Keras LSTM:检查模型输入尺寸时出错

时间:2017-03-12 07:30:18

标签: python neural-network deep-learning keras lstm

我是keras的新用户,并尝试实施LSTM模型。对于测试,我声明了如下所示的模型,但由于输入维度的不同而失败。虽然我在这个网站上发现了类似的问题,但我自己找不到自己的错误。

ValueError: 
Error when checking model input: 
expected lstm_input_4 to have 3 dimensions, but got array with shape (300, 100)

我的环境

  • python 3.5.2
  • keras 1.2.0(Theano)

代码

from keras.layers import Input, Dense
from keras.models import Sequential
from keras.layers import LSTM
from keras.optimizers import RMSprop, Adadelta
from keras.layers.wrappers import TimeDistributed
import numpy as np

in_size = 100
out_size = 10
nb_hidden = 8

model = Sequential()
model.add(LSTM(nb_hidden, 
               name='lstm',
               activation='tanh',
               return_sequences=True,
               input_shape=(None, in_size)))
model.add(TimeDistributed(Dense(out_size, activation='softmax')))

adadelta = Adadelta(clipnorm=1.)
model.compile(optimizer=adadelta,
              loss='categorical_crossentropy',
              metrics=['accuracy'])

# create dummy data
data_size = 300
train = np.zeros((data_size, in_size,), dtype=np.float32)
labels = np.zeros((data_size, out_size,), dtype=np.float32)
model.fit(train, labels)

编辑1(在MarcinMożejko的评论之后不起作用)

谢谢MarcinMożejko。但我有类似的错误,如下所示。我更新了虚拟数据以供检查。这段代码出了什么问题?

  

ValueError:检查模型目标时出错:预期   timedistributed_36有3个维度,但得到了有形状的数组   (208,1)

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

data_size = 300
dataset = np.zeros((data_size, feature_size), dtype=np.float32)
dataset_labels = np.zeros((data_size, 1), dtype=np.float32)

train_size = int(data_size * 0.7)
trainX = dataset[0:train_size, :]
trainY = dataset_labels[0:train_size, :]
testX = dataset[train_size:, :]
testY = dataset_labels[train_size:, 0]
trainX, trainY = create_dataset(trainX, trainY)
print(trainX.shape, trainY.shape) # (208, 1, 1) (208, 1)

# in_size = 100
feature_size = 1
out_size = 1
nb_hidden = 8

model = Sequential()
model.add(LSTM(nb_hidden, 
               name='lstm',
               activation='tanh',
               return_sequences=True,
               input_shape=(1, feature_size)))

model.add(TimeDistributed(Dense(out_size, activation='softmax')))
adadelta = Adadelta(clipnorm=1.)
model.compile(optimizer=adadelta,
              loss='categorical_crossentropy',
              metrics=['accuracy'])
model.fit(trainX, trainY, nb_epoch=10, batch_size=1)

1 个答案:

答案 0 :(得分:3)

这是LSTMKeras的一个非常经典的问题。 LSTM输入形状应为2d - 形状为(sequence_length, nb_of_features)。额外的第三个维度来自示例维度 - 因此提供给模型的表格具有形状(nb_of_examples, sequence_length, nb_of_features)。这是您的问题所在。请注意,1-d序列应显示为2-d数组,其形状为(sequence_length, 1)。这应该是LSTM

的输入形状
model.add(LSTM(nb_hidden, 
           name='lstm',
           activation='tanh',
           return_sequences=True,
           input_shape=(in_size, 1)))

请记住reshape输入适当的格式。