我正在编写一个预测风速的代码。起初，我使用了print(history.history.keys())来打印loss、val_loss、mape和val_mean_absolute_percentage_error的值，但是，它只显示了dict_keys([‘loss’, ‘mape’])。然后，因为它没有val_loss和val_mean_absolute_percentage_error的值，所以它显示了一个KeyError: ‘val_mean_absolute_percentage_error’

你能帮我吗？

数据集

这是我的代码：

from __future__ import print_function from sklearn.metrics import mean_absolute_errorimport mathimport numpy as npimport matplotlib.pyplot as pltfrom pandas import read_csvfrom keras.models import Sequentialfrom keras.layers import Dense, LSTMfrom sklearn.preprocessing import MinMaxScalerfrom sklearn.metrics import mean_squared_error# convert an array of values into a dataset matrixdef create_dataset(dataset, look_back=1):dataX, dataY = [], []for i in range(len(dataset)-look_back-1):a = dataset[i:(i+look_back), 0]dataX.append(a)dataY.append(dataset[i + look_back, 0])return np.array(dataX), np.array(dataY)# fix random seed for reproducibilitynp.random.seed(7)# load the datasetdataframe = read_csv(‘OND_Q4.csv’, usecols=[7], engine=’python’, header=3) dataset = dataframe.valuesprint(dataframe.head)dataset = dataset.astype(‘float32′) # normalize the datasetscaler = MinMaxScaler(feature_range=(0, 1))dataset = scaler.fit_transform(dataset)# split into train and test setstrain_size = int(len(dataset) * 0.7) # Use 70% of data to traintest_size = len(dataset) – train_sizetrain, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]# reshape into X=t and Y=t+1look_back = 1trainX, trainY = create_dataset(train, look_back)testX, testY = create_dataset(test, look_back)# reshape input to be [samples, time steps, features]trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))# create and fit the LSTM networkmodel = Sequential()model.add(LSTM(4, input_shape=(1, look_back)))model.add(Dense(1))#compile modelmodel.compile(loss=’mean_squared_error’, optimizer=’adam’,metrics=[‘mape’])history=model.fit(trainX, trainY, epochs=5, batch_size=1, verbose=2)# list all data in historyprint(history.history.keys())train_MAPE = history.history[‘mape’]valid_MAPE = history.history[‘val_mean_absolute_percentage_error’]train_MSE = history.history[‘loss’]valid_MSE = history.history[‘val_loss’]

谢谢

回答：

您需要在model.fit()中定义一个验证集

您可以使用validation_split=0.2（介于0和1之间的浮点数，用作验证数据的训练数据的比例）

例如：history=model.fit(trainX, trainY, epochs=5, validation_split=0.2, batch_size=1, verbose=2)

或者您可以使用validation_data=（用于在每个epoch结束时评估损失和任何模型指标的数据。模型不会在这组数据上进行训练。validation_data将覆盖validation_split。validation_data可以是：- Numpy数组或张量的元组(x_val, y_val) – Numpy数组的元组(x_val, y_val, val_sample_weights) – 数据集或数据集迭代器）