在Keras中设置LSTM和CuDNNLSTM的参数

Question

我开始学习Keras，对LSTM有些困惑。我不知道输入参数是什么，比如括号（n）中的第一个参数和input_shape

我的数据集是数字的，它有30列，29列是特征，1列是输出（1和0）

DataFrame shape (23991, 30)
x_train shape (19192, 29)
y_train shape (19192,)
x_test shape (4799, 29)
y_test shape (4799,)

基于此，参数在我的图层中应该是什么样子

第一:

model = Sequential()
model.add(LSTM((?), input_shape = ?, return_sequences = ?, activation = ?))
model.add(Dropout(0.01))
model.add(Dense(1, activation='sigmoid')) 

第二：

model = Sequential()
model.add(LSTM((?), input_shape = ?, return_sequences = ?, activation = ?))
model.add(LSTM((?), input_shape = ?, return_sequences = ?, activation = ?))
model.add(Dropout(0.01))
model.add(Dense(1, activation='sigmoid')) 

如果我使用例如CuDNNLSTM，这些参数是否相同

Answer 1

x_train shape (19192, 29)
y_train shape (19192,)
x_test shape (4799, 29)
y_test shape (4799,)

如果您有熊猫数据帧，请将它们转换为numpy数组

x_train = x_train.to_numpy()
y_train = y_train.to_numpy()

x_test = x_test.to_numpy()
y_test = y_test.to_numpy()

首先，您需要重塑数据

x_train = x_train.reshape(19192, 29, 1)
y_train = y_train.reshape(19192,1)
x_test = x_test.reshape(4799, 29, 1)
y_test = y_test.reshape(4799,1)

现在，LSTM的尺寸通常为：

0 - Samples. One sequence is one sample. A batch is comprised of one or more samples.
1 - Time Steps. One time step is one point of observation in the sample.
2 - Features. One feature is one observation at a time step.

因此，第三个1我们添加了一个维度来对应特征

LSTM输入形状将为（29,1）（29=时间步长，1=每个时间序列的特征数量（同样为简单起见，您可以将其视为CNN中的通道数量）

model = Sequential()
model.add(LSTM(units = 10, input_shape = (29,1), return_sequences = False)) # keep other parameters default if you're not sure
model.add(Dropout(0.01))
model.add(Dense(1, activation='sigmoid')) 

观察，我们为第一层添加了return_srquence=True，但对于第二层LSTM，我们没有。原因是LSTM需要3D数据（批次、时间、特征），而Dense需要2D数据（批次、特征），当我们看到return_srquence=True时，我们将3D数据发送到下一层进行Dense，而不是发送2D数据

model = Sequential()
model.add(LSTM(units = 10, input_shape = (29,1), return_sequences = True))
model.add(LSTM(units = 10, return_sequences = False))
model.add(Dropout(0.01))
model.add(Dense(1, activation='sigmoid'))