卷積神經網絡(CNN)可以作爲編解碼器結構中的編碼器。CNN不直接支持序列輸入;相反，一維CNN能夠讀取序列輸入並自動學習顯著特徵。然後可以按照正常情況由LSTM解碼器解釋這些。我們將使用CNN和LSTM的混合模型稱爲cn -LSTM模型，在本例中，我們將在一個編解碼器體系結構中同時使用它們。CNN希望輸入的數據具有與LSTM模型相同的3D結構，儘管多個特性被讀取爲不同的通道，最終具有相同的效果。我們將簡化這個示例，並將重點放在具有單變量輸入的cn - lstm上，但是它也可以很容易地更新爲使用多元輸入，這只是一個練習。與之前一樣，我們將使用由14天的日總功耗組成的輸入序列。我們將爲編碼器定義一個簡單但有效的CNN架構，它由兩個卷積層和一個最大池化層組成，然後將結果扁平化。第一個卷積層讀取輸入序列並將結果投影到特徵圖上。第二層對第一層創建的特徵圖執行相同的操作，試圖放大任何顯著的特徵。我們將在每個卷積層使用64個feature map，讀取內核大小爲3個時間步長的輸入序列。最大池層通過保留最大信號值的1/4來簡化特徵映射。在池化層之後提取的特徵映射被壓扁成一個長向量，然後可以用作解碼過程的輸入。
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
解碼器與前面幾節定義的解碼器相同。唯一的其他變化是將訓練時間設置爲20個。帶有這些更改的build_model()函數如下所示。
# train the model
def build_model(train, n_input):
# prepare data
train_x, train_y = to_supervised(train, n_input)
# define parameters
verbose, epochs, batch_size = 0, 20, 16
n_timesteps, n_features, n_outputs = train_x.shape[1], train_x.shape[2], train_y.shape[1]
# reshape output into [samples, timesteps, features]
train_y = train_y.reshape((train_y.shape[0], train_y.shape[1], 1))
# define model
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(RepeatVector(n_outputs))
model.add(LSTM(200, activation='relu', return_sequences=True))
model.add(TimeDistributed(Dense(100, activation='relu')))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mse', optimizer='adam')
# fit network
model.fit(train_x, train_y, epochs=epochs, batch_size=batch_size, verbose=verbose)
return model
現在我們準備使用CNN編碼器來嘗試編碼器-解碼器架構。下面提供了完整的代碼清單。
# univariate multi-step encoder-decoder cnn-lstm
from math import sqrt
from numpy import split
from numpy import array
from pandas import read_csv
from sklearn.metrics import mean_squared_error
from matplotlib import pyplot
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import LSTM
from keras.layers import RepeatVector
from keras.layers import TimeDistributed
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D
# split a univariate dataset into train/test sets
def split_dataset(data):
# split into standard weeks
train, test = data[1:-328], data[-328:-6]
# restructure into windows of weekly data
train = array(split(train, len(train)/7))
test = array(split(test, len(test)/7))
return train, test
# evaluate one or more weekly forecasts against expected values
def evaluate_forecasts(actual, predicted):
scores = list()
# calculate an RMSE score for each day
for i in range(actual.shape[1]):
# calculate mse
mse = mean_squared_error(actual[:, i], predicted[:, i])
# calculate rmse
rmse = sqrt(mse)
# store
scores.append(rmse)
# calculate overall RMSE
s = 0
for row in range(actual.shape[0]):
for col in range(actual.shape[1]):
s += (actual[row, col] - predicted[row, col])**2
score = sqrt(s / (actual.shape[0] * actual.shape[1]))
return score, scores
# summarize scores
def summarize_scores(name, score, scores):
s_scores = ', '.join(['%.1f' % s for s in scores])
print('%s: [%.3f] %s' % (name, score, s_scores))
# convert history into inputs and outputs
def to_supervised(train, n_input, n_out=7):
# flatten data
data = train.reshape((train.shape[0]*train.shape[1], train.shape[2]))
X, y = list(), list()
in_start = 0
# step over the entire history one time step at a time
for _ in range(len(data)):
# define the end of the input sequence
in_end = in_start + n_input
out_end = in_end + n_out
# ensure we have enough data for this instance
if out_end < len(data):
x_input = data[in_start:in_end, 0]
x_input = x_input.reshape((len(x_input), 1))
X.append(x_input)
y.append(data[in_end:out_end, 0])
# move along one time step
in_start += 1
return array(X), array(y)
# train the model
def build_model(train, n_input):
# prepare data
train_x, train_y = to_supervised(train, n_input)
# define parameters
verbose, epochs, batch_size = 0, 20, 16
n_timesteps, n_features, n_outputs = train_x.shape[1], train_x.shape[2], train_y.shape[1]
# reshape output into [samples, timesteps, features]
train_y = train_y.reshape((train_y.shape[0], train_y.shape[1], 1))
# define model
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(RepeatVector(n_outputs))
model.add(LSTM(200, activation='relu', return_sequences=True))
model.add(TimeDistributed(Dense(100, activation='relu')))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mse', optimizer='adam')
# fit network
model.fit(train_x, train_y, epochs=epochs, batch_size=batch_size, verbose=verbose)
return model
# make a forecast
def forecast(model, history, n_input):
# flatten data
data = array(history)
data = data.reshape((data.shape[0]*data.shape[1], data.shape[2]))
# retrieve last observations for input data
input_x = data[-n_input:, 0]
# reshape into [1, n_input, 1]
input_x = input_x.reshape((1, len(input_x), 1))
# forecast the next week
yhat = model.predict(input_x, verbose=0)
# we only want the vector forecast
yhat = yhat[0]
return yhat
# evaluate a single model
def evaluate_model(train, test, n_input):
# fit model
model = build_model(train, n_input)
# history is a list of weekly data
history = [x for x in train]
# walk-forward validation over each week
predictions = list()
for i in range(len(test)):
# predict the week
yhat_sequence = forecast(model, history, n_input)
# store the predictions
predictions.append(yhat_sequence)
# get real observation and add to history for predicting the next week
history.append(test[i, :])
# evaluate predictions days for each week
predictions = array(predictions)
score, scores = evaluate_forecasts(test[:, :, 0], predictions)
return score, scores
# load the new file
dataset = read_csv('household_power_consumption_days.csv', header=0, infer_datetime_format=True, parse_dates=['datetime'], index_col=['datetime'])
# split into train and test
train, test = split_dataset(dataset.values)
# evaluate model and get scores
n_input = 14
score, scores = evaluate_model(train, test, n_input)
# summarize scores
summarize_scores('lstm', score, scores)
# plot scores
days = ['sun', 'mon', 'tue', 'wed', 'thr', 'fri', 'sat']
pyplot.plot(days, scores, marker='o', label='lstm')
pyplot.show()