Question

我正在尝试使用Keras在我的自定义功能集上运行LSTM。我在单独的文件中训练和测试功能。每个csv文件包含11列，最后一列作为类标签。我的数据集中共有40个类。问题是我无法找到第一层正确的input_shape。我已经探索了所有的stackoverflow和github，但仍然无法解决这个问题以下是我的完整代码。

import numpy
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM

numpy.random.seed(7)

train_dataset = numpy.loadtxt("train.csv", delimiter=",")
X_train = train_dataset[:, 0:10]
y_train = train_dataset[:, 10]

test_dataset = numpy.loadtxt("test.csv", delimiter=",")
X_test = test_dataset[:, 0:10]
y_test = test_dataset[:, 10]

model = Sequential()

model.add(LSTM(32, return_sequences=True, input_shape=X_train.shape))
model.add(LSTM(32, return_sequences=True))
model.add(LSTM(32))
model.add(Dense(1, activation='softmax'))
model.compile(loss='mean_squared_error', optimizer='sgd', metrics=['accuracy'])
model.fit(X_train, y_train, batch_size=10, epochs=1)

score, acc = model.evaluate(X_test, y_test, batch_size=10)
print('Test score:', score)
print('Test accuracy:', acc * 100)

无论我在input_shape参数中发生什么变化，我都会在拟合方法的第一个LSTM层中出现错误。

Answer 1

您的输入中没有时间维度。当您的输入具有维度(batch_size, time_step, features)时，RNN的输入应为(batch_size, features)。

如果你想一次使用10列，你应该重新整形数组 numpy.reshape(train_dataset, (-1, train_dataset.shape[1], 1))

试试这段代码：

train_dataset = numpy.loadtxt("train.csv", delimiter=",")
train_dataset = numpy.reshape(train_dataset, (-1, train_dataset.shape[1], 1))

X_train = train_dataset[:, 0:10]
y_train = train_dataset[:, 10]

test_dataset = numpy.loadtxt("test.csv", delimiter=",")
test_dataset = numpy.reshape(test_dataset, (-1, train_dataset.shape[1], 1))

X_test = test_dataset[:, 0:10]
y_test = test_dataset[:, 10]

model = Sequential()

model.add(LSTM(32, return_sequences=True, input_shape=(X_train.shape[1], 1)))
model.add(LSTM(32, return_sequences=True))
model.add(LSTM(32))
model.add(Dense(1, activation='softmax'))
model.compile(loss='mean_squared_error', optimizer='sgd', metrics=['accuracy'])
model.fit(X_train, y_train, batch_size=10, epochs=1)

score, acc = model.evaluate(X_test, y_test, batch_size=10)
print('Test score:', score)
print('Test accuracy:', acc * 100)

keras中LSTM的形状不匹配

1 个答案: