Keras LSTM 训练。如何塑造我的输入数据？

Question

我有一个包含 3000 个观察值的数据集。每个观察由 3 个长度为 200 个样本的时间序列组成。作为输出，我有 5 个类标签。

所以我构建训练作为测试集如下：

test_split = round(num_samples * 3 / 4)
X_train = X_all[:test_split, :, :] # Start upto just before test_split
y_train = y_all[:test_split]
X_test = X_all[test_split:, :, :] # From test_split to end
y_test = y_all[test_split:]

# Print shapes and class labels
print(X_train.shape)
print(y_train.shape)


> (2250, 200, 3)
> (22250, 5)

我使用 Keras 功能 API 构建我的网络：

from keras.models import  Model
from keras.layers import Dense, Activation, Input, Dropout, concatenate
from keras.layers.recurrent import LSTM
from keras.constraints import maxnorm
from keras.optimizers import SGD
from keras.callbacks import EarlyStopping

series_len = 200
num_RNN_neurons = 64
ch1 = Input(shape=(series_len, 1), name='ch1')
ch2 = Input(shape=(series_len, 1), name='ch2')
ch3 = Input(shape=(series_len, 1), name='ch3')

ch1_layer = LSTM(num_RNN_neurons, return_sequences=False)(ch1)
ch2_layer = LSTM(num_RNN_neurons, return_sequences=False)(ch2)
ch3_layer = LSTM(num_RNN_neurons, return_sequences=False)(ch3)


visible = concatenate([
    ch1_layer,
    ch2_layer,
    ch3_layer])


hidden1 = Dense(30, activation='linear', name='weighted_average_channels')(visible)
output = Dense(num_classes, activation='softmax')(hidden1)

model = Model(inputs= [ch1, ch2, ch3], outputs=output)

# Compile model
model.compile(loss='categorical_crossentropy', optimizer=SGD(), metrics=['accuracy'])
monitor = EarlyStopping(monitor='val_loss', min_delta=1e-4, patience=5, verbose=1, mode='auto')

然后，我尝试拟合模型：

# Fit the model
model.fit(X_train, y_train, 
          epochs=epochs, 
          batch_size=batch_size,
          validation_data=(X_test, y_test),
          callbacks=[monitor],
          verbose=1)

我收到以下错误：

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 3 array(s), but instead got the following list of 1 arrays...

我应该如何重塑我的数据以解决问题？

Answer 1

您神奇地假设具有 3 个时间序列的单个输入 X_train 将分成 4 个通道并分配给不同的输入。好吧，这不会发生，这就是错误所抱怨的。您有 1 个输入：

ch123_in = Input(shape=(series_len, 3), name='ch123')
latent = LSTM(num_RNN_neurons)(ch123_in)
hidden1 = Dense(30, activation='linear', name='weighted_average_channels')(latent)

通过将系列合并到单个 LSTM 中，该模型也可以拾取跨时间序列的关系。现在你的目标形状必须是y_train.shape == (2250, 5)，第一个维度必须匹配X_train.shape[0]。

另一点是Dense 层具有线性激活，这几乎没有用，因为它不提供任何非线性。您可能想要使用像 relu 这样的非线性激活函数。