back, 4), activation='relu'))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(4, activation='relu'))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])
history = LossHistory()
model.fit(trainX, trainY, epochs=10, batch_size=batch_size, callbacks=[history])
print(history.losses)

我想知道以下问题的规格;

• 对于每个纪元结束，我得到了 LossHistory 类的损失 . 如何在每个时代之后获得重量？我知道 model.get_weights() 给了我所有的重量 . 但是我怎样才能在每个时代之后得到它们？

• 如何才能最佳地了解我应该在LSTM和密集层使用哪种激活功能，以便我的数据表现“最佳”并且给我很好的准确性？

• model.get_config() 给了我 'stateful': False . 如果我执行一个有状态的LSTM，实际会发生什么变化并检查哪些值我能理解这个变化？

• 如果 return_sequences=False 会发生什么变化？

• 如何最佳地选择LSTM和密集层的隐藏节点（神经元）的数量？

运行上述代码，10个时期后的损失历史如下，

[0.016399867401633194, 0.0029856997435597997, 0.0021351441705040426, 0.0016288172078515754, 0.0012535296516730061, 0.0010065438170736181, 0.00085688360991555948, 0.0007937529246583822, 0.00073356743746738303, 0.00069794598373472037]

准确度为77％ .

我正在添加几个迭代方法的表 .

对不起如果我问了很多 . 如果可能，请分享您的帮助 .