定义具有多个输入的自定义LSTM

Question

按照教程 编写自定义层我正在尝试实现一个自定义的LSTM层，有多个输入时序。我提供了两个向量 input_1 和 input_2 作为 list [input_1, input_2] 如教程中建议的那样。的 单一输入法 正在工作，但当我改变多个输入的代码时，它抛出了错误。

self.kernel = self.add_weight(shape=(input_shape[0][-1], self.units),
    TypeError: 'NoneType' object is not subscriptable.

我要做什么修改才能消除这个错误？下面是修改后的代码。

class MinimalRNNCell(keras.layers.Layer):
    def __init__(self, units, **kwargs):
        self.units = units
        self.state_size = units
        super(MinimalRNNCell, self).__init__(**kwargs)
    def build(self, input_shape):
        print(type(input_shape))
        self.kernel = self.add_weight(shape=(input_shape[0][-1], self.units),
                                      initializer='uniform',
                                      name='kernel')
        self.recurrent_kernel = self.add_weight(
            shape=(self.units, self.units),
            initializer='uniform',
            name='recurrent_kernel')
        self.built = True
    def call(self, inputs, states):
        prev_output = states[0]
        h = K.dot(inputs[0], self.kernel)
        output = h + K.dot(prev_output, self.recurrent_kernel)
        return output, [output]   

# Let's use this cell in a RNN layer:
cell = MinimalRNNCell(32)
input_1 = keras.Input((None, 5))
input_2 = keras.Input((None, 5))
layer = RNN(cell)
y = layer([input_1, input_2])

Answer 1

错误是因为行。y = layer([input_1, input_2]).

将该行改为 y = layer((input_1, input_2)) (以Tuple of Inputs而不是List of Inputs的形式传递)，可以解决这个错误。

完成工作代码，使用 tf.keras 如下图所示。

from tensorflow import keras
from tensorflow.keras import backend as K
from tensorflow.keras.layers import RNN
import tensorflow as tf

class MinimalRNNCell(tf.keras.layers.Layer):
    def __init__(self, units, **kwargs):
        self.units = units
        self.state_size = units
        #self.state_size = [tf.TensorShape([units])]
        super(MinimalRNNCell, self).__init__(**kwargs)
    def build(self, input_shape):
        print(type(input_shape))
        self.kernel = self.add_weight(shape=(input_shape[0][-1], self.units),
                                      initializer='uniform',
                                      name='kernel')
        self.recurrent_kernel = self.add_weight(
            shape=(self.units, self.units),
            initializer='uniform',
            name='recurrent_kernel')
        self.built = True
    def call(self, inputs, states):
        prev_output = states[0]
        h = K.dot(inputs[0], self.kernel)
        output = h + K.dot(prev_output, self.recurrent_kernel)
        return output, [output]   

# Let's use this cell in a RNN layer:
cell = MinimalRNNCell(32)
input_1 = tf.keras.Input((None, 5))
input_2 = tf.keras.Input((None, 5))
layer = RNN(cell)
y = layer((input_1, input_2))

以上代码的输出是：

<class 'tuple'>

希望能帮到你 祝大家学习愉快!