当我使用 keras 库训练 RNN 时,如何纠正不断出现的维度错误?

How can I correct the dimension error I keep getting when I train RNN using keras library?

我想构建 40-class LSTM classifier 来分析时间序列数据。我有一个从 13 个传感器收集的 13 维实时数据。当我 运行 下面的代码时,我不断收到此错误消息。

ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 arrays but instead got the following list of 241458 arrays: [array([[ 0.64817517, 0.12892013, 0.01879949, 0.00946322, 0.00458952, 0.01668651, 0.04776124, 0.03301365, 0.0360659 , 0.15013408, 0.10112171, 0.05494366, 0.02620634],

RNN代码

from __future__ import print_function
import keras
from keras import metrics
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout, Activation
from keras.utils import np_utils
from keras.layers.normalization import BatchNormalization
from sklearn.cross_validation import train_test_split
import pandas as pd
from keras.callbacks import CSVLogger
from keras.models import load_model
from keras.layers import LSTM
import numpy as np
import tensorflow as tf
from sklearn.preprocessing import LabelEncoder
import keras


def top_k_acc(y_true, y_pred):
    return metrics.top_k_categorical_accuracy(y_true, y_pred, k=5)


# train Parameters
sequence_length = 60
data_dim = 13
num_classes = 40
batch_size = 15000
epochs = 10


# tf.set_random_seed(777)  # reproducibility


def MinMaxScaler(data):
    ''' Min Max Normalization
    Parameters
    ----------
    data : numpy.ndarray
        input data to be normalized
        shape: [Batch size, dimension]
    Returns
    ----------
    data : numpy.ndarry
        normalized data
        shape: [Batch size, dimension]
    References
    ----------
    .. [1] http://sebastianraschka.com/Articles/2014_about_feature_scaling.html
    '''
    numerator = data - np.min(data, 0)
    denominator = np.max(data, 0) - np.min(data, 0)
    # noise term prevents the zero division
    return numerator / (denominator + 1e-7)



# Load data
xy = np.loadtxt('sc_total_for 60s v4.0 test.csv', delimiter=',', skiprows=1)
x = xy[:, 1:14]
x = MinMaxScaler(x)
y = xy[:,0]


# Build a dataset
x_data = []
y_data = []
for i in range(0, len(y) - sequence_length):
    _x = x[i:i + sequence_length]
    _y = y[i + sequence_length]
    # print(_x, "->", _y)
    x_data.append(_x)
    y_data.append(_y)



# One-hot encoding
encoder = LabelEncoder()
encoder.fit(y_data)
encoded_Y = encoder.transform(y_data)
dummy_y = np_utils.to_categorical(encoded_Y)



#train/test split
x_train,x_test,y_train,y_test=train_test_split(x_data,dummy_y,random_state=4,test_size=0.3);
# print(x_train[0],"->",y_train[0])


# Network
model = Sequential()
model.add(LSTM(40, batch_input_shape=(batch_size, sequence_length, data_dim),return_sequences=True))
model.add(LSTM(40, return_sequences=False))
model.add(Dense(40))
model.add(Activation("linear"))

# model.add(Dense(40))
# model.add(Dense(25, init='uniform', activation='relu'))
# model.add(BatchNormalization())
# model.add(Dense(30, init='uniform', activation='relu'))
# model.add(BatchNormalization())
# model.add(Dense(40, init='uniform', activation='softmax'))

model.summary()


model.compile(loss='mean_squared_error',
              optimizer='adam',
              metrics=['accuracy'])


csv_logger = CSVLogger('LSTM 1111.log')


history = model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_data=(x_test, y_test),
                    callbacks=[csv_logger])


score = model.evaluate(x_test, y_test, verbose=0)


predictions=model.predict(x_test)


# model.save('New Model6 save.h5')


#plot_model(model, to_file='model1.png')

# print('Test loss:', score[0])
# print('Test accuracy:', score[1])

问题是:

# Build a dataset
x_data = []
y_data = []
for i in range(0, len(y) - sequence_length):
    _x = x[i:i + sequence_length]
    _y = y[i + sequence_length]
    # print(_x, "->", _y)
    x_data.append(_x)
    y_data.append(_y)

当 Keras 需要 LSTM 的单个三维数组时,您正在为 x_data 构建二维 numpy 数组列表。改为这样做:

num_samples = len(y) - sequence_length

x_data = np.zeros((num_samples, sequence_length, data_dim))
y_data = np.zeros((num_samples))

for i in range(num_samples):
    x_data[i] = x[i:i + sequence_length]
    y_data[i] = y[i + sequence_length]